diff --git a/.devcontainer/Dockerfile b/.devcontainer/Dockerfile index 379f6310..02f580a0 100644 --- a/.devcontainer/Dockerfile +++ b/.devcontainer/Dockerfile @@ -1,10 +1,10 @@ -# [Choice] Python version (use -bullseye variants on local arm64/Apple Silicon): 3, 3.10, 3.9, 3.8, 3.7, 3.6, 3-bullseye, 3.10-bullseye, 3.9-bullseye, 3.8-bullseye, 3.7-bullseye, 3.6-bullseye, 3-buster, 3.10-buster, 3.9-buster, 3.8-buster, 3.7-buster, 3.6-buster +# [Choice] Python version (use -bullseye variants on local arm64/Apple Silicon): 3, 3.10, 3-bullseye, 3.10-bullseye, 3-buster, 3.10-buster ARG VARIANT=3-bullseye -FROM --platform=linux/amd64 python:3.8 +FROM --platform=linux/amd64 python:3.10 RUN apt-get update && export DEBIAN_FRONTEND=noninteractive \ # Remove imagemagick due to https://security-tracker.debian.org/tracker/CVE-2019-10131 - && apt-get purge -y imagemagick imagemagick-6-common + && apt-get purge -y imagemagick imagemagick-6-common # Temporary: Upgrade python packages due to https://cve.mitre.org/cgi-bin/cvename.cgi?name=CVE-2022-40897 # They are installed by the base image (python) which does not have the patch. @@ -25,4 +25,4 @@ RUN apt-get update && export DEBIAN_FRONTEND=noninteractive \ # && apt-get -y install --no-install-recommends # [Optional] Uncomment this line to install global node packages. -# RUN su vscode -c "source /usr/local/share/nvm/nvm.sh && npm install -g " 2>&1 \ No newline at end of file +# RUN su vscode -c "source /usr/local/share/nvm/nvm.sh && npm install -g " 2>&1 diff --git a/.env.template b/.env.template index eeff2907..60edecd6 100644 --- a/.env.template +++ b/.env.template @@ -1,174 +1,197 @@ ################################################################################ ### AUTO-GPT - GENERAL SETTINGS ################################################################################ -# EXECUTE_LOCAL_COMMANDS - Allow local command execution (Example: False) -EXECUTE_LOCAL_COMMANDS=False -# BROWSE_CHUNK_MAX_LENGTH - When browsing website, define the length of chunk stored in memory -BROWSE_CHUNK_MAX_LENGTH=8192 -# BROWSE_SUMMARY_MAX_TOKEN - Define the maximum length of the summary generated by GPT agent when browsing website -BROWSE_SUMMARY_MAX_TOKEN=300 -# USER_AGENT - Define the user-agent used by the requests library to browse website (string) + +## EXECUTE_LOCAL_COMMANDS - Allow local command execution (Default: False) +## RESTRICT_TO_WORKSPACE - Restrict file operations to workspace ./auto_gpt_workspace (Default: True) +# EXECUTE_LOCAL_COMMANDS=False +# RESTRICT_TO_WORKSPACE=True + +## USER_AGENT - Define the user-agent used by the requests library to browse website (string) # USER_AGENT="Mozilla/5.0 (Macintosh; Intel Mac OS X 10_15_4) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/83.0.4103.97 Safari/537.36" -# AI_SETTINGS_FILE - Specifies which AI Settings file to use (defaults to ai_settings.yaml) -AI_SETTINGS_FILE=ai_settings.yaml -# USE_WEB_BROWSER - Sets the web-browser drivers to use with selenium (defaults to chrome). -# Note: set this to either 'chrome', 'firefox', or 'safari' depending on your current browser -# USE_WEB_BROWSER=chrome + +## AI_SETTINGS_FILE - Specifies which AI Settings file to use (defaults to ai_settings.yaml) +# AI_SETTINGS_FILE=ai_settings.yaml ################################################################################ ### LLM PROVIDER ################################################################################ ### OPENAI -# OPENAI_API_KEY - OpenAI API Key (Example: my-openai-api-key) -# TEMPERATURE - Sets temperature in OpenAI (Default: 0) -# USE_AZURE - Use Azure OpenAI or not (Default: False) +## OPENAI_API_KEY - OpenAI API Key (Example: my-openai-api-key) +## TEMPERATURE - Sets temperature in OpenAI (Default: 0) +## USE_AZURE - Use Azure OpenAI or not (Default: False) OPENAI_API_KEY=your-openai-api-key -TEMPERATURE=0 -USE_AZURE=False +# TEMPERATURE=0 +# USE_AZURE=False ### AZURE -# cleanup azure env as already moved to `azure.yaml.template` +# moved to `azure.yaml.template` ################################################################################ ### LLM MODELS ################################################################################ -# SMART_LLM_MODEL - Smart language model (Default: gpt-4) -# FAST_LLM_MODEL - Fast language model (Default: gpt-3.5-turbo) -SMART_LLM_MODEL=gpt-4 -FAST_LLM_MODEL=gpt-3.5-turbo +## SMART_LLM_MODEL - Smart language model (Default: gpt-4) +## FAST_LLM_MODEL - Fast language model (Default: gpt-3.5-turbo) +# SMART_LLM_MODEL=gpt-4 +# FAST_LLM_MODEL=gpt-3.5-turbo ### LLM MODEL SETTINGS -# FAST_TOKEN_LIMIT - Fast token limit for OpenAI (Default: 4000) -# SMART_TOKEN_LIMIT - Smart token limit for OpenAI (Default: 8000) -# When using --gpt3only this needs to be set to 4000. -FAST_TOKEN_LIMIT=4000 -SMART_TOKEN_LIMIT=8000 +## FAST_TOKEN_LIMIT - Fast token limit for OpenAI (Default: 4000) +## SMART_TOKEN_LIMIT - Smart token limit for OpenAI (Default: 8000) +## When using --gpt3only this needs to be set to 4000. +# FAST_TOKEN_LIMIT=4000 +# SMART_TOKEN_LIMIT=8000 ################################################################################ ### MEMORY ################################################################################ ### MEMORY_BACKEND - Memory backend type -# local - Default -# pinecone - Pinecone (if configured) -# redis - Redis (if configured) -MEMORY_BACKEND=local +## local - Default +## pinecone - Pinecone (if configured) +## redis - Redis (if configured) +## milvus - Milvus (if configured) +## MEMORY_INDEX - Name of index created in Memory backend (Default: auto-gpt) +# MEMORY_BACKEND=local +# MEMORY_INDEX=auto-gpt ### PINECONE -# PINECONE_API_KEY - Pinecone API Key (Example: my-pinecone-api-key) -# PINECONE_ENV - Pinecone environment (region) (Example: us-west-2) -PINECONE_API_KEY=your-pinecone-api-key -PINECONE_ENV=your-pinecone-region +## PINECONE_API_KEY - Pinecone API Key (Example: my-pinecone-api-key) +## PINECONE_ENV - Pinecone environment (region) (Example: us-west-2) +# PINECONE_API_KEY=your-pinecone-api-key +# PINECONE_ENV=your-pinecone-region ### REDIS -# REDIS_HOST - Redis host (Default: localhost) -# REDIS_PORT - Redis port (Default: 6379) -# REDIS_PASSWORD - Redis password (Default: "") -# WIPE_REDIS_ON_START - Wipes data / index on start (Default: False) -# MEMORY_INDEX - Name of index created in Redis database (Default: auto-gpt) -REDIS_HOST=localhost -REDIS_PORT=6379 -REDIS_PASSWORD= -WIPE_REDIS_ON_START=False -MEMORY_INDEX=auto-gpt +## REDIS_HOST - Redis host (Default: localhost, use "redis" for docker-compose) +## REDIS_PORT - Redis port (Default: 6379) +## REDIS_PASSWORD - Redis password (Default: "") +## WIPE_REDIS_ON_START - Wipes data / index on start (Default: True) +# REDIS_HOST=localhost +# REDIS_PORT=6379 +# REDIS_PASSWORD= +# WIPE_REDIS_ON_START=True ### WEAVIATE -# MEMORY_BACKEND - Use 'weaviate' to use Weaviate vector storage -# WEAVIATE_HOST - Weaviate host IP -# WEAVIATE_PORT - Weaviate host port -# WEAVIATE_PROTOCOL - Weaviate host protocol (e.g. 'http') -# USE_WEAVIATE_EMBEDDED - Whether to use Embedded Weaviate -# WEAVIATE_EMBEDDED_PATH - File system path were to persist data when running Embedded Weaviate -# WEAVIATE_USERNAME - Weaviate username -# WEAVIATE_PASSWORD - Weaviate password -# WEAVIATE_API_KEY - Weaviate API key if using API-key-based authentication -# MEMORY_INDEX - Name of index to create in Weaviate -WEAVIATE_HOST="127.0.0.1" -WEAVIATE_PORT=8080 -WEAVIATE_PROTOCOL="http" -USE_WEAVIATE_EMBEDDED=False -WEAVIATE_EMBEDDED_PATH="/home/me/.local/share/weaviate" -WEAVIATE_USERNAME= -WEAVIATE_PASSWORD= -WEAVIATE_API_KEY= -MEMORY_INDEX=AutoGpt +## MEMORY_BACKEND - Use 'weaviate' to use Weaviate vector storage +## WEAVIATE_HOST - Weaviate host IP +## WEAVIATE_PORT - Weaviate host port +## WEAVIATE_PROTOCOL - Weaviate host protocol (e.g. 'http') +## USE_WEAVIATE_EMBEDDED - Whether to use Embedded Weaviate +## WEAVIATE_EMBEDDED_PATH - File system path were to persist data when running Embedded Weaviate +## WEAVIATE_USERNAME - Weaviate username +## WEAVIATE_PASSWORD - Weaviate password +## WEAVIATE_API_KEY - Weaviate API key if using API-key-based authentication +# WEAVIATE_HOST="127.0.0.1" +# WEAVIATE_PORT=8080 +# WEAVIATE_PROTOCOL="http" +# USE_WEAVIATE_EMBEDDED=False +# WEAVIATE_EMBEDDED_PATH="/home/me/.local/share/weaviate" +# WEAVIATE_USERNAME= +# WEAVIATE_PASSWORD= +# WEAVIATE_API_KEY= ### MILVUS -# MILVUS_ADDR - Milvus remote address (e.g. localhost:19530) -# MILVUS_COLLECTION - Milvus collection, -# change it if you want to start a new memory and retain the old memory. -MILVUS_ADDR=your-milvus-cluster-host-port -MILVUS_COLLECTION=autogpt +## MILVUS_ADDR - Milvus remote address (e.g. localhost:19530) +## MILVUS_COLLECTION - Milvus collection, +## change it if you want to start a new memory and retain the old memory. +# MILVUS_ADDR=your-milvus-cluster-host-port +# MILVUS_COLLECTION=autogpt ################################################################################ ### IMAGE GENERATION PROVIDER ################################################################################ ### OPEN AI -# IMAGE_PROVIDER - Image provider (Example: dalle) -IMAGE_PROVIDER=dalle +## IMAGE_PROVIDER - Image provider (Example: dalle) +## IMAGE_SIZE - Image size (Example: 256) +## DALLE: 256, 512, 1024 +# IMAGE_PROVIDER=dalle +# IMAGE_SIZE=256 ### HUGGINGFACE -# STABLE DIFFUSION -# (Default URL: https://api-inference.huggingface.co/models/CompVis/stable-diffusion-v1-4) -# Set in image_gen.py) -# HUGGINGFACE_API_TOKEN - HuggingFace API token (Example: my-huggingface-api-token) -HUGGINGFACE_API_TOKEN=your-huggingface-api-token +## HUGGINGFACE_IMAGE_MODEL - Text-to-image model from Huggingface (Default: CompVis/stable-diffusion-v1-4) +## HUGGINGFACE_API_TOKEN - HuggingFace API token (Example: my-huggingface-api-token) +# HUGGINGFACE_IMAGE_MODEL=CompVis/stable-diffusion-v1-4 +# HUGGINGFACE_API_TOKEN=your-huggingface-api-token + +### STABLE DIFFUSION WEBUI +## SD_WEBUI_AUTH - Stable diffusion webui username:password pair (Example: username:password) +## SD_WEBUI_URL - Stable diffusion webui API URL (Example: http://127.0.0.1:7860) +# SD_WEBUI_AUTH= +# SD_WEBUI_URL=http://127.0.0.1:7860 ################################################################################ ### AUDIO TO TEXT PROVIDER ################################################################################ ### HUGGINGFACE -HUGGINGFACE_AUDIO_TO_TEXT_MODEL=facebook/wav2vec2-base-960h +# HUGGINGFACE_AUDIO_TO_TEXT_MODEL=facebook/wav2vec2-base-960h ################################################################################ ### GIT Provider for repository actions ################################################################################ ### GITHUB -# GITHUB_API_KEY - Github API key / PAT (Example: github_pat_123) -# GITHUB_USERNAME - Github username -GITHUB_API_KEY=github_pat_123 -GITHUB_USERNAME=your-github-username +## GITHUB_API_KEY - Github API key / PAT (Example: github_pat_123) +## GITHUB_USERNAME - Github username +# GITHUB_API_KEY=github_pat_123 +# GITHUB_USERNAME=your-github-username ################################################################################ -### SEARCH PROVIDER +### WEB BROWSING ################################################################################ +### BROWSER +## HEADLESS_BROWSER - Whether to run the browser in headless mode (default: True) +## USE_WEB_BROWSER - Sets the web-browser driver to use with selenium (default: chrome). +## Note: set this to either 'chrome', 'firefox', or 'safari' depending on your current browser +# HEADLESS_BROWSER=True +# USE_WEB_BROWSER=chrome +## BROWSE_CHUNK_MAX_LENGTH - When browsing website, define the length of chunks to summarize (in number of tokens, excluding the response. 75 % of FAST_TOKEN_LIMIT is usually wise ) +# BROWSE_CHUNK_MAX_LENGTH=3000 +## BROWSE_SPACY_LANGUAGE_MODEL is used to split sentences. Install additional languages via pip, and set the model name here. Example Chinese: python -m spacy download zh_core_web_sm +# BROWSE_SPACY_LANGUAGE_MODEL=en_core_web_sm + ### GOOGLE -# GOOGLE_API_KEY - Google API key (Example: my-google-api-key) -# CUSTOM_SEARCH_ENGINE_ID - Custom search engine ID (Example: my-custom-search-engine-id) -GOOGLE_API_KEY=your-google-api-key -CUSTOM_SEARCH_ENGINE_ID=your-custom-search-engine-id +## GOOGLE_API_KEY - Google API key (Example: my-google-api-key) +## CUSTOM_SEARCH_ENGINE_ID - Custom search engine ID (Example: my-custom-search-engine-id) +# GOOGLE_API_KEY=your-google-api-key +# CUSTOM_SEARCH_ENGINE_ID=your-custom-search-engine-id ################################################################################ ### TTS PROVIDER ################################################################################ ### MAC OS -# USE_MAC_OS_TTS - Use Mac OS TTS or not (Default: False) -USE_MAC_OS_TTS=False +## USE_MAC_OS_TTS - Use Mac OS TTS or not (Default: False) +# USE_MAC_OS_TTS=False ### STREAMELEMENTS -# USE_BRIAN_TTS - Use Brian TTS or not (Default: False) -USE_BRIAN_TTS=False +## USE_BRIAN_TTS - Use Brian TTS or not (Default: False) +# USE_BRIAN_TTS=False ### ELEVENLABS -# ELEVENLABS_API_KEY - Eleven Labs API key (Example: my-elevenlabs-api-key) -# ELEVENLABS_VOICE_1_ID - Eleven Labs voice 1 ID (Example: my-voice-id-1) -# ELEVENLABS_VOICE_2_ID - Eleven Labs voice 2 ID (Example: my-voice-id-2) -ELEVENLABS_API_KEY=your-elevenlabs-api-key -ELEVENLABS_VOICE_1_ID=your-voice-id-1 -ELEVENLABS_VOICE_2_ID=your-voice-id-2 +## ELEVENLABS_API_KEY - Eleven Labs API key (Example: my-elevenlabs-api-key) +## ELEVENLABS_VOICE_1_ID - Eleven Labs voice 1 ID (Example: my-voice-id-1) +## ELEVENLABS_VOICE_2_ID - Eleven Labs voice 2 ID (Example: my-voice-id-2) +# ELEVENLABS_API_KEY=your-elevenlabs-api-key +# ELEVENLABS_VOICE_1_ID=your-voice-id-1 +# ELEVENLABS_VOICE_2_ID=your-voice-id-2 ################################################################################ -### TWITTER API +### TWITTER API ################################################################################ -TW_CONSUMER_KEY= -TW_CONSUMER_SECRET= -TW_ACCESS_TOKEN= -TW_ACCESS_TOKEN_SECRET= +# TW_CONSUMER_KEY= +# TW_CONSUMER_SECRET= +# TW_ACCESS_TOKEN= +# TW_ACCESS_TOKEN_SECRET= + +################################################################################ +### ALLOWLISTED PLUGINS +################################################################################ + +#ALLOWLISTED_PLUGINS - Sets the listed plugins that are allowed (Example: plugin1,plugin2,plugin3) +ALLOWLISTED_PLUGINS= diff --git a/.envrc b/.envrc new file mode 100644 index 00000000..a7ad7263 --- /dev/null +++ b/.envrc @@ -0,0 +1,4 @@ +# Upon entering directory, direnv requests user permission once to automatically load project dependencies onwards. +# Eliminating the need of running "nix develop github:superherointj/nix-auto-gpt" for Nix users to develop/use Auto-GPT. + +[[ -z $IN_NIX_SHELL ]] && use flake github:superherointj/nix-auto-gpt diff --git a/.flake8 b/.flake8 index c456b393..77976224 100644 --- a/.flake8 +++ b/.flake8 @@ -1,12 +1,12 @@ [flake8] max-line-length = 88 -extend-ignore = E203 +select = "E303, W293, W291, W292, E305, E231, E302" exclude = .tox, __pycache__, *.pyc, .env - venv/* - .venv/* - reports/* - dist/* \ No newline at end of file + venv*/*, + .venv/*, + reports/*, + dist/*, diff --git a/.github/ISSUE_TEMPLATE/1.bug.yml b/.github/ISSUE_TEMPLATE/1.bug.yml index 7f1d2771..6645142e 100644 --- a/.github/ISSUE_TEMPLATE/1.bug.yml +++ b/.github/ISSUE_TEMPLATE/1.bug.yml @@ -2,6 +2,20 @@ name: Bug report 🐛 description: Create a bug report for Auto-GPT. labels: ['status: needs triage'] body: + - type: markdown + attributes: + value: | + ### ⚠️ Before you continue + * Check out our [backlog], [roadmap] and join our [discord] to discuss what's going on + * If you need help, you can ask in the [discussions] section or in [#tech-support] + * **Throughly search the [existing issues] before creating a new one** + + [backlog]: https://github.com/orgs/Significant-Gravitas/projects/1 + [roadmap]: https://github.com/orgs/Significant-Gravitas/projects/2 + [discord]: https://discord.gg/autogpt + [discussions]: https://github.com/Significant-Gravitas/Auto-GPT/discussions + [#tech-support]: https://discord.com/channels/1092243196446249134/1092275629602394184 + [existing issues]: https://github.com/Significant-Gravitas/Auto-GPT/issues?q=is%3Aissue - type: checkboxes attributes: label: ⚠️ Search for existing issues first ⚠️ @@ -28,14 +42,32 @@ body: - Provide commit-hash (`git rev-parse HEAD` gets it) - If it's a pip/packages issue, provide pip version, python version - If it's a crash, provide traceback. - - type: checkboxes + - type: dropdown attributes: - label: GPT-3 or GPT-4 + label: Which Operating System are you using? + description: > + Please select the operating system you were using to run Auto-GPT when this problem occurred. + options: + - Windows + - Linux + - MacOS + - Docker + - Devcontainer / Codespace + - Windows Subsystem for Linux (WSL) + - Other (Please specify in your problem) + validations: + required: true + - type: dropdown + attributes: + label: GPT-3 or GPT-4? description: > If you are using Auto-GPT with `--gpt3only`, your problems may be caused by - the limitations of GPT-3.5 + the [limitations](https://github.com/Significant-Gravitas/Auto-GPT/issues?q=is%3Aissue+label%3A%22AI+model+limitation%22) of GPT-3.5. options: - - label: I am using Auto-GPT with GPT-3 (GPT-3.5) + - GPT-3.5 + - GPT-4 + validations: + required: true - type: textarea attributes: label: Steps to reproduce 🕹 @@ -52,9 +84,34 @@ body: - type: textarea attributes: label: Your prompt 📝 - description: | - If applicable please provide the prompt you are using. You can find your last-used prompt in last_run_ai_settings.yaml. + description: > + If applicable please provide the prompt you are using. Your prompt is stored in your `ai_settings.yaml` file. value: | ```yaml # Paste your prompt here ``` + - type: textarea + attributes: + label: Your Logs 📒 + description: | + Please include the log showing your error and the command that caused it, if applicable. + You can copy it from your terminal or from `logs/activity.log`. + This will help us understand your issue better! + +
+ Example + ```log + INFO NEXT ACTION: COMMAND = execute_shell ARGUMENTS = {'command_line': 'some_command'} + INFO -=-=-=-=-=-=-= COMMAND AUTHORISED BY USER -=-=-=-=-=-=-= + Traceback (most recent call last): + File "/home/anaconda3/lib/python3.9/site-packages/openai/api_requestor.py", line 619, in _interpret_response + self._interpret_response_line( + File "/home/anaconda3/lib/python3.9/site-packages/openai/api_requestor.py", line 682, in _interpret_response_line + raise self.handle_error_response( + openai.error.InvalidRequestError: This model's maximum context length is 8191 tokens, however you requested 10982 tokens (10982 in your prompt; 0 for the completion). Please reduce your prompt; or completion length. + ``` +
+ value: | + ```log + + ``` diff --git a/.github/PULL_REQUEST_TEMPLATE.md b/.github/PULL_REQUEST_TEMPLATE.md index c355965a..a4f28a3d 100644 --- a/.github/PULL_REQUEST_TEMPLATE.md +++ b/.github/PULL_REQUEST_TEMPLATE.md @@ -1,3 +1,10 @@ + + - + diff --git a/.github/workflows/benchmark.yml b/.github/workflows/benchmark.yml index c5a42b2c..53b6e7a0 100644 --- a/.github/workflows/benchmark.yml +++ b/.github/workflows/benchmark.yml @@ -9,11 +9,11 @@ jobs: environment: benchmark strategy: matrix: - python-version: [3.8] + python-version: ['3.10', '3.11'] steps: - name: Check out repository - uses: actions/checkout@v2 + uses: actions/checkout@v3 - name: Set up Python ${{ matrix.python-version }} uses: actions/setup-python@v2 diff --git a/.github/workflows/ci.yml b/.github/workflows/ci.yml index 39f3aea9..b37e7f00 100644 --- a/.github/workflows/ci.yml +++ b/.github/workflows/ci.yml @@ -2,23 +2,54 @@ name: Python CI on: push: - branches: - - master + branches: [master] pull_request: - branches: - - master + branches: [master] + +concurrency: + group: ${{ format('ci-{0}', format('pr-{0}', github.event.pull_request.number) || github.sha) }} + cancel-in-progress: ${{ github.event_name == 'pull_request' }} jobs: - build: + lint: runs-on: ubuntu-latest - - strategy: - matrix: - python-version: [3.8] + env: + min-python-version: '3.10' steps: - name: Check out repository - uses: actions/checkout@v2 + uses: actions/checkout@v3 + + - name: Set up Python ${{ env.min-python-version }} + uses: actions/setup-python@v2 + with: + python-version: ${{ env.min-python-version }} + + - name: Install dependencies + run: | + python -m pip install --upgrade pip + pip install -r requirements.txt + + - name: Lint with flake8 + run: flake8 + + - name: Check black formatting + run: black . --check + if: success() || failure() + + - name: Check isort formatting + run: isort . --check + if: success() || failure() + + test: + runs-on: ubuntu-latest + strategy: + matrix: + python-version: ['3.10', '3.11'] + + steps: + - name: Check out repository + uses: actions/checkout@v3 - name: Set up Python ${{ matrix.python-version }} uses: actions/setup-python@v2 @@ -30,10 +61,6 @@ jobs: python -m pip install --upgrade pip pip install -r requirements.txt - - name: Lint with flake8 - continue-on-error: false - run: flake8 autogpt/ tests/ --select E303,W293,W291,W292,E305,E231,E302 - - name: Run unittest tests with coverage run: | pytest --cov=autogpt --without-integration --without-slow-integration @@ -42,3 +69,4 @@ jobs: run: | coverage report coverage xml + if: success() || failure() diff --git a/.github/workflows/docker-image.yml b/.github/workflows/docker-image.yml index 9c77098e..2fcf6401 100644 --- a/.github/workflows/docker-image.yml +++ b/.github/workflows/docker-image.yml @@ -5,6 +5,9 @@ on: branches: [ "master" ] pull_request: branches: [ "master" ] +concurrency: + group: ${{ format('docker-ci-{0}', github.event.pull_request.number || github.sha) }} + cancel-in-progress: true jobs: diff --git a/.github/workflows/dockerhub-imagepush.yml b/.github/workflows/dockerhub-imagepush.yml index 6805eebf..165f6265 100644 --- a/.github/workflows/dockerhub-imagepush.yml +++ b/.github/workflows/dockerhub-imagepush.yml @@ -1,8 +1,8 @@ name: Push Docker Image on Release on: - push: - branches: [ "stable" ] + release: + types: [published,edited] jobs: @@ -19,6 +19,13 @@ jobs: run: | docker login -u $DOCKER_USER -p $DOCKER_PASSWORD - name: Build the Docker image - run: docker build . --file Dockerfile --tag ${{secrets.DOCKER_USER}}/auto-gpt:$(git describe --tags `git rev-list --tags --max-count=1`) + run: | + tag_v=$(git describe --tags $(git rev-list --tags --max-count=1)) + tag=$(echo $tag_v | sed 's/v//') + docker build . --file Dockerfile --tag ${{secrets.DOCKER_USER}}/auto-gpt:${tag} - name: Docker Push - run: docker push ${{secrets.DOCKER_USER}}/auto-gpt + run: | + tag_v2=$(git describe --tags $(git rev-list --tags --max-count=1)) + tag2=$(echo $tag_v | sed 's/v//') + docker push ${{secrets.DOCKER_USER}}/auto-gpt:${tag2} + diff --git a/.github/workflows/pr-label.yml b/.github/workflows/pr-label.yml new file mode 100644 index 00000000..f1b200b0 --- /dev/null +++ b/.github/workflows/pr-label.yml @@ -0,0 +1,48 @@ +name: "Pull Request auto-label" +on: + # So that PRs touching the same files as the push are updated + push: + # So that the `dirtyLabel` is removed if conflicts are resolve + # We recommend `pull_request_target` so that github secrets are available. + # In `pull_request` we wouldn't be able to change labels of fork PRs + pull_request_target: + types: [opened, synchronize] +concurrency: + group: ${{ format('pr-label-{0}', github.event.pull_request.number || github.sha) }} + cancel-in-progress: true + +jobs: + conflicts: + runs-on: ubuntu-latest + permissions: + contents: read + pull-requests: write + steps: + - name: Update PRs with conflict labels + uses: eps1lon/actions-label-merge-conflict@releases/2.x + with: + dirtyLabel: "conflicts" + #removeOnDirtyLabel: "PR: ready to ship" + repoToken: "${{ secrets.GITHUB_TOKEN }}" + commentOnDirty: "This pull request has conflicts with the base branch, please resolve those so we can evaluate the pull request." + commentOnClean: "Conflicts have been resolved! 🎉 A maintainer will review the pull request shortly." + + size: + if: ${{ github.event_name == 'pull_request_target' }} + permissions: + issues: write + pull-requests: write + runs-on: ubuntu-latest + steps: + - uses: codelytv/pr-size-labeler@v1.7.0 + with: + GITHUB_TOKEN: ${{ secrets.GITHUB_TOKEN }} + s_label: "size/s" + s_max_size: "10" + m_label: "size/m" + m_max_size: "50" + l_label: "size/l" + l_max_size: "200" + xl_label: "size/xl" + fail_if_xl: "false" + github_api_url: "api.github.com" diff --git a/.github/workflows/sponsors_readme.yml b/.github/workflows/sponsors_readme.yml new file mode 100644 index 00000000..fffdbd4d --- /dev/null +++ b/.github/workflows/sponsors_readme.yml @@ -0,0 +1,25 @@ +name: Generate Sponsors README +on: + workflow_dispatch: + schedule: + - cron: '0 */12 * * *' +jobs: + deploy: + runs-on: ubuntu-latest + steps: + - name: Checkout 🛎️ + uses: actions/checkout@v2 + - name: Generate Sponsors 💖 + uses: JamesIves/github-sponsors-readme-action@v1 + with: + token: ${{ secrets.README_UPDATER_PAT }} + file: 'README.md' + minimum: 2500 + maximum: 99999 + + - name: Deploy to GitHub Pages 🚀 + uses: JamesIves/github-pages-deploy-action@v4 + with: + branch: master + folder: '.' + token: ${{ secrets.README_UPDATER_PAT }} diff --git a/.gitignore b/.gitignore index 2220ef6e..0c277d89 100644 --- a/.gitignore +++ b/.gitignore @@ -10,7 +10,6 @@ auto_gpt_workspace/* *.mpeg .env azure.yaml -outputs/* ai_settings.yaml last_run_ai_settings.yaml .vscode @@ -127,6 +126,7 @@ celerybeat.pid *.sage.py # Environments +.direnv/ .env .venv env/ @@ -156,3 +156,8 @@ vicuna-* # mac .DS_Store + +openai/ + +# news +CURRENT_BULLETIN.md \ No newline at end of file diff --git a/.isort.cfg b/.isort.cfg index 8ad53a86..17eab482 100644 --- a/.isort.cfg +++ b/.isort.cfg @@ -1,10 +1,10 @@ [settings] profile = black multi_line_output = 3 -include_trailing_comma = True +include_trailing_comma = true force_grid_wrap = 0 -use_parentheses = True -ensure_newline_before_comments = True +use_parentheses = true +ensure_newline_before_comments = true line_length = 88 -skip = venv,env,node_modules,.env,.venv,dist -sections = FUTURE,STDLIB,THIRDPARTY,FIRSTPARTY,LOCALFOLDER \ No newline at end of file +sections = FUTURE,STDLIB,THIRDPARTY,FIRSTPARTY,LOCALFOLDER +skip = .tox,__pycache__,*.pyc,venv*/*,reports,venv,env,node_modules,.env,.venv,dist diff --git a/.pre-commit-config.yaml b/.pre-commit-config.yaml index dd1d0ec9..3722b25e 100644 --- a/.pre-commit-config.yaml +++ b/.pre-commit-config.yaml @@ -1,39 +1,32 @@ repos: - - repo: https://github.com/sourcery-ai/sourcery - rev: v1.1.0 # Get the latest tag from https://github.com/sourcery-ai/sourcery/tags - hooks: - - id: sourcery - - repo: https://github.com/pre-commit/pre-commit-hooks rev: v0.9.2 hooks: - id: check-added-large-files - args: [ '--maxkb=500' ] + args: ['--maxkb=500'] - id: check-byte-order-marker - id: check-case-conflict - id: check-merge-conflict - id: check-symlinks - id: debug-statements - - - repo: local + + - repo: https://github.com/pycqa/isort + rev: 5.12.0 hooks: - id: isort - name: isort-local - entry: isort - language: python - types: [ python ] - exclude: .+/(dist|.venv|venv|build)/.+ - pass_filenames: true + language_version: python3.10 + + - repo: https://github.com/psf/black + rev: 23.3.0 + hooks: - id: black - name: black-local - entry: black - language: python - types: [ python ] - exclude: .+/(dist|.venv|venv|build)/.+ - pass_filenames: true + language_version: python3.10 + + - repo: local + hooks: - id: pytest-check name: pytest-check entry: pytest --cov=autogpt --without-integration --without-slow-integration language: system pass_filenames: false - always_run: true \ No newline at end of file + always_run: true diff --git a/.sourcery.yaml b/.sourcery.yaml index a7f5b9d7..da171e75 100644 --- a/.sourcery.yaml +++ b/.sourcery.yaml @@ -30,7 +30,7 @@ rule_settings: - refactoring - suggestion - comment - python_version: '3.9' # A string specifying the lowest Python version your project supports. Sourcery will not suggest refactorings requiring a higher Python version. + python_version: '3.10' # A string specifying the lowest Python version your project supports. Sourcery will not suggest refactorings requiring a higher Python version. # rules: # A list of custom rules Sourcery will include in its analysis. # - id: no-print-statements @@ -68,4 +68,4 @@ rule_settings: # proxy: # url: # ssl_certs_file: -# no_ssl_verify: false \ No newline at end of file +# no_ssl_verify: false diff --git a/BULLETIN.md b/BULLETIN.md new file mode 100644 index 00000000..735048dd --- /dev/null +++ b/BULLETIN.md @@ -0,0 +1,2 @@ +Welcome to Auto-GPT! We'll keep you informed of the latest news and features by printing messages here. +If you don't wish to see this message, you can run Auto-GPT with the --skip-news flag \ No newline at end of file diff --git a/CONTRIBUTING.md b/CONTRIBUTING.md index b2a2490c..79169a0c 100644 --- a/CONTRIBUTING.md +++ b/CONTRIBUTING.md @@ -20,6 +20,12 @@ This document provides guidelines and best practices to help you contribute effe By participating in this project, you agree to abide by our [Code of Conduct](CODE_OF_CONDUCT.md). Please read it to understand the expectations we have for everyone who contributes to this project. +## 📢 A Quick Word +Right now we will not be accepting any Contributions that add non-essential commands to Auto-GPT. + +However, you absolutely can still add these commands to Auto-GPT in the form of plugins. Please check out this [template](https://github.com/Significant-Gravitas/Auto-GPT-Plugin-Template). +> ⚠️ Plugin support is expected to ship within the week. You can follow PR #757 for more updates! + ## Getting Started To start contributing, follow these steps: diff --git a/Dockerfile b/Dockerfile index 9886d742..83961549 100644 --- a/Dockerfile +++ b/Dockerfile @@ -1,10 +1,20 @@ # Use an official Python base image from the Docker Hub -FROM python:3.11-slim +FROM python:3.10-slim # Install git RUN apt-get -y update RUN apt-get -y install git chromium-driver +# Install Xvfb and other dependencies for headless browser testing +RUN apt-get update \ + && apt-get install -y wget gnupg2 libgtk-3-0 libdbus-glib-1-2 dbus-x11 xvfb ca-certificates + +# Install Firefox / Chromium +RUN wget -q -O - https://dl-ssl.google.com/linux/linux_signing_key.pub | apt-key add - \ + && echo "deb [arch=amd64] http://dl.google.com/linux/chrome/deb/ stable main" >> /etc/apt/sources.list.d/google-chrome.list \ + && apt-get update \ + && apt-get install -y chromium firefox-esr + # Set environment variables ENV PIP_NO_CACHE_DIR=yes \ PYTHONUNBUFFERED=1 \ @@ -17,8 +27,9 @@ RUN chown appuser:appuser /home/appuser USER appuser # Copy the requirements.txt file and install the requirements -COPY --chown=appuser:appuser requirements-docker.txt . -RUN pip install --no-cache-dir --user -r requirements-docker.txt +COPY --chown=appuser:appuser requirements.txt . +RUN sed -i '/Items below this point will not be included in the Docker Image/,$d' requirements.txt && \ + pip install --no-cache-dir --user -r requirements.txt # Copy the application files COPY --chown=appuser:appuser autogpt/ ./autogpt diff --git a/README.md b/README.md index 71957748..743584e5 100644 --- a/README.md +++ b/README.md @@ -32,16 +32,21 @@ Development of this free, open-source project is made possible by all the -

Enterprise Sponsors

-InfluxData    Roost.AI    NucleiAI    AlgohashFe    

+
-

Individual Sponsors

-

-robinicus  prompthero  crizzler  tob-le-rone  FSTatSBS  toverly1  ddtarazona  Nalhos  Kazamario  pingbotan  indoor47  AuroraHolding  kreativai  hunteraraujo  Explorergt92  judegomila   -thepok -  SpacingLily  merwanehamadi  m  zkonduit  maxxflyer  tekelsey  digisomni  nocodeclarity  tjarmain -Dradstone  CrypteorCapital  avy-ai  shawnharmsen  sunchongren  DailyBotHQ  mathewhawkins  MediConCenHK  kMag410  nicoguyon  Mobivs  jazgarewal  marv-technology  rapidstartup  Brodie0  lucas-chu  rejunity  comet-ml  ColinConwell  cfarquhar  ikarosai  ChrisDMT  Odin519Tomas  vkozacek  belharethsami  sultanmeghji  scryptedinc  johnculkin  RealChrisSean  fruition  jd3655  Web3Capital  allenstecat  tob-le-rone  SwftCoins  MetaPath01  joaomdmoura  ternary5  refinery1  josephcmiller2  webbcolton  tommygeee  lmaugustin  garythebat  Cameron-Fulton  angiaou  caitlynmeeks  MBassi91  Daniel1357  omphos  abhinav-pandey29  DataMetis  concreit  st617  RThaweewat  KiaArmani  Pythagora-io  AryaXAI  fabrietech  jun784  Mr-Bishop42  rickscode  projectonegames  rocks6  GalaxyVideoAgency  thisisjeffchen  TheStoneMX  txtr99  ZERO-A-ONE  

+Zilliz +Roost.AI +NucleiAI +Algohash +TypingMind +
+ +
+
+ + +

robinicus  arthur-x88  knifour  prompthero  digisomni  sultanmeghji  allenstecat  jd3655  tullytim  shawnharmsen  DailyBotHQ  thepok  jacobyoby  MediConCenHK  concreit  tob-le-rone  Heitechsoft  jsolejr  angiaou  kenndanielso  FSTatSBS  bentoml  cfarquhar  MBassi91  Daniel1357  iddelacruz  josephjacks  arjunb023  johnculkin  indoor47  rapidstartup  RawBanana  comet-ml  MetaPath01  maxxflyer  Nalhos  KiaArmani  SparkplanAI  jenius-eagle  toverly1  st617  judegomila  tekelsey  morcos  turintech  Mr-Bishop42  yx3110  rocks6  Odin519Tomas  Cameron-Fulton  ddtarazona  saten-private  cxs  fruition  Kazamario  MayurVirkar  ikarosai  RThaweewat  founderblocks-sils  RealChrisSean  marv-technology  merwanehamadi  fabrietech  tommi-joentakanen  CrypteorCapital  tommygeee  Josecodesalot  thisisjeffchen  ternary5  CrazySwami  omphos  Explorergt92  DataMetis  belharethsami  rickscode  Brodie0  ChrisDMT  humungasaurus  lucas-chu  avy-ai  ASmithOWL  chatgpt-prompts  ZERO-A-ONE  jazgarewal  mathewhawkins  crizzler  Pythagora-io  neverinstall  Dradstone  sunchongren  pingbotan  dexterityx  CatsMeow492  joaomdmoura  zkonduit  Mobivs  doverhq  projectonegames  nnkostov  TheStoneMX  ColinConwell  hunteraraujo  ciscodebs  rejunity  SpacingLily  lazzacapital  SwftCoins  ZoneSixGames  eelbaz  m  caitlynmeeks  AcountoOU  vkozacek  goldenrecursion  scryptedinc  lmaugustin  webbcolton  VoiceBeer  Web3Capital  garythebat  txtr99  ntwrite  AryaXAI  kreativai  abhinav-pandey29  anvarazizov  AuroraHolding  0xmatchmaker  nicoguyon  MatthewAgs  kMag410  josephcmiller2  AIdevelopersAI  GalaxyVideoAgency  jun784  Partender  tjarmain  horazius  nocodeclarity  refinery1  jondwillis  CarmenCocoa  LeeRobidas  wenfengwang  

## 🚀 Features @@ -65,8 +70,21 @@ Development of this free, open-source project is made possible by all the Billing](./docs/imgs/openai-api-key-billing-paid-account.png) + +#### **PLEASE ENSURE YOU HAVE DONE THIS STEP BEFORE PROCEEDING, OTHERWISE NOTHING WILL WORK!** + ## 💾 Installation To install Auto-GPT, follow these steps: @@ -79,7 +97,7 @@ _To execute the following commands, open a CMD, Bash, or Powershell window by na you can download the [latest stable release](https://github.com/Significant-Gravitas/Auto-GPT/releases/latest) (`Source code (zip)`, bottom of the page). ```bash - git clone https://github.com/Significant-Gravitas/Auto-GPT.git + git clone -b stable https://github.com/Significant-Gravitas/Auto-GPT.git ``` 3. Navigate to the directory where the repository was downloaded @@ -123,11 +141,15 @@ _To execute the following commands, open a CMD, Bash, or Powershell window by na ## 🔧 Usage -1. Run `autogpt` Python module in your terminal +1. Run `autogpt` Python module in your terminal. + ```bash + # On Linux of Mac: + ./run.sh - ``` - python -m autogpt - ``` + # On Windows: + .\run.bat + ``` + Running with `--help` after `.\run.bat` lists all the possible command line arguments you can pass. 2. After each action, choose from options to authorize command(s), exit the program, or provide feedback to the AI. @@ -207,18 +229,6 @@ python -m autogpt --speak - Adam : pNInz6obpgDQGcFmaJgB - Sam : yoZ06aMxZJJ28mfd3POQ - -## OpenAI API Keys Configuration - -Obtain your OpenAI API key from: https://platform.openai.com/account/api-keys. - -To use OpenAI API key for Auto-GPT, you NEED to have billing set up (AKA paid account). - -You can set up paid account at https://platform.openai.com/account/billing/overview. - -![For OpenAI API key to work, set up paid account at OpenAI API > Billing](./docs/imgs/openai-api-key-billing-paid-account.png) - - ## 🔍 Google API Keys Configuration This section is optional, use the official google api if you are having issues with error 429 when running a google search. @@ -253,6 +263,22 @@ export GOOGLE_API_KEY="YOUR_GOOGLE_API_KEY" export CUSTOM_SEARCH_ENGINE_ID="YOUR_CUSTOM_SEARCH_ENGINE_ID" ``` +## Plugins + +See https://github.com/Significant-Gravitas/Auto-GPT-Plugin-Template for the template of the plugins. + +⚠️💀 WARNING 💀⚠️: Review the code of any plugin you use, this allows for any Python to be executed and do malicious things. Like stealing your API keys. + +Drop the repo's zipfile in the plugins folder. + +![Download Zip](https://raw.githubusercontent.com/BillSchumacher/Auto-GPT/master/plugin.png) + +If you add the plugins class name to the `ALLOWLISTED_PLUGINS` in the `.env` you will not be prompted otherwise you'll be warned before loading the plugin: + +``` +ALLOWLISTED_PLUGINS=example-plugin1,example-plugin2,example-plugin3 +``` + ## Setting Your Cache Type By default, Auto-GPT is going to use LocalCache instead of redis or Pinecone. @@ -325,7 +351,7 @@ export MEMORY_BACKEND="pinecone" ### Milvus Setup -[Milvus](https://milvus.io/) is a open-source, high scalable vector database to storage huge amount of vector-based memory and provide fast relevant search. +[Milvus](https://milvus.io/) is an open-source, highly scalable vector database to store huge amounts of vector-based memory and provide fast relevant search. - setup milvus database, keep your pymilvus version and milvus version same to avoid compatible issues. - setup by open source [Install Milvus](https://milvus.io/docs/install_standalone-operator.md) @@ -341,6 +367,14 @@ export MEMORY_BACKEND="pinecone" [Weaviate](https://weaviate.io/) is an open-source vector database. It allows to store data objects and vector embeddings from ML-models and scales seamlessly to billion of data objects. [An instance of Weaviate can be created locally (using Docker), on Kubernetes or using Weaviate Cloud Services](https://weaviate.io/developers/weaviate/quickstart). Although still experimental, [Embedded Weaviate](https://weaviate.io/developers/weaviate/installation/embedded) is supported which allows the Auto-GPT process itself to start a Weaviate instance. To enable it, set `USE_WEAVIATE_EMBEDDED` to `True` and make sure you `pip install "weaviate-client>=3.15.4"`. +#### Install the Weaviate client + +Install the Weaviate client before usage. + +``` +$ pip install weaviate-client +``` + #### Setting up environment variables In your `.env` file set the following: diff --git a/autogpt/__main__.py b/autogpt/__main__.py index 5f462234..128f9eea 100644 --- a/autogpt/__main__.py +++ b/autogpt/__main__.py @@ -1,50 +1,5 @@ -"""Main script for the autogpt package.""" -import logging -from colorama import Fore -from autogpt.agent.agent import Agent -from autogpt.args import parse_arguments -from autogpt.config import Config, check_openai_api_key -from autogpt.logs import logger -from autogpt.memory import get_memory -from autogpt.prompt import construct_prompt -# Load environment variables from .env file - - -def main() -> None: - """Main function for the script""" - cfg = Config() - # TODO: fill in llm values here - check_openai_api_key() - parse_arguments() - logger.set_level(logging.DEBUG if cfg.debug_mode else logging.INFO) - ai_name = "" - system_prompt = construct_prompt() - # print(prompt) - # Initialize variables - full_message_history = [] - next_action_count = 0 - # Make a constant: - triggering_prompt = ( - "Determine which next command to use, and respond using the" - " format specified above:" - ) - # Initialize memory and make sure it is empty. - # this is particularly important for indexing and referencing pinecone memory - memory = get_memory(cfg, init=True) - logger.typewriter_log( - f"Using memory of type:", Fore.GREEN, f"{memory.__class__.__name__}" - ) - logger.typewriter_log(f"Using Browser:", Fore.GREEN, cfg.selenium_web_browser) - agent = Agent( - ai_name=ai_name, - memory=memory, - full_message_history=full_message_history, - next_action_count=next_action_count, - system_prompt=system_prompt, - triggering_prompt=triggering_prompt, - ) - agent.start_interaction_loop() - +"""Auto-GPT: A GPT powered AI Assistant""" +import autogpt.cli if __name__ == "__main__": - main() + autogpt.cli.main() diff --git a/autogpt/agent/agent.py b/autogpt/agent/agent.py index dca614c7..189338f5 100644 --- a/autogpt/agent/agent.py +++ b/autogpt/agent/agent.py @@ -1,10 +1,10 @@ from colorama import Fore, Style -from autogpt.app import execute_command, get_command +from autogpt.app import execute_command, get_command from autogpt.chat import chat_with_ai, create_chat_message from autogpt.config import Config -from autogpt.json_fixes.master_json_fix_method import fix_json_using_multiple_techniques -from autogpt.json_validation.validate_json import validate_json +from autogpt.json_utils.json_fix_llm import fix_json_using_multiple_techniques +from autogpt.json_utils.utilities import validate_json from autogpt.logs import logger, print_assistant_thoughts from autogpt.speech import say_text from autogpt.spinner import Spinner @@ -19,18 +19,25 @@ class Agent: memory: The memory object to use. full_message_history: The full message history. next_action_count: The number of actions to execute. - system_prompt: The system prompt is the initial prompt that defines everything the AI needs to know to achieve its task successfully. - Currently, the dynamic and customizable information in the system prompt are ai_name, description and goals. + system_prompt: The system prompt is the initial prompt that defines everything + the AI needs to know to achieve its task successfully. + Currently, the dynamic and customizable information in the system prompt are + ai_name, description and goals. - triggering_prompt: The last sentence the AI will see before answering. For Auto-GPT, this prompt is: - Determine which next command to use, and respond using the format specified above: - The triggering prompt is not part of the system prompt because between the system prompt and the triggering - prompt we have contextual information that can distract the AI and make it forget that its goal is to find the next task to achieve. + triggering_prompt: The last sentence the AI will see before answering. + For Auto-GPT, this prompt is: + Determine which next command to use, and respond using the format specified + above: + The triggering prompt is not part of the system prompt because between the + system prompt and the triggering + prompt we have contextual information that can distract the AI and make it + forget that its goal is to find the next task to achieve. SYSTEM PROMPT CONTEXTUAL INFORMATION (memory, previous conversations, anything relevant) TRIGGERING PROMPT - The triggering prompt reminds the AI about its short term meta task (defining the next task) + The triggering prompt reminds the AI about its short term meta task + (defining the next task) """ def __init__( @@ -39,6 +46,8 @@ class Agent: memory, full_message_history, next_action_count, + command_registry, + config, system_prompt, triggering_prompt, ): @@ -46,6 +55,8 @@ class Agent: self.memory = memory self.full_message_history = full_message_history self.next_action_count = next_action_count + self.command_registry = command_registry + self.config = config self.system_prompt = system_prompt self.triggering_prompt = triggering_prompt @@ -73,6 +84,7 @@ class Agent: # Send message to AI, get response with Spinner("Thinking... "): assistant_reply = chat_with_ai( + self, self.system_prompt, self.triggering_prompt, self.full_message_history, @@ -81,22 +93,25 @@ class Agent: ) # TODO: This hardcodes the model to use GPT3.5. Make this an argument assistant_reply_json = fix_json_using_multiple_techniques(assistant_reply) + for plugin in cfg.plugins: + if not plugin.can_handle_post_planning(): + continue + assistant_reply_json = plugin.post_planning(self, assistant_reply_json) # Print Assistant thoughts if assistant_reply_json != {}: - validate_json(assistant_reply_json, 'llm_response_format_1') + validate_json(assistant_reply_json, "llm_response_format_1") # Get command name and arguments try: print_assistant_thoughts(self.ai_name, assistant_reply_json) command_name, arguments = get_command(assistant_reply_json) - # command_name, arguments = assistant_reply_json_valid["command"]["name"], assistant_reply_json_valid["command"]["args"] if cfg.speak_mode: say_text(f"I want to execute {command_name}") except Exception as e: logger.error("Error: \n", str(e)) if not cfg.continuous_mode and self.next_action_count == 0: - ### GET USER AUTHORIZATION TO EXECUTE COMMAND ### + # ### GET USER AUTHORIZATION TO EXECUTE COMMAND ### # Get key press: Prompt the user to press enter to continue or escape # to exit logger.typewriter_log( @@ -115,9 +130,12 @@ class Agent: console_input = clean_input( Fore.MAGENTA + "Input:" + Style.RESET_ALL ) - if console_input.lower().rstrip() == "y": + if console_input.lower().strip() == "y": user_input = "GENERATE NEXT COMMAND JSON" break + elif console_input.lower().strip() == "": + print("Invalid input format.") + continue elif console_input.lower().startswith("y -"): try: self.next_action_count = abs( @@ -165,30 +183,46 @@ class Agent: elif command_name == "human_feedback": result = f"Human feedback: {user_input}" else: - result = ( - f"Command {command_name} returned: " - f"{execute_command(command_name, arguments)}" + for plugin in cfg.plugins: + if not plugin.can_handle_pre_command(): + continue + command_name, arguments = plugin.pre_command( + command_name, arguments + ) + command_result = execute_command( + self.command_registry, + command_name, + arguments, + self.config.prompt_generator, ) + result = f"Command {command_name} returned: " f"{command_result}" + + for plugin in cfg.plugins: + if not plugin.can_handle_post_command(): + continue + result = plugin.post_command(command_name, result) if self.next_action_count > 0: self.next_action_count -= 1 - - memory_to_add = ( - f"Assistant Reply: {assistant_reply} " - f"\nResult: {result} " - f"\nHuman Feedback: {user_input} " - ) - - self.memory.add(memory_to_add) - - # Check if there's a result from the command append it to the message - # history - if result is not None: - self.full_message_history.append(create_chat_message("system", result)) - logger.typewriter_log("SYSTEM: ", Fore.YELLOW, result) - else: - self.full_message_history.append( - create_chat_message("system", "Unable to execute command") - ) - logger.typewriter_log( - "SYSTEM: ", Fore.YELLOW, "Unable to execute command" + if command_name != "do_nothing": + memory_to_add = ( + f"Assistant Reply: {assistant_reply} " + f"\nResult: {result} " + f"\nHuman Feedback: {user_input} " ) + + self.memory.add(memory_to_add) + + # Check if there's a result from the command append it to the message + # history + if result is not None: + self.full_message_history.append( + create_chat_message("system", result) + ) + logger.typewriter_log("SYSTEM: ", Fore.YELLOW, result) + else: + self.full_message_history.append( + create_chat_message("system", "Unable to execute command") + ) + logger.typewriter_log( + "SYSTEM: ", Fore.YELLOW, "Unable to execute command" + ) diff --git a/autogpt/agent/agent_manager.py b/autogpt/agent/agent_manager.py index e4bfb126..9a62ef61 100644 --- a/autogpt/agent/agent_manager.py +++ b/autogpt/agent/agent_manager.py @@ -1,8 +1,11 @@ """Agent manager for managing GPT agents""" from __future__ import annotations +from typing import List, Union + +from autogpt.config.config import Config, Singleton from autogpt.llm_utils import create_chat_completion -from autogpt.config.config import Singleton +from autogpt.types.openai import Message class AgentManager(metaclass=Singleton): @@ -11,6 +14,7 @@ class AgentManager(metaclass=Singleton): def __init__(self): self.next_key = 0 self.agents = {} # key, (task, full_message_history, model) + self.cfg = Config() # Create new GPT agent # TODO: Centralise use of create_chat_completion() to globally enforce token limit @@ -26,19 +30,32 @@ class AgentManager(metaclass=Singleton): Returns: The key of the new agent """ - messages = [ + messages: List[Message] = [ {"role": "user", "content": prompt}, ] - + for plugin in self.cfg.plugins: + if not plugin.can_handle_pre_instruction(): + continue + if plugin_messages := plugin.pre_instruction(messages): + messages.extend(iter(plugin_messages)) # Start GPT instance agent_reply = create_chat_completion( model=model, messages=messages, ) - # Update full message history messages.append({"role": "assistant", "content": agent_reply}) + plugins_reply = "" + for i, plugin in enumerate(self.cfg.plugins): + if not plugin.can_handle_on_instruction(): + continue + if plugin_result := plugin.on_instruction(messages): + sep = "\n" if i else "" + plugins_reply = f"{plugins_reply}{sep}{plugin_result}" + + if plugins_reply and plugins_reply != "": + messages.append({"role": "assistant", "content": plugins_reply}) key = self.next_key # This is done instead of len(agents) to make keys unique even if agents # are deleted @@ -46,6 +63,11 @@ class AgentManager(metaclass=Singleton): self.agents[key] = (task, messages, model) + for plugin in self.cfg.plugins: + if not plugin.can_handle_post_instruction(): + continue + agent_reply = plugin.post_instruction(agent_reply) + return key, agent_reply def message_agent(self, key: str | int, message: str) -> str: @@ -63,15 +85,37 @@ class AgentManager(metaclass=Singleton): # Add user message to message history before sending to agent messages.append({"role": "user", "content": message}) + for plugin in self.cfg.plugins: + if not plugin.can_handle_pre_instruction(): + continue + if plugin_messages := plugin.pre_instruction(messages): + for plugin_message in plugin_messages: + messages.append(plugin_message) + # Start GPT instance agent_reply = create_chat_completion( model=model, messages=messages, ) - # Update full message history messages.append({"role": "assistant", "content": agent_reply}) + plugins_reply = agent_reply + for i, plugin in enumerate(self.cfg.plugins): + if not plugin.can_handle_on_instruction(): + continue + if plugin_result := plugin.on_instruction(messages): + sep = "\n" if i else "" + plugins_reply = f"{plugins_reply}{sep}{plugin_result}" + # Update full message history + if plugins_reply and plugins_reply != "": + messages.append({"role": "assistant", "content": plugins_reply}) + + for plugin in self.cfg.plugins: + if not plugin.can_handle_post_instruction(): + continue + agent_reply = plugin.post_instruction(agent_reply) + return agent_reply def list_agents(self) -> list[tuple[str | int, str]]: @@ -84,7 +128,7 @@ class AgentManager(metaclass=Singleton): # Return a list of agent keys and their tasks return [(key, task) for key, (task, _, _) in self.agents.items()] - def delete_agent(self, key: Union[str, int]) -> bool: + def delete_agent(self, key: str | int) -> bool: """Delete an agent from the agent manager Args: diff --git a/autogpt/app.py b/autogpt/app.py index 19c075f0..cf8e29a3 100644 --- a/autogpt/app.py +++ b/autogpt/app.py @@ -1,32 +1,15 @@ """ Command and Control """ import json -from typing import List, NoReturn, Union, Dict +from typing import Dict, List, NoReturn, Union + from autogpt.agent.agent_manager import AgentManager -from autogpt.commands.evaluate_code import evaluate_code -from autogpt.commands.google_search import google_official_search, google_search -from autogpt.commands.improve_code import improve_code -from autogpt.commands.write_tests import write_tests -from autogpt.config import Config -from autogpt.commands.image_gen import generate_image -from autogpt.commands.audio_text import read_audio_from_file +from autogpt.commands.command import CommandRegistry, command from autogpt.commands.web_requests import scrape_links, scrape_text -from autogpt.commands.execute_code import execute_python_file, execute_shell -from autogpt.commands.file_operations import ( - append_to_file, - delete_file, - read_file, - search_files, - write_to_file, - download_file -) -from autogpt.json_fixes.parsing import fix_and_parse_json +from autogpt.config import Config from autogpt.memory import get_memory from autogpt.processing.text import summarize_text +from autogpt.prompts.generator import PromptGenerator from autogpt.speech import say_text -from autogpt.commands.web_selenium import browse_website -from autogpt.commands.git_operations import clone_repository -from autogpt.commands.twitter import send_tweet - CFG = Config() AGENT_MANAGER = AgentManager() @@ -104,7 +87,12 @@ def map_command_synonyms(command_name: str): return command_name -def execute_command(command_name: str, arguments): +def execute_command( + command_registry: CommandRegistry, + command_name: str, + arguments, + prompt: PromptGenerator, +): """Execute the command and return the result Args: @@ -112,96 +100,32 @@ def execute_command(command_name: str, arguments): arguments (dict): The arguments for the command Returns: - str: The result of the command""" - memory = get_memory(CFG) - + str: The result of the command + """ try: - command_name = map_command_synonyms(command_name) - if command_name == "google": - # Check if the Google API key is set and use the official search method - # If the API key is not set or has only whitespaces, use the unofficial - # search method - key = CFG.google_api_key - if key and key.strip() and key != "your-google-api-key": - google_result = google_official_search(arguments["input"]) - return google_result - else: - google_result = google_search(arguments["input"]) + cmd = command_registry.commands.get(command_name) - # google_result can be a list or a string depending on the search results - if isinstance(google_result, list): - safe_message = [google_result_single.encode('utf-8', 'ignore') for google_result_single in google_result] - else: - safe_message = google_result.encode('utf-8', 'ignore') + # If the command is found, call it with the provided arguments + if cmd: + return cmd(**arguments) + + # TODO: Remove commands below after they are moved to the command registry. + command_name = map_command_synonyms(command_name.lower()) + + if command_name == "memory_add": + return get_memory(CFG).add(arguments["string"]) - return str(safe_message) - elif command_name == "memory_add": - return memory.add(arguments["string"]) - elif command_name == "start_agent": - return start_agent( - arguments["name"], arguments["task"], arguments["prompt"] - ) - elif command_name == "message_agent": - return message_agent(arguments["key"], arguments["message"]) - elif command_name == "list_agents": - return list_agents() - elif command_name == "delete_agent": - return delete_agent(arguments["key"]) - elif command_name == "get_text_summary": - return get_text_summary(arguments["url"], arguments["question"]) - elif command_name == "get_hyperlinks": - return get_hyperlinks(arguments["url"]) - elif command_name == "clone_repository": - return clone_repository( - arguments["repository_url"], arguments["clone_path"] - ) - elif command_name == "read_file": - return read_file(arguments["file"]) - elif command_name == "write_to_file": - return write_to_file(arguments["file"], arguments["text"]) - elif command_name == "append_to_file": - return append_to_file(arguments["file"], arguments["text"]) - elif command_name == "delete_file": - return delete_file(arguments["file"]) - elif command_name == "search_files": - return search_files(arguments["directory"]) - elif command_name == "download_file": - if not CFG.allow_downloads: - return "Error: You do not have user authorization to download files locally." - return download_file(arguments["url"], arguments["file"]) - elif command_name == "browse_website": - return browse_website(arguments["url"], arguments["question"]) # TODO: Change these to take in a file rather than pasted code, if # non-file is given, return instructions "Input should be a python - # filepath, write your code to file and try again" - elif command_name == "evaluate_code": - return evaluate_code(arguments["code"]) - elif command_name == "improve_code": - return improve_code(arguments["suggestions"], arguments["code"]) - elif command_name == "write_tests": - return write_tests(arguments["code"], arguments.get("focus")) - elif command_name == "execute_python_file": # Add this command - return execute_python_file(arguments["file"]) - elif command_name == "execute_shell": - if CFG.execute_local_commands: - return execute_shell(arguments["command_line"]) - else: - return ( - "You are not allowed to run local shell commands. To execute" - " shell commands, EXECUTE_LOCAL_COMMANDS must be set to 'True' " - "in your config. Do not attempt to bypass the restriction." - ) - elif command_name == "read_audio_from_file": - return read_audio_from_file(arguments["file"]) - elif command_name == "generate_image": - return generate_image(arguments["prompt"]) - elif command_name == "send_tweet": - return send_tweet(arguments["text"]) + # filepath, write your code to file and try again elif command_name == "do_nothing": return "No action performed." elif command_name == "task_complete": shutdown() else: + for command in prompt.commands: + if command_name == command["label"] or command_name == command["name"]: + return command["function"](*arguments.values()) return ( f"Unknown command '{command_name}'. Please refer to the 'COMMANDS'" " list for available commands and only respond in the specified JSON" @@ -211,8 +135,11 @@ def execute_command(command_name: str, arguments): return f"Error: {str(e)}" +@command( + "get_text_summary", "Get text summary", '"url": "", "question": ""' +) def get_text_summary(url: str, question: str) -> str: - """Return the results of a google search + """Return the results of a Google search Args: url (str): The url to scrape @@ -226,8 +153,9 @@ def get_text_summary(url: str, question: str) -> str: return f""" "Result" : {summary}""" +@command("get_hyperlinks", "Get text summary", '"url": ""') def get_hyperlinks(url: str) -> Union[str, List[str]]: - """Return the results of a google search + """Return the results of a Google search Args: url (str): The url to scrape @@ -244,6 +172,11 @@ def shutdown() -> NoReturn: quit() +@command( + "start_agent", + "Start GPT Agent", + '"name": "", "task": "", "prompt": ""', +) def start_agent(name: str, task: str, prompt: str, model=CFG.fast_llm_model) -> str: """Start an agent with a given name, task, and prompt @@ -276,6 +209,7 @@ def start_agent(name: str, task: str, prompt: str, model=CFG.fast_llm_model) -> return f"Agent {name} created with key {key}. First response: {agent_response}" +@command("message_agent", "Message GPT Agent", '"key": "", "message": ""') def message_agent(key: str, message: str) -> str: """Message an agent with a given key and message""" # Check if the key is a valid integer @@ -290,7 +224,8 @@ def message_agent(key: str, message: str) -> str: return agent_response -def list_agents(): +@command("list_agents", "List GPT Agents", "") +def list_agents() -> str: """List all agents Returns: @@ -301,6 +236,7 @@ def list_agents(): ) +@command("delete_agent", "Delete GPT Agent", '"key": ""') def delete_agent(key: str) -> str: """Delete an agent with a given key diff --git a/autogpt/args.py b/autogpt/args.py deleted file mode 100644 index f0e9c07a..00000000 --- a/autogpt/args.py +++ /dev/null @@ -1,151 +0,0 @@ -"""This module contains the argument parsing logic for the script.""" -import argparse - -from colorama import Fore, Back, Style -from autogpt import utils -from autogpt.config import Config -from autogpt.logs import logger -from autogpt.memory import get_supported_memory_backends - -CFG = Config() - - -def parse_arguments() -> None: - """Parses the arguments passed to the script - - Returns: - None - """ - CFG.set_debug_mode(False) - CFG.set_continuous_mode(False) - CFG.set_speak_mode(False) - - parser = argparse.ArgumentParser(description="Process arguments.") - parser.add_argument( - "--continuous", "-c", action="store_true", help="Enable Continuous Mode" - ) - parser.add_argument( - "--continuous-limit", - "-l", - type=int, - dest="continuous_limit", - help="Defines the number of times to run in continuous mode", - ) - parser.add_argument("--speak", action="store_true", help="Enable Speak Mode") - parser.add_argument("--debug", action="store_true", help="Enable Debug Mode") - parser.add_argument( - "--gpt3only", action="store_true", help="Enable GPT3.5 Only Mode" - ) - parser.add_argument("--gpt4only", action="store_true", help="Enable GPT4 Only Mode") - parser.add_argument( - "--use-memory", - "-m", - dest="memory_type", - help="Defines which Memory backend to use", - ) - parser.add_argument( - "--skip-reprompt", - "-y", - dest="skip_reprompt", - action="store_true", - help="Skips the re-prompting messages at the beginning of the script", - ) - parser.add_argument( - "--use-browser", - "-b", - dest="browser_name", - help="Specifies which web-browser to use when using selenium to scrape the web.", - ) - parser.add_argument( - "--ai-settings", - "-C", - dest="ai_settings_file", - help="Specifies which ai_settings.yaml file to use, will also automatically" - " skip the re-prompt.", - ) - parser.add_argument( - '--allow-downloads', - action='store_true', - dest='allow_downloads', - help='Dangerous: Allows Auto-GPT to download files natively.' - ) - args = parser.parse_args() - - if args.debug: - logger.typewriter_log("Debug Mode: ", Fore.GREEN, "ENABLED") - CFG.set_debug_mode(True) - - if args.continuous: - logger.typewriter_log("Continuous Mode: ", Fore.RED, "ENABLED") - logger.typewriter_log( - "WARNING: ", - Fore.RED, - "Continuous mode is not recommended. It is potentially dangerous and may" - " cause your AI to run forever or carry out actions you would not usually" - " authorise. Use at your own risk.", - ) - CFG.set_continuous_mode(True) - - if args.continuous_limit: - logger.typewriter_log( - "Continuous Limit: ", Fore.GREEN, f"{args.continuous_limit}" - ) - CFG.set_continuous_limit(args.continuous_limit) - - # Check if continuous limit is used without continuous mode - if args.continuous_limit and not args.continuous: - parser.error("--continuous-limit can only be used with --continuous") - - if args.speak: - logger.typewriter_log("Speak Mode: ", Fore.GREEN, "ENABLED") - CFG.set_speak_mode(True) - - if args.gpt3only: - logger.typewriter_log("GPT3.5 Only Mode: ", Fore.GREEN, "ENABLED") - CFG.set_smart_llm_model(CFG.fast_llm_model) - - if args.gpt4only: - logger.typewriter_log("GPT4 Only Mode: ", Fore.GREEN, "ENABLED") - CFG.set_fast_llm_model(CFG.smart_llm_model) - - if args.memory_type: - supported_memory = get_supported_memory_backends() - chosen = args.memory_type - if chosen not in supported_memory: - logger.typewriter_log( - "ONLY THE FOLLOWING MEMORY BACKENDS ARE SUPPORTED: ", - Fore.RED, - f"{supported_memory}", - ) - logger.typewriter_log("Defaulting to: ", Fore.YELLOW, CFG.memory_backend) - else: - CFG.memory_backend = chosen - - if args.skip_reprompt: - logger.typewriter_log("Skip Re-prompt: ", Fore.GREEN, "ENABLED") - CFG.skip_reprompt = True - - if args.ai_settings_file: - file = args.ai_settings_file - - # Validate file - (validated, message) = utils.validate_yaml_file(file) - if not validated: - logger.typewriter_log("FAILED FILE VALIDATION", Fore.RED, message) - logger.double_check() - exit(1) - - logger.typewriter_log("Using AI Settings File:", Fore.GREEN, file) - CFG.ai_settings_file = file - CFG.skip_reprompt = True - - if args.allow_downloads: - logger.typewriter_log("Native Downloading:", Fore.GREEN, "ENABLED") - logger.typewriter_log("WARNING: ", Fore.YELLOW, - f"{Back.LIGHTYELLOW_EX}Auto-GPT will now be able to download and save files to your machine.{Back.RESET} " + - "It is recommended that you monitor any files it downloads carefully.") - logger.typewriter_log("WARNING: ", Fore.YELLOW, f"{Back.RED + Style.BRIGHT}ALWAYS REMEMBER TO NEVER OPEN FILES YOU AREN'T SURE OF!{Style.RESET_ALL}") - CFG.allow_downloads = True - - if args.browser_name: - CFG.selenium_web_browser = args.browser_name diff --git a/autogpt/chat.py b/autogpt/chat.py index 1f6bca96..f9fc9471 100644 --- a/autogpt/chat.py +++ b/autogpt/chat.py @@ -6,11 +6,12 @@ from autogpt import token_counter from autogpt.config import Config from autogpt.llm_utils import create_chat_completion from autogpt.logs import logger +from autogpt.types.openai import Message cfg = Config() -def create_chat_message(role, content): +def create_chat_message(role, content) -> Message: """ Create a chat message with the given role and content. @@ -51,7 +52,7 @@ def generate_context(prompt, relevant_memory, full_message_history, model): # TODO: Change debug from hardcode to argument def chat_with_ai( - prompt, user_input, full_message_history, permanent_memory, token_limit + agent, prompt, user_input, full_message_history, permanent_memory, token_limit ): """Interact with the OpenAI API, sending the prompt, user input, message history, and permanent memory.""" @@ -135,6 +136,25 @@ def chat_with_ai( # Append user input, the length of this is accounted for above current_context.extend([create_chat_message("user", user_input)]) + plugin_count = len(cfg.plugins) + for i, plugin in enumerate(cfg.plugins): + if not plugin.can_handle_on_planning(): + continue + plugin_response = plugin.on_planning( + agent.prompt_generator, current_context + ) + if not plugin_response or plugin_response == "": + continue + tokens_to_add = token_counter.count_message_tokens( + [create_chat_message("system", plugin_response)], model + ) + if current_tokens_used + tokens_to_add > send_token_limit: + if cfg.debug_mode: + print("Plugin response too long, skipping:", plugin_response) + print("Plugins remaining at stop:", plugin_count - i) + break + current_context.append(create_chat_message("system", plugin_response)) + # Calculate remaining tokens tokens_remaining = token_limit - current_tokens_used # assert tokens_remaining >= 0, "Tokens remaining is negative. diff --git a/autogpt/cli.py b/autogpt/cli.py new file mode 100644 index 00000000..51a946a7 --- /dev/null +++ b/autogpt/cli.py @@ -0,0 +1,181 @@ +"""Main script for the autogpt package.""" +import click + + +@click.group(invoke_without_command=True) +@click.option("-c", "--continuous", is_flag=True, help="Enable Continuous Mode") +@click.option( + "--skip-reprompt", + "-y", + is_flag=True, + help="Skips the re-prompting messages at the beginning of the script", +) +@click.option( + "--ai-settings", + "-C", + help="Specifies which ai_settings.yaml file to use, will also automatically skip the re-prompt.", +) +@click.option( + "-l", + "--continuous-limit", + type=int, + help="Defines the number of times to run in continuous mode", +) +@click.option("--speak", is_flag=True, help="Enable Speak Mode") +@click.option("--debug", is_flag=True, help="Enable Debug Mode") +@click.option("--gpt3only", is_flag=True, help="Enable GPT3.5 Only Mode") +@click.option("--gpt4only", is_flag=True, help="Enable GPT4 Only Mode") +@click.option( + "--use-memory", + "-m", + "memory_type", + type=str, + help="Defines which Memory backend to use", +) +@click.option( + "-b", + "--browser-name", + help="Specifies which web-browser to use when using selenium to scrape the web.", +) +@click.option( + "--allow-downloads", + is_flag=True, + help="Dangerous: Allows Auto-GPT to download files natively.", +) +@click.option( + "--skip-news", + is_flag=True, + help="Specifies whether to suppress the output of latest news on startup.", +) +@click.pass_context +def main( + ctx: click.Context, + continuous: bool, + continuous_limit: int, + ai_settings: str, + skip_reprompt: bool, + speak: bool, + debug: bool, + gpt3only: bool, + gpt4only: bool, + memory_type: str, + browser_name: str, + allow_downloads: bool, + skip_news: bool, +) -> None: + """ + Welcome to AutoGPT an experimental open-source application showcasing the capabilities of the GPT-4 pushing the boundaries of AI. + + Start an Auto-GPT assistant. + """ + # Put imports inside function to avoid importing everything when starting the CLI + import logging + import sys + + from colorama import Fore + + from autogpt.agent.agent import Agent + from autogpt.commands.command import CommandRegistry + from autogpt.config import Config, check_openai_api_key + from autogpt.configurator import create_config + from autogpt.logs import logger + from autogpt.memory import get_memory + from autogpt.plugins import scan_plugins + from autogpt.prompts.prompt import construct_main_ai_config + from autogpt.utils import get_current_git_branch, get_latest_bulletin + + if ctx.invoked_subcommand is None: + cfg = Config() + # TODO: fill in llm values here + check_openai_api_key() + create_config( + continuous, + continuous_limit, + ai_settings, + skip_reprompt, + speak, + debug, + gpt3only, + gpt4only, + memory_type, + browser_name, + allow_downloads, + skip_news, + ) + logger.set_level(logging.DEBUG if cfg.debug_mode else logging.INFO) + ai_name = "" + if not cfg.skip_news: + motd = get_latest_bulletin() + if motd: + logger.typewriter_log("NEWS: ", Fore.GREEN, motd) + git_branch = get_current_git_branch() + if git_branch and git_branch != "stable": + logger.typewriter_log( + "WARNING: ", + Fore.RED, + f"You are running on `{git_branch}` branch " + "- this is not a supported branch.", + ) + if sys.version_info < (3, 10): + logger.typewriter_log( + "WARNING: ", + Fore.RED, + "You are running on an older version of Python. " + "Some people have observed problems with certain " + "parts of Auto-GPT with this version. " + "Please consider upgrading to Python 3.10 or higher.", + ) + + cfg = Config() + cfg.set_plugins(scan_plugins(cfg, cfg.debug_mode)) + # Create a CommandRegistry instance and scan default folder + command_registry = CommandRegistry() + command_registry.import_commands("autogpt.commands.analyze_code") + command_registry.import_commands("autogpt.commands.audio_text") + command_registry.import_commands("autogpt.commands.execute_code") + command_registry.import_commands("autogpt.commands.file_operations") + command_registry.import_commands("autogpt.commands.git_operations") + command_registry.import_commands("autogpt.commands.google_search") + command_registry.import_commands("autogpt.commands.image_gen") + command_registry.import_commands("autogpt.commands.improve_code") + command_registry.import_commands("autogpt.commands.twitter") + command_registry.import_commands("autogpt.commands.web_selenium") + command_registry.import_commands("autogpt.commands.write_tests") + command_registry.import_commands("autogpt.app") + ai_name = "" + ai_config = construct_main_ai_config() + ai_config.command_registry = command_registry + # print(prompt) + # Initialize variables + full_message_history = [] + next_action_count = 0 + # Make a constant: + triggering_prompt = ( + "Determine which next command to use, and respond using the" + " format specified above:" + ) + # Initialize memory and make sure it is empty. + # this is particularly important for indexing and referencing pinecone memory + memory = get_memory(cfg, init=True) + logger.typewriter_log( + "Using memory of type:", Fore.GREEN, f"{memory.__class__.__name__}" + ) + logger.typewriter_log("Using Browser:", Fore.GREEN, cfg.selenium_web_browser) + system_prompt = ai_config.construct_full_prompt() + if cfg.debug_mode: + logger.typewriter_log("Prompt:", Fore.GREEN, system_prompt) + agent = Agent( + ai_name=ai_name, + memory=memory, + full_message_history=full_message_history, + next_action_count=next_action_count, + command_registry=command_registry, + config=ai_config, + system_prompt=system_prompt, + triggering_prompt=triggering_prompt, + ) + agent.start_interaction_loop() + + +if __name__ == "__main__": + main() diff --git a/autogpt/commands/evaluate_code.py b/autogpt/commands/analyze_code.py similarity index 79% rename from autogpt/commands/evaluate_code.py rename to autogpt/commands/analyze_code.py index 8f7cbca9..b87d73e1 100644 --- a/autogpt/commands/evaluate_code.py +++ b/autogpt/commands/analyze_code.py @@ -1,10 +1,16 @@ """Code evaluation module.""" from __future__ import annotations +from autogpt.commands.command import command from autogpt.llm_utils import call_ai_function -def evaluate_code(code: str) -> list[str]: +@command( + "analyze_code", + "Analyze Code", + '"code": ""', +) +def analyze_code(code: str) -> list[str]: """ A function that takes in a string and returns a response from create chat completion api call. diff --git a/autogpt/commands/audio_text.py b/autogpt/commands/audio_text.py index 84819d5e..b409fefd 100644 --- a/autogpt/commands/audio_text.py +++ b/autogpt/commands/audio_text.py @@ -1,23 +1,51 @@ -import requests +"""Commands for converting audio to text.""" import json +import requests + +from autogpt.commands.command import command from autogpt.config import Config from autogpt.workspace import path_in_workspace -cfg = Config() +CFG = Config() -def read_audio_from_file(audio_path): - audio_path = path_in_workspace(audio_path) +@command( + "read_audio_from_file", + "Convert Audio to text", + '"filename": ""', + CFG.huggingface_audio_to_text_model, + "Configure huggingface_audio_to_text_model.", +) +def read_audio_from_file(filename: str) -> str: + """ + Convert audio to text. + + Args: + audio_path (str): The path to the audio file + + Returns: + str: The text from the audio + """ + audio_path = path_in_workspace(filename) with open(audio_path, "rb") as audio_file: audio = audio_file.read() return read_audio(audio) -def read_audio(audio): - model = cfg.huggingface_audio_to_text_model +def read_audio(audio: bytes) -> str: + """ + Convert audio to text. + + Args: + audio (bytes): The audio to convert + + Returns: + str: The text from the audio + """ + model = CFG.huggingface_audio_to_text_model api_url = f"https://api-inference.huggingface.co/models/{model}" - api_token = cfg.huggingface_api_token + api_token = CFG.huggingface_api_token headers = {"Authorization": f"Bearer {api_token}"} if api_token is None: @@ -32,4 +60,4 @@ def read_audio(audio): ) text = json.loads(response.content.decode("utf-8"))["text"] - return "The audio says: " + text + return f"The audio says: {text}" diff --git a/autogpt/commands/command.py b/autogpt/commands/command.py new file mode 100644 index 00000000..e97af008 --- /dev/null +++ b/autogpt/commands/command.py @@ -0,0 +1,153 @@ +import importlib +import inspect +from typing import Any, Callable, Optional + +# Unique identifier for auto-gpt commands +AUTO_GPT_COMMAND_IDENTIFIER = "auto_gpt_command" + + +class Command: + """A class representing a command. + + Attributes: + name (str): The name of the command. + description (str): A brief description of what the command does. + signature (str): The signature of the function that the command executes. Defaults to None. + """ + + def __init__( + self, + name: str, + description: str, + method: Callable[..., Any], + signature: str = "", + enabled: bool = True, + disabled_reason: Optional[str] = None, + ): + self.name = name + self.description = description + self.method = method + self.signature = signature if signature else str(inspect.signature(self.method)) + self.enabled = enabled + self.disabled_reason = disabled_reason + + def __call__(self, *args, **kwargs) -> Any: + if not self.enabled: + return f"Command '{self.name}' is disabled: {self.disabled_reason}" + return self.method(*args, **kwargs) + + def __str__(self) -> str: + return f"{self.name}: {self.description}, args: {self.signature}" + + +class CommandRegistry: + """ + The CommandRegistry class is a manager for a collection of Command objects. + It allows the registration, modification, and retrieval of Command objects, + as well as the scanning and loading of command plugins from a specified + directory. + """ + + def __init__(self): + self.commands = {} + + def _import_module(self, module_name: str) -> Any: + return importlib.import_module(module_name) + + def _reload_module(self, module: Any) -> Any: + return importlib.reload(module) + + def register(self, cmd: Command) -> None: + self.commands[cmd.name] = cmd + + def unregister(self, command_name: str): + if command_name in self.commands: + del self.commands[command_name] + else: + raise KeyError(f"Command '{command_name}' not found in registry.") + + def reload_commands(self) -> None: + """Reloads all loaded command plugins.""" + for cmd_name in self.commands: + cmd = self.commands[cmd_name] + module = self._import_module(cmd.__module__) + reloaded_module = self._reload_module(module) + if hasattr(reloaded_module, "register"): + reloaded_module.register(self) + + def get_command(self, name: str) -> Callable[..., Any]: + return self.commands[name] + + def call(self, command_name: str, **kwargs) -> Any: + if command_name not in self.commands: + raise KeyError(f"Command '{command_name}' not found in registry.") + command = self.commands[command_name] + return command(**kwargs) + + def command_prompt(self) -> str: + """ + Returns a string representation of all registered `Command` objects for use in a prompt + """ + commands_list = [ + f"{idx + 1}. {str(cmd)}" for idx, cmd in enumerate(self.commands.values()) + ] + return "\n".join(commands_list) + + def import_commands(self, module_name: str) -> None: + """ + Imports the specified Python module containing command plugins. + + This method imports the associated module and registers any functions or + classes that are decorated with the `AUTO_GPT_COMMAND_IDENTIFIER` attribute + as `Command` objects. The registered `Command` objects are then added to the + `commands` dictionary of the `CommandRegistry` object. + + Args: + module_name (str): The name of the module to import for command plugins. + """ + + module = importlib.import_module(module_name) + + for attr_name in dir(module): + attr = getattr(module, attr_name) + # Register decorated functions + if hasattr(attr, AUTO_GPT_COMMAND_IDENTIFIER) and getattr( + attr, AUTO_GPT_COMMAND_IDENTIFIER + ): + self.register(attr.command) + # Register command classes + elif ( + inspect.isclass(attr) and issubclass(attr, Command) and attr != Command + ): + cmd_instance = attr() + self.register(cmd_instance) + + +def command( + name: str, + description: str, + signature: str = "", + enabled: bool = True, + disabled_reason: Optional[str] = None, +) -> Callable[..., Any]: + """The command decorator is used to create Command objects from ordinary functions.""" + + def decorator(func: Callable[..., Any]) -> Command: + cmd = Command( + name=name, + description=description, + method=func, + signature=signature, + enabled=enabled, + disabled_reason=disabled_reason, + ) + + def wrapper(*args, **kwargs) -> Any: + return func(*args, **kwargs) + + wrapper.command = cmd + + setattr(wrapper, AUTO_GPT_COMMAND_IDENTIFIER, True) + return wrapper + + return decorator diff --git a/autogpt/commands/execute_code.py b/autogpt/commands/execute_code.py index 2cc797cb..ff35d428 100644 --- a/autogpt/commands/execute_code.py +++ b/autogpt/commands/execute_code.py @@ -5,19 +5,24 @@ import subprocess import docker from docker.errors import ImageNotFound -from autogpt.workspace import path_in_workspace, WORKSPACE_PATH +from autogpt.commands.command import command +from autogpt.config import Config +from autogpt.workspace import WORKSPACE_PATH, path_in_workspace + +CFG = Config() -def execute_python_file(file: str): +@command("execute_python_file", "Execute Python File", '"filename": ""') +def execute_python_file(filename: str) -> str: """Execute a Python file in a Docker container and return the output Args: - file (str): The name of the file to execute + filename (str): The name of the file to execute Returns: str: The output of the file """ - + file = filename print(f"Executing file '{file}' in workspace '{WORKSPACE_PATH}'") if not file.endswith(".py"): @@ -40,10 +45,10 @@ def execute_python_file(file: str): try: client = docker.from_env() - # You can replace 'python:3.8' with the desired Python image/version + # You can replace this with the desired Python image/version # You can find available Python images on Docker Hub: # https://hub.docker.com/_/python - image_name = "python:3.10" + image_name = "python:3-alpine" try: client.images.get(image_name) print(f"Image '{image_name}' found locally") @@ -84,10 +89,25 @@ def execute_python_file(file: str): return logs + except docker.errors.DockerException as e: + print( + "Could not run the script in a container. If you haven't already, please install Docker https://docs.docker.com/get-docker/" + ) + return f"Error: {str(e)}" + except Exception as e: return f"Error: {str(e)}" +@command( + "execute_shell", + "Execute Shell Command, non-interactive commands only", + '"command_line": ""', + CFG.execute_local_commands, + "You are not allowed to run local shell commands. To execute" + " shell commands, EXECUTE_LOCAL_COMMANDS must be set to 'True' " + "in your config. Do not attempt to bypass the restriction.", +) def execute_shell(command_line: str) -> str: """Execute a shell command and return the output @@ -97,6 +117,13 @@ def execute_shell(command_line: str) -> str: Returns: str: The output of the command """ + + if not CFG.execute_local_commands: + return ( + "You are not allowed to run local shell commands. To execute" + " shell commands, EXECUTE_LOCAL_COMMANDS must be set to 'True' " + "in your config. Do not attempt to bypass the restriction." + ) current_dir = os.getcwd() # Change dir into workspace if necessary if str(WORKSPACE_PATH) not in current_dir: @@ -111,7 +138,43 @@ def execute_shell(command_line: str) -> str: os.chdir(current_dir) - return output + +@command( + "execute_shell_popen", + "Execute Shell Command, non-interactive commands only", + '"command_line": ""', + CFG.execute_local_commands, + "You are not allowed to run local shell commands. To execute" + " shell commands, EXECUTE_LOCAL_COMMANDS must be set to 'True' " + "in your config. Do not attempt to bypass the restriction.", +) +def execute_shell_popen(command_line) -> str: + """Execute a shell command with Popen and returns an english description + of the event and the process id + + Args: + command_line (str): The command line to execute + + Returns: + str: Description of the fact that the process started and its id + """ + current_dir = os.getcwd() + # Change dir into workspace if necessary + if str(WORKSPACE_PATH) not in current_dir: + os.chdir(WORKSPACE_PATH) + + print(f"Executing command '{command_line}' in working directory '{os.getcwd()}'") + + do_not_show_output = subprocess.DEVNULL + process = subprocess.Popen( + command_line, shell=True, stdout=do_not_show_output, stderr=do_not_show_output + ) + + # Change back to whatever the prior working dir was + + os.chdir(current_dir) + + return f"Subprocess started with PID:'{str(process.pid)}'" def we_are_running_in_a_docker_container() -> bool: diff --git a/autogpt/commands/file_operations.py b/autogpt/commands/file_operations.py index d273c1a3..b73fb987 100644 --- a/autogpt/commands/file_operations.py +++ b/autogpt/commands/file_operations.py @@ -3,17 +3,19 @@ from __future__ import annotations import os import os.path -from pathlib import Path -from typing import Generator, List +from typing import Generator + import requests -from requests.adapters import HTTPAdapter -from requests.adapters import Retry -from colorama import Fore, Back +from colorama import Back, Fore +from requests.adapters import HTTPAdapter, Retry + +from autogpt.commands.command import command +from autogpt.config import Config from autogpt.spinner import Spinner from autogpt.utils import readable_file_size -from autogpt.workspace import path_in_workspace, WORKSPACE_PATH - +from autogpt.workspace import WORKSPACE_PATH, path_in_workspace +CFG = Config() LOG_FILE = "file_logger.txt" LOG_FILE_PATH = WORKSPACE_PATH / LOG_FILE @@ -47,7 +49,7 @@ def log_operation(operation: str, filename: str) -> None: with open(LOG_FILE_PATH, "w", encoding="utf-8") as f: f.write("File Operation Logger ") - append_to_file(LOG_FILE, log_entry, shouldLog = False) + append_to_file(LOG_FILE, log_entry, shouldLog=False) def split_file( @@ -70,13 +72,19 @@ def split_file( while start < content_length: end = start + max_length if end + overlap < content_length: - chunk = content[start : end + overlap] + chunk = content[start : end + overlap - 1] else: chunk = content[start:content_length] + + # Account for the case where the last chunk is shorter than the overlap, so it has already been consumed + if len(chunk) <= overlap: + break + yield chunk start += max_length - overlap +@command("read_file", "Read file", '"filename": ""') def read_file(filename: str) -> str: """Read a file and return the contents @@ -129,6 +137,7 @@ def ingest_file( print(f"Error while ingesting file '{filename}': {str(e)}") +@command("write_to_file", "Write to file", '"filename": "", "text": ""') def write_to_file(filename: str, text: str) -> str: """Write text to a file @@ -154,6 +163,9 @@ def write_to_file(filename: str, text: str) -> str: return f"Error: {str(e)}" +@command( + "append_to_file", "Append to file", '"filename": "", "text": ""' +) def append_to_file(filename: str, text: str, shouldLog: bool = True) -> str: """Append text to a file @@ -177,6 +189,7 @@ def append_to_file(filename: str, text: str, shouldLog: bool = True) -> str: return f"Error: {str(e)}" +@command("delete_file", "Delete file", '"filename": ""') def delete_file(filename: str) -> str: """Delete a file @@ -197,6 +210,7 @@ def delete_file(filename: str) -> str: return f"Error: {str(e)}" +@command("search_files", "Search Files", '"directory": ""') def search_files(directory: str) -> list[str]: """Search for files in a directory @@ -223,6 +237,13 @@ def search_files(directory: str) -> list[str]: return found_files +@command( + "download_file", + "Search Files", + '"url": "", "filename": ""', + CFG.allow_downloads, + "Error: You do not have user authorization to download files locally.", +) def download_file(url, filename): """Downloads a file Args: @@ -236,23 +257,23 @@ def download_file(url, filename): session = requests.Session() retry = Retry(total=3, backoff_factor=1, status_forcelist=[502, 503, 504]) adapter = HTTPAdapter(max_retries=retry) - session.mount('http://', adapter) - session.mount('https://', adapter) + session.mount("http://", adapter) + session.mount("https://", adapter) total_size = 0 downloaded_size = 0 with session.get(url, allow_redirects=True, stream=True) as r: r.raise_for_status() - total_size = int(r.headers.get('Content-Length', 0)) + total_size = int(r.headers.get("Content-Length", 0)) downloaded_size = 0 - with open(safe_filename, 'wb') as f: + with open(safe_filename, "wb") as f: for chunk in r.iter_content(chunk_size=8192): f.write(chunk) downloaded_size += len(chunk) - # Update the progress message + # Update the progress message progress = f"{readable_file_size(downloaded_size)} / {readable_file_size(total_size)}" spinner.update_message(f"{message} {progress}") diff --git a/autogpt/commands/git_operations.py b/autogpt/commands/git_operations.py index 675eb228..1fb99e5b 100644 --- a/autogpt/commands/git_operations.py +++ b/autogpt/commands/git_operations.py @@ -1,25 +1,34 @@ """Git operations for autogpt""" -import git +from git.repo import Repo + +from autogpt.commands.command import command from autogpt.config import Config from autogpt.workspace import path_in_workspace CFG = Config() -def clone_repository(repo_url: str, clone_path: str) -> str: - """Clone a github repository locally +@command( + "clone_repository", + "Clone Repositoryy", + '"repository_url": "", "clone_path": ""', + CFG.github_username and CFG.github_api_key, + "Configure github_username and github_api_key.", +) +def clone_repository(repository_url: str, clone_path: str) -> str: + """Clone a GitHub repository locally Args: - repo_url (str): The URL of the repository to clone + repository_url (str): The URL of the repository to clone clone_path (str): The path to clone the repository to Returns: str: The result of the clone operation""" - split_url = repo_url.split("//") + split_url = repository_url.split("//") auth_repo_url = f"//{CFG.github_username}:{CFG.github_api_key}@".join(split_url) safe_clone_path = path_in_workspace(clone_path) try: - git.Repo.clone_from(auth_repo_url, safe_clone_path) - return f"""Cloned {repo_url} to {safe_clone_path}""" + Repo.clone_from(auth_repo_url, safe_clone_path) + return f"""Cloned {repository_url} to {safe_clone_path}""" except Exception as e: return f"Error: {str(e)}" diff --git a/autogpt/commands/google_search.py b/autogpt/commands/google_search.py index 148ba1d0..fcc1a9f4 100644 --- a/autogpt/commands/google_search.py +++ b/autogpt/commands/google_search.py @@ -5,13 +5,15 @@ import json from duckduckgo_search import ddg +from autogpt.commands.command import command from autogpt.config import Config CFG = Config() +@command("google", "Google Search", '"query": ""', not CFG.google_api_key) def google_search(query: str, num_results: int = 8) -> str: - """Return the results of a google search + """Return the results of a Google search Args: query (str): The search query. @@ -31,11 +33,19 @@ def google_search(query: str, num_results: int = 8) -> str: for j in results: search_results.append(j) - return json.dumps(search_results, ensure_ascii=False, indent=4) + results = json.dumps(search_results, ensure_ascii=False, indent=4) + return safe_google_results(results) +@command( + "google", + "Google Search", + '"query": ""', + bool(CFG.google_api_key), + "Configure google_api_key.", +) def google_official_search(query: str, num_results: int = 8) -> str | list[str]: - """Return the results of a google search using the official Google API + """Return the results of a Google search using the official Google API Args: query (str): The search query. @@ -82,6 +92,26 @@ def google_official_search(query: str, num_results: int = 8) -> str | list[str]: return "Error: The provided Google API key is invalid or missing." else: return f"Error: {e}" + # google_result can be a list or a string depending on the search results # Return the list of search result URLs - return search_results_links + return safe_google_results(search_results_links) + + +def safe_google_results(results: str | list) -> str: + """ + Return the results of a google search in a safe format. + + Args: + results (str | list): The search results. + + Returns: + str: The results of the search. + """ + if isinstance(results, list): + safe_message = json.dumps( + [result.enocde("utf-8", "ignore") for result in results] + ) + else: + safe_message = results.encode("utf-8", "ignore").decode("utf-8") + return safe_message diff --git a/autogpt/commands/image_gen.py b/autogpt/commands/image_gen.py index 6243616e..962c41fb 100644 --- a/autogpt/commands/image_gen.py +++ b/autogpt/commands/image_gen.py @@ -1,23 +1,26 @@ """ Image Generation Module for AutoGPT.""" import io -import os.path import uuid from base64 import b64decode import openai import requests from PIL import Image + +from autogpt.commands.command import command from autogpt.config import Config from autogpt.workspace import path_in_workspace CFG = Config() -def generate_image(prompt: str) -> str: +@command("generate_image", "Generate Image", '"prompt": ""', CFG.image_provider) +def generate_image(prompt: str, size: int = 256) -> str: """Generate an image from a prompt. Args: prompt (str): The prompt to use + size (int, optional): The size of the image. Defaults to 256. (Not supported by HuggingFace) Returns: str: The filename of the image @@ -26,11 +29,14 @@ def generate_image(prompt: str) -> str: # DALL-E if CFG.image_provider == "dalle": - return generate_image_with_dalle(prompt, filename) - elif CFG.image_provider == "sd": + return generate_image_with_dalle(prompt, filename, size) + # HuggingFace + elif CFG.image_provider == "huggingface": return generate_image_with_hf(prompt, filename) - else: - return "No Image Provider Set" + # SD WebUI + elif CFG.image_provider == "sdwebui": + return generate_image_with_sd_webui(prompt, filename, size) + return "No Image Provider Set" def generate_image_with_hf(prompt: str, filename: str) -> str: @@ -44,13 +50,16 @@ def generate_image_with_hf(prompt: str, filename: str) -> str: str: The filename of the image """ API_URL = ( - "https://api-inference.huggingface.co/models/CompVis/stable-diffusion-v1-4" + f"https://api-inference.huggingface.co/models/{CFG.huggingface_image_model}" ) if CFG.huggingface_api_token is None: raise ValueError( "You need to set your Hugging Face API token in the config file." ) - headers = {"Authorization": f"Bearer {CFG.huggingface_api_token}"} + headers = { + "Authorization": f"Bearer {CFG.huggingface_api_token}", + "X-Use-Cache": "false", + } response = requests.post( API_URL, @@ -68,22 +77,31 @@ def generate_image_with_hf(prompt: str, filename: str) -> str: return f"Saved to disk:{filename}" -def generate_image_with_dalle(prompt: str, filename: str) -> str: +def generate_image_with_dalle(prompt: str, filename: str, size: int) -> str: """Generate an image with DALL-E. Args: prompt (str): The prompt to use filename (str): The filename to save the image to + size (int): The size of the image Returns: str: The filename of the image """ openai.api_key = CFG.openai_api_key + # Check for supported image sizes + if size not in [256, 512, 1024]: + closest = min([256, 512, 1024], key=lambda x: abs(x - size)) + print( + f"DALL-E only supports image sizes of 256x256, 512x512, or 1024x1024. Setting to {closest}, was {size}." + ) + size = closest + response = openai.Image.create( prompt=prompt, n=1, - size="256x256", + size=f"{size}x{size}", response_format="b64_json", ) @@ -95,3 +113,53 @@ def generate_image_with_dalle(prompt: str, filename: str) -> str: png.write(image_data) return f"Saved to disk:{filename}" + + +def generate_image_with_sd_webui( + prompt: str, + filename: str, + size: int = 512, + negative_prompt: str = "", + extra: dict = {}, +) -> str: + """Generate an image with Stable Diffusion webui. + Args: + prompt (str): The prompt to use + filename (str): The filename to save the image to + size (int, optional): The size of the image. Defaults to 256. + negative_prompt (str, optional): The negative prompt to use. Defaults to "". + extra (dict, optional): Extra parameters to pass to the API. Defaults to {}. + Returns: + str: The filename of the image + """ + # Create a session and set the basic auth if needed + s = requests.Session() + if CFG.sd_webui_auth: + username, password = CFG.sd_webui_auth.split(":") + s.auth = (username, password or "") + + # Generate the images + response = requests.post( + f"{CFG.sd_webui_url}/sdapi/v1/txt2img", + json={ + "prompt": prompt, + "negative_prompt": negative_prompt, + "sampler_index": "DDIM", + "steps": 20, + "cfg_scale": 7.0, + "width": size, + "height": size, + "n_iter": 1, + **extra, + }, + ) + + print(f"Image Generated for prompt:{prompt}") + + # Save the image to disk + response = response.json() + b64 = b64decode(response["images"][0].split(",", 1)[0]) + image = Image.open(io.BytesIO(b64)) + image.save(path_in_workspace(filename)) + + return f"Saved to disk:{filename}" diff --git a/autogpt/commands/improve_code.py b/autogpt/commands/improve_code.py index e3440d8b..41a369b4 100644 --- a/autogpt/commands/improve_code.py +++ b/autogpt/commands/improve_code.py @@ -2,9 +2,15 @@ from __future__ import annotations import json +from autogpt.commands.command import command from autogpt.llm_utils import call_ai_function +@command( + "improve_code", + "Get Improved Code", + '"suggestions": "", "code": ""', +) def improve_code(suggestions: list[str], code: str) -> str: """ A function that takes in code and suggestions and returns a response from create diff --git a/autogpt/commands/twitter.py b/autogpt/commands/twitter.py index dc4d450c..f0502271 100644 --- a/autogpt/commands/twitter.py +++ b/autogpt/commands/twitter.py @@ -1,11 +1,30 @@ -import tweepy +"""A module that contains a command to send a tweet.""" import os + +import tweepy from dotenv import load_dotenv +from autogpt.commands.command import command + load_dotenv() -def send_tweet(tweet_text): +@command( + "send_tweet", + "Send Tweet", + '"tweet_text": ""', +) +def send_tweet(tweet_text: str) -> str: + """ + A function that takes in a string and returns a response from create chat + completion api call. + + Args: + tweet_text (str): Text to be tweeted. + + Returns: + A result from sending the tweet. + """ consumer_key = os.environ.get("TW_CONSUMER_KEY") consumer_secret = os.environ.get("TW_CONSUMER_SECRET") access_token = os.environ.get("TW_ACCESS_TOKEN") @@ -20,6 +39,6 @@ def send_tweet(tweet_text): # Send tweet try: api.update_status(tweet_text) - print("Tweet sent successfully!") + return "Tweet sent successfully!" except tweepy.TweepyException as e: - print("Error sending tweet: {}".format(e.reason)) + return f"Error sending tweet: {e.reason}" diff --git a/autogpt/commands/web_playwright.py b/autogpt/commands/web_playwright.py index a1abb6cb..4e388ded 100644 --- a/autogpt/commands/web_playwright.py +++ b/autogpt/commands/web_playwright.py @@ -8,6 +8,7 @@ except ImportError: "Playwright not installed. Please install it with 'pip install playwright' to use." ) from bs4 import BeautifulSoup + from autogpt.processing.html import extract_hyperlinks, format_hyperlinks diff --git a/autogpt/commands/web_requests.py b/autogpt/commands/web_requests.py index 50d8d383..406338f4 100644 --- a/autogpt/commands/web_requests.py +++ b/autogpt/commands/web_requests.py @@ -4,9 +4,9 @@ from __future__ import annotations from urllib.parse import urljoin, urlparse import requests -from requests.compat import urljoin -from requests import Response from bs4 import BeautifulSoup +from requests import Response +from requests.compat import urljoin from autogpt.config import Config from autogpt.memory import get_memory @@ -58,9 +58,28 @@ def check_local_file_access(url: str) -> bool: """ local_prefixes = [ "file:///", + "file://localhost/", "file://localhost", "http://localhost", + "http://localhost/", "https://localhost", + "https://localhost/", + "http://2130706433", + "http://2130706433/", + "https://2130706433", + "https://2130706433/", + "http://127.0.0.1/", + "http://127.0.0.1", + "https://127.0.0.1/", + "https://127.0.0.1", + "https://0.0.0.0/", + "https://0.0.0.0", + "http://0.0.0.0/", + "http://0.0.0.0", + "http://0000", + "http://0000/", + "https://0000", + "https://0000/", ] return any(url.startswith(prefix) for prefix in local_prefixes) diff --git a/autogpt/commands/web_selenium.py b/autogpt/commands/web_selenium.py index 8c652294..e0e0d70a 100644 --- a/autogpt/commands/web_selenium.py +++ b/autogpt/commands/web_selenium.py @@ -1,27 +1,36 @@ """Selenium web scraping module.""" from __future__ import annotations -from selenium import webdriver -from autogpt.processing.html import extract_hyperlinks, format_hyperlinks -import autogpt.processing.text as summary -from bs4 import BeautifulSoup -from selenium.webdriver.remote.webdriver import WebDriver -from selenium.webdriver.common.by import By -from selenium.webdriver.support.wait import WebDriverWait -from selenium.webdriver.support import expected_conditions as EC -from webdriver_manager.chrome import ChromeDriverManager -from webdriver_manager.firefox import GeckoDriverManager -from selenium.webdriver.chrome.options import Options as ChromeOptions -from selenium.webdriver.firefox.options import Options as FirefoxOptions -from selenium.webdriver.safari.options import Options as SafariOptions import logging from pathlib import Path +from sys import platform + +from bs4 import BeautifulSoup +from selenium import webdriver +from selenium.webdriver.chrome.options import Options as ChromeOptions +from selenium.webdriver.common.by import By +from selenium.webdriver.firefox.options import Options as FirefoxOptions +from selenium.webdriver.remote.webdriver import WebDriver +from selenium.webdriver.safari.options import Options as SafariOptions +from selenium.webdriver.support import expected_conditions as EC +from selenium.webdriver.support.wait import WebDriverWait +from webdriver_manager.chrome import ChromeDriverManager +from webdriver_manager.firefox import GeckoDriverManager + +import autogpt.processing.text as summary +from autogpt.commands.command import command from autogpt.config import Config +from autogpt.processing.html import extract_hyperlinks, format_hyperlinks FILE_DIR = Path(__file__).parent.parent CFG = Config() +@command( + "browse_website", + "Browse Website", + '"url": "", "question": ""', +) def browse_website(url: str, question: str) -> tuple[str, WebDriver]: """Browse a website and return the answer and links to the user @@ -75,7 +84,15 @@ def scrape_text_with_selenium(url: str) -> tuple[WebDriver, str]: # See https://developer.apple.com/documentation/webkit/testing_with_webdriver_in_safari driver = webdriver.Safari(options=options) else: + if platform == "linux" or platform == "linux2": + options.add_argument("--disable-dev-shm-usage") + options.add_argument("--remote-debugging-port=9222") + options.add_argument("--no-sandbox") + if CFG.selenium_headless: + options.add_argument("--headless") + options.add_argument("--disable-gpu") + driver = webdriver.Chrome( executable_path=ChromeDriverManager().install(), options=options ) diff --git a/autogpt/commands/write_tests.py b/autogpt/commands/write_tests.py index 138a1adb..91cd9304 100644 --- a/autogpt/commands/write_tests.py +++ b/autogpt/commands/write_tests.py @@ -2,9 +2,16 @@ from __future__ import annotations import json + +from autogpt.commands.command import command from autogpt.llm_utils import call_ai_function +@command( + "write_tests", + "Write Tests", + '"code": "", "focus": ""', +) def write_tests(code: str, focus: list[str]) -> str: """ A function that takes in code and focus topics and returns a response from create diff --git a/autogpt/config/__init__.py b/autogpt/config/__init__.py index ceb5566c..726b6dcf 100644 --- a/autogpt/config/__init__.py +++ b/autogpt/config/__init__.py @@ -2,7 +2,7 @@ This module contains the configuration classes for AutoGPT. """ from autogpt.config.ai_config import AIConfig -from autogpt.config.config import check_openai_api_key, Config +from autogpt.config.config import Config, check_openai_api_key from autogpt.config.singleton import AbstractSingleton, Singleton __all__ = [ diff --git a/autogpt/config/ai_config.py b/autogpt/config/ai_config.py index 86171357..1e48ab4d 100644 --- a/autogpt/config/ai_config.py +++ b/autogpt/config/ai_config.py @@ -5,9 +5,16 @@ A module that contains the AIConfig class object that contains the configuration from __future__ import annotations import os -from typing import Type +from pathlib import Path +from typing import Optional, Type + import yaml +from autogpt.prompts.generator import PromptGenerator + +# Soon this will go in a folder where it remembers more stuff about the run(s) +SAVE_FILE = str(Path(os.getcwd()) / "ai_settings.yaml") + class AIConfig: """ @@ -37,9 +44,8 @@ class AIConfig: self.ai_name = ai_name self.ai_role = ai_role self.ai_goals = ai_goals - - # Soon this will go in a folder where it remembers more stuff about the run(s) - SAVE_FILE = os.path.join(os.path.dirname(__file__), "..", "ai_settings.yaml") + self.prompt_generator = None + self.command_registry = None @staticmethod def load(config_file: str = SAVE_FILE) -> "AIConfig": @@ -88,7 +94,9 @@ class AIConfig: with open(config_file, "w", encoding="utf-8") as file: yaml.dump(config, file, allow_unicode=True) - def construct_full_prompt(self) -> str: + def construct_full_prompt( + self, prompt_generator: Optional[PromptGenerator] = None + ) -> str: """ Returns a prompt to the user with the class information in an organized fashion. @@ -107,14 +115,25 @@ class AIConfig: "" ) - from autogpt.prompt import get_prompt + from autogpt.config import Config + from autogpt.prompts.prompt import build_default_prompt_generator + + cfg = Config() + if prompt_generator is None: + prompt_generator = build_default_prompt_generator() + prompt_generator.goals = self.ai_goals + prompt_generator.name = self.ai_name + prompt_generator.role = self.ai_role + prompt_generator.command_registry = self.command_registry + for plugin in cfg.plugins: + if not plugin.can_handle_post_prompt(): + continue + prompt_generator = plugin.post_prompt(prompt_generator) # Construct full prompt - full_prompt = ( - f"You are {self.ai_name}, {self.ai_role}\n{prompt_start}\n\nGOALS:\n\n" - ) + full_prompt = f"You are {prompt_generator.name}, {prompt_generator.role}\n{prompt_start}\n\nGOALS:\n\n" for i, goal in enumerate(self.ai_goals): full_prompt += f"{i+1}. {goal}\n" - - full_prompt += f"\n\n{get_prompt()}" + self.prompt_generator = prompt_generator + full_prompt += f"\n\n{prompt_generator.generate_prompt_string()}" return full_prompt diff --git a/autogpt/config/config.py b/autogpt/config/config.py index 8dc3b487..80551514 100644 --- a/autogpt/config/config.py +++ b/autogpt/config/config.py @@ -1,14 +1,15 @@ """Configuration class to store the state of bools for different scripts access.""" import os -from colorama import Fore - -from autogpt.config.singleton import Singleton +from typing import List import openai import yaml - +from auto_gpt_plugin_template import AutoGPTPluginTemplate +from colorama import Fore from dotenv import load_dotenv +from autogpt.config.singleton import Singleton + load_dotenv(verbose=True) @@ -25,22 +26,27 @@ class Config(metaclass=Singleton): self.speak_mode = False self.skip_reprompt = False self.allow_downloads = False + self.skip_news = False - self.selenium_web_browser = os.getenv("USE_WEB_BROWSER", "chrome") self.ai_settings_file = os.getenv("AI_SETTINGS_FILE", "ai_settings.yaml") self.fast_llm_model = os.getenv("FAST_LLM_MODEL", "gpt-3.5-turbo") self.smart_llm_model = os.getenv("SMART_LLM_MODEL", "gpt-4") self.fast_token_limit = int(os.getenv("FAST_TOKEN_LIMIT", 4000)) self.smart_token_limit = int(os.getenv("SMART_TOKEN_LIMIT", 8000)) - self.browse_chunk_max_length = int(os.getenv("BROWSE_CHUNK_MAX_LENGTH", 8192)) - self.browse_summary_max_token = int(os.getenv("BROWSE_SUMMARY_MAX_TOKEN", 300)) + self.browse_chunk_max_length = int(os.getenv("BROWSE_CHUNK_MAX_LENGTH", 3000)) + self.browse_spacy_language_model = os.getenv( + "BROWSE_SPACY_LANGUAGE_MODEL", "en_core_web_sm" + ) self.openai_api_key = os.getenv("OPENAI_API_KEY") - self.temperature = float(os.getenv("TEMPERATURE", "1")) + self.temperature = float(os.getenv("TEMPERATURE", "0")) self.use_azure = os.getenv("USE_AZURE") == "True" self.execute_local_commands = ( os.getenv("EXECUTE_LOCAL_COMMANDS", "False") == "True" ) + self.restrict_to_workspace = ( + os.getenv("RESTRICT_TO_WORKSPACE", "True") == "True" + ) if self.use_azure: self.load_azure_config() @@ -75,19 +81,31 @@ class Config(metaclass=Singleton): self.weaviate_scopes = os.getenv("WEAVIATE_SCOPES", None) self.weaviate_embedded_path = os.getenv("WEAVIATE_EMBEDDED_PATH") self.weaviate_api_key = os.getenv("WEAVIATE_API_KEY", None) - self.use_weaviate_embedded = os.getenv("USE_WEAVIATE_EMBEDDED", "False") == "True" + self.use_weaviate_embedded = ( + os.getenv("USE_WEAVIATE_EMBEDDED", "False") == "True" + ) # milvus configuration, e.g., localhost:19530. self.milvus_addr = os.getenv("MILVUS_ADDR", "localhost:19530") self.milvus_collection = os.getenv("MILVUS_COLLECTION", "autogpt") self.image_provider = os.getenv("IMAGE_PROVIDER") + self.image_size = int(os.getenv("IMAGE_SIZE", 256)) self.huggingface_api_token = os.getenv("HUGGINGFACE_API_TOKEN") + self.huggingface_image_model = os.getenv( + "HUGGINGFACE_IMAGE_MODEL", "CompVis/stable-diffusion-v1-4" + ) self.huggingface_audio_to_text_model = os.getenv( "HUGGINGFACE_AUDIO_TO_TEXT_MODEL" ) + self.sd_webui_url = os.getenv("SD_WEBUI_URL", "http://localhost:7860") + self.sd_webui_auth = os.getenv("SD_WEBUI_AUTH") - # User agent headers to use when browsing web + # Selenium browser settings + self.selenium_web_browser = os.getenv("USE_WEB_BROWSER", "chrome") + self.selenium_headless = os.getenv("HEADLESS_BROWSER", "True") == "True" + + # User agent header to use when making HTTP requests # Some websites might just completely deny request with an error code if # no user agent was found. self.user_agent = os.getenv( @@ -95,6 +113,7 @@ class Config(metaclass=Singleton): "Mozilla/5.0 (Macintosh; Intel Mac OS X 10_15_4) AppleWebKit/537.36" " (KHTML, like Gecko) Chrome/83.0.4103.97 Safari/537.36", ) + self.redis_host = os.getenv("REDIS_HOST", "localhost") self.redis_port = os.getenv("REDIS_PORT", "6379") self.redis_password = os.getenv("REDIS_PASSWORD", "") @@ -106,6 +125,17 @@ class Config(metaclass=Singleton): # Initialize the OpenAI API client openai.api_key = self.openai_api_key + self.plugins_dir = os.getenv("PLUGINS_DIR", "plugins") + self.plugins: List[AutoGPTPluginTemplate] = [] + self.plugins_openai = [] + + plugins_allowlist = os.getenv("ALLOWLISTED_PLUGINS") + if plugins_allowlist: + self.plugins_allowlist = plugins_allowlist.split(",") + else: + self.plugins_allowlist = [] + self.plugins_denylist = [] + def get_azure_deployment_id_for_model(self, model: str) -> str: """ Returns the relevant deployment id for the model specified. @@ -131,7 +161,7 @@ class Config(metaclass=Singleton): else: return "" - AZURE_CONFIG_FILE = os.path.join(os.path.dirname(__file__), "..", "azure.yaml") + AZURE_CONFIG_FILE = os.path.join(os.path.dirname(__file__), "../..", "azure.yaml") def load_azure_config(self, config_file: str = AZURE_CONFIG_FILE) -> None: """ @@ -154,7 +184,7 @@ class Config(metaclass=Singleton): self.openai_api_version = ( config_params.get("azure_api_version") or "2023-03-15-preview" ) - self.azure_model_to_deployment_id_map = config_params.get("azure_model_map", []) + self.azure_model_to_deployment_id_map = config_params.get("azure_model_map", {}) def set_continuous_mode(self, value: bool) -> None: """Set the continuous mode value.""" @@ -188,10 +218,6 @@ class Config(metaclass=Singleton): """Set the browse_website command chunk max length value.""" self.browse_chunk_max_length = value - def set_browse_summary_max_token(self, value: int) -> None: - """Set the browse_website command summary max token value.""" - self.browse_summary_max_token = value - def set_openai_api_key(self, value: str) -> None: """Set the OpenAI API key value.""" self.openai_api_key = value @@ -228,6 +254,10 @@ class Config(metaclass=Singleton): """Set the debug mode value.""" self.debug_mode = value + def set_plugins(self, value: list) -> None: + """Set the plugins value.""" + self.plugins = value + def check_openai_api_key() -> None: """Check if the OpenAI API key is set in config.py or as an environment variable.""" @@ -237,5 +267,5 @@ def check_openai_api_key() -> None: Fore.RED + "Please set your OpenAI API key in .env or as an environment variable." ) - print("You can get your key from https://beta.openai.com/account/api-keys") + print("You can get your key from https://platform.openai.com/account/api-keys") exit(1) diff --git a/autogpt/configurator.py b/autogpt/configurator.py new file mode 100644 index 00000000..1dc3be12 --- /dev/null +++ b/autogpt/configurator.py @@ -0,0 +1,134 @@ +"""Configurator module.""" +import click +from colorama import Back, Fore, Style + +from autogpt import utils +from autogpt.config import Config +from autogpt.logs import logger +from autogpt.memory import get_supported_memory_backends + +CFG = Config() + + +def create_config( + continuous: bool, + continuous_limit: int, + ai_settings_file: str, + skip_reprompt: bool, + speak: bool, + debug: bool, + gpt3only: bool, + gpt4only: bool, + memory_type: str, + browser_name: str, + allow_downloads: bool, + skip_news: bool, +) -> None: + """Updates the config object with the given arguments. + + Args: + continuous (bool): Whether to run in continuous mode + continuous_limit (int): The number of times to run in continuous mode + ai_settings_file (str): The path to the ai_settings.yaml file + skip_reprompt (bool): Whether to skip the re-prompting messages at the beginning of the script + speak (bool): Whether to enable speak mode + debug (bool): Whether to enable debug mode + gpt3only (bool): Whether to enable GPT3.5 only mode + gpt4only (bool): Whether to enable GPT4 only mode + memory_type (str): The type of memory backend to use + browser_name (str): The name of the browser to use when using selenium to scrape the web + allow_downloads (bool): Whether to allow Auto-GPT to download files natively + skips_news (bool): Whether to suppress the output of latest news on startup + """ + CFG.set_debug_mode(False) + CFG.set_continuous_mode(False) + CFG.set_speak_mode(False) + + if debug: + logger.typewriter_log("Debug Mode: ", Fore.GREEN, "ENABLED") + CFG.set_debug_mode(True) + + if continuous: + logger.typewriter_log("Continuous Mode: ", Fore.RED, "ENABLED") + logger.typewriter_log( + "WARNING: ", + Fore.RED, + "Continuous mode is not recommended. It is potentially dangerous and may" + " cause your AI to run forever or carry out actions you would not usually" + " authorise. Use at your own risk.", + ) + CFG.set_continuous_mode(True) + + if continuous_limit: + logger.typewriter_log( + "Continuous Limit: ", Fore.GREEN, f"{continuous_limit}" + ) + CFG.set_continuous_limit(continuous_limit) + + # Check if continuous limit is used without continuous mode + if continuous_limit and not continuous: + raise click.UsageError("--continuous-limit can only be used with --continuous") + + if speak: + logger.typewriter_log("Speak Mode: ", Fore.GREEN, "ENABLED") + CFG.set_speak_mode(True) + + if gpt3only: + logger.typewriter_log("GPT3.5 Only Mode: ", Fore.GREEN, "ENABLED") + CFG.set_smart_llm_model(CFG.fast_llm_model) + + if gpt4only: + logger.typewriter_log("GPT4 Only Mode: ", Fore.GREEN, "ENABLED") + CFG.set_fast_llm_model(CFG.smart_llm_model) + + if memory_type: + supported_memory = get_supported_memory_backends() + chosen = memory_type + if chosen not in supported_memory: + logger.typewriter_log( + "ONLY THE FOLLOWING MEMORY BACKENDS ARE SUPPORTED: ", + Fore.RED, + f"{supported_memory}", + ) + logger.typewriter_log("Defaulting to: ", Fore.YELLOW, CFG.memory_backend) + else: + CFG.memory_backend = chosen + + if skip_reprompt: + logger.typewriter_log("Skip Re-prompt: ", Fore.GREEN, "ENABLED") + CFG.skip_reprompt = True + + if ai_settings_file: + file = ai_settings_file + + # Validate file + (validated, message) = utils.validate_yaml_file(file) + if not validated: + logger.typewriter_log("FAILED FILE VALIDATION", Fore.RED, message) + logger.double_check() + exit(1) + + logger.typewriter_log("Using AI Settings File:", Fore.GREEN, file) + CFG.ai_settings_file = file + CFG.skip_reprompt = True + + if allow_downloads: + logger.typewriter_log("Native Downloading:", Fore.GREEN, "ENABLED") + logger.typewriter_log( + "WARNING: ", + Fore.YELLOW, + f"{Back.LIGHTYELLOW_EX}Auto-GPT will now be able to download and save files to your machine.{Back.RESET} " + + "It is recommended that you monitor any files it downloads carefully.", + ) + logger.typewriter_log( + "WARNING: ", + Fore.YELLOW, + f"{Back.RED + Style.BRIGHT}ALWAYS REMEMBER TO NEVER OPEN FILES YOU AREN'T SURE OF!{Style.RESET_ALL}", + ) + CFG.allow_downloads = True + + if skip_news: + CFG.skip_news = True + + if browser_name: + CFG.selenium_web_browser = browser_name diff --git a/autogpt/json_fixes/auto_fix.py b/autogpt/json_fixes/auto_fix.py deleted file mode 100644 index 0d3bd73c..00000000 --- a/autogpt/json_fixes/auto_fix.py +++ /dev/null @@ -1,53 +0,0 @@ -"""This module contains the function to fix JSON strings using GPT-3.""" -import json - -from autogpt.llm_utils import call_ai_function -from autogpt.logs import logger -from autogpt.config import Config - -CFG = Config() - - -def fix_json(json_string: str, schema: str) -> str: - """Fix the given JSON string to make it parseable and fully compliant with - the provided schema. - - Args: - json_string (str): The JSON string to fix. - schema (str): The schema to use to fix the JSON. - Returns: - str: The fixed JSON string. - """ - # Try to fix the JSON using GPT: - function_string = "def fix_json(json_string: str, schema:str=None) -> str:" - args = [f"'''{json_string}'''", f"'''{schema}'''"] - description_string = ( - "This function takes a JSON string and ensures that it" - " is parseable and fully compliant with the provided schema. If an object" - " or field specified in the schema isn't contained within the correct JSON," - " it is omitted. The function also escapes any double quotes within JSON" - " string values to ensure that they are valid. If the JSON string contains" - " any None or NaN values, they are replaced with null before being parsed." - ) - - # If it doesn't already start with a "`", add one: - if not json_string.startswith("`"): - json_string = "```json\n" + json_string + "\n```" - result_string = call_ai_function( - function_string, args, description_string, model=CFG.fast_llm_model - ) - logger.debug("------------ JSON FIX ATTEMPT ---------------") - logger.debug(f"Original JSON: {json_string}") - logger.debug("-----------") - logger.debug(f"Fixed JSON: {result_string}") - logger.debug("----------- END OF FIX ATTEMPT ----------------") - - try: - json.loads(result_string) # just check the validity - return result_string - except json.JSONDecodeError: - # Get the call stack: - # import traceback - # call_stack = traceback.format_exc() - # print(f"Failed to fix JSON: '{json_string}' "+call_stack) - return "failed" diff --git a/autogpt/json_fixes/bracket_termination.py b/autogpt/json_fixes/bracket_termination.py deleted file mode 100644 index dd9a8376..00000000 --- a/autogpt/json_fixes/bracket_termination.py +++ /dev/null @@ -1,36 +0,0 @@ -"""Fix JSON brackets.""" -from __future__ import annotations - -import contextlib -import json -from typing import Optional -from autogpt.config import Config - -CFG = Config() - - -def balance_braces(json_string: str) -> Optional[str]: - """ - Balance the braces in a JSON string. - - Args: - json_string (str): The JSON string. - - Returns: - str: The JSON string with braces balanced. - """ - - open_braces_count = json_string.count("{") - close_braces_count = json_string.count("}") - - while open_braces_count > close_braces_count: - json_string += "}" - close_braces_count += 1 - - while close_braces_count > open_braces_count: - json_string = json_string.rstrip("}") - close_braces_count -= 1 - - with contextlib.suppress(json.JSONDecodeError): - json.loads(json_string) - return json_string diff --git a/autogpt/json_fixes/escaping.py b/autogpt/json_fixes/escaping.py deleted file mode 100644 index 68eb1714..00000000 --- a/autogpt/json_fixes/escaping.py +++ /dev/null @@ -1,33 +0,0 @@ -""" Fix invalid escape sequences in JSON strings. """ -import json - -from autogpt.config import Config -from autogpt.json_fixes.utilities import extract_char_position - -CFG = Config() - - -def fix_invalid_escape(json_to_load: str, error_message: str) -> str: - """Fix invalid escape sequences in JSON strings. - - Args: - json_to_load (str): The JSON string. - error_message (str): The error message from the JSONDecodeError - exception. - - Returns: - str: The JSON string with invalid escape sequences fixed. - """ - while error_message.startswith("Invalid \\escape"): - bad_escape_location = extract_char_position(error_message) - json_to_load = ( - json_to_load[:bad_escape_location] + json_to_load[bad_escape_location + 1 :] - ) - try: - json.loads(json_to_load) - return json_to_load - except json.JSONDecodeError as e: - if CFG.debug_mode: - print("json loads error - fix invalid escape", e) - error_message = str(e) - return json_to_load diff --git a/autogpt/json_fixes/master_json_fix_method.py b/autogpt/json_fixes/master_json_fix_method.py deleted file mode 100644 index 7a2cf3cc..00000000 --- a/autogpt/json_fixes/master_json_fix_method.py +++ /dev/null @@ -1,28 +0,0 @@ -from typing import Any, Dict - -from autogpt.config import Config -from autogpt.logs import logger -from autogpt.speech import say_text -CFG = Config() - - -def fix_json_using_multiple_techniques(assistant_reply: str) -> Dict[Any, Any]: - from autogpt.json_fixes.parsing import attempt_to_fix_json_by_finding_outermost_brackets - - from autogpt.json_fixes.parsing import fix_and_parse_json - - # Parse and print Assistant response - assistant_reply_json = fix_and_parse_json(assistant_reply) - if assistant_reply_json == {}: - assistant_reply_json = attempt_to_fix_json_by_finding_outermost_brackets( - assistant_reply - ) - - if assistant_reply_json != {}: - return assistant_reply_json - - logger.error("Error: The following AI output couldn't be converted to a JSON:\n", assistant_reply) - if CFG.speak_mode: - say_text("I have received an invalid JSON response from the OpenAI API.") - - return {} diff --git a/autogpt/json_fixes/missing_quotes.py b/autogpt/json_fixes/missing_quotes.py deleted file mode 100644 index 552a1517..00000000 --- a/autogpt/json_fixes/missing_quotes.py +++ /dev/null @@ -1,27 +0,0 @@ -"""Fix quotes in a JSON string.""" -import json -import re - - -def add_quotes_to_property_names(json_string: str) -> str: - """ - Add quotes to property names in a JSON string. - - Args: - json_string (str): The JSON string. - - Returns: - str: The JSON string with quotes added to property names. - """ - - def replace_func(match: re.Match) -> str: - return f'"{match[1]}":' - - property_name_pattern = re.compile(r"(\w+):") - corrected_json_string = property_name_pattern.sub(replace_func, json_string) - - try: - json.loads(corrected_json_string) - return corrected_json_string - except json.JSONDecodeError as e: - raise e diff --git a/autogpt/json_fixes/utilities.py b/autogpt/json_fixes/utilities.py deleted file mode 100644 index 0852b18a..00000000 --- a/autogpt/json_fixes/utilities.py +++ /dev/null @@ -1,20 +0,0 @@ -"""Utilities for the json_fixes package.""" -import re - - -def extract_char_position(error_message: str) -> int: - """Extract the character position from the JSONDecodeError message. - - Args: - error_message (str): The error message from the JSONDecodeError - exception. - - Returns: - int: The character position. - """ - - char_pattern = re.compile(r"\(char (\d+)\)") - if match := char_pattern.search(error_message): - return int(match[1]) - else: - raise ValueError("Character position not found in the error message.") diff --git a/autogpt/json_fixes/__init__.py b/autogpt/json_utils/__init__.py similarity index 100% rename from autogpt/json_fixes/__init__.py rename to autogpt/json_utils/__init__.py diff --git a/autogpt/json_utils/json_fix_general.py b/autogpt/json_utils/json_fix_general.py new file mode 100644 index 00000000..7010fa3b --- /dev/null +++ b/autogpt/json_utils/json_fix_general.py @@ -0,0 +1,124 @@ +"""This module contains functions to fix JSON strings using general programmatic approaches, suitable for addressing +common JSON formatting issues.""" +from __future__ import annotations + +import contextlib +import json +import re +from typing import Optional + +from autogpt.config import Config +from autogpt.json_utils.utilities import extract_char_position + +CFG = Config() + + +def fix_invalid_escape(json_to_load: str, error_message: str) -> str: + """Fix invalid escape sequences in JSON strings. + + Args: + json_to_load (str): The JSON string. + error_message (str): The error message from the JSONDecodeError + exception. + + Returns: + str: The JSON string with invalid escape sequences fixed. + """ + while error_message.startswith("Invalid \\escape"): + bad_escape_location = extract_char_position(error_message) + json_to_load = ( + json_to_load[:bad_escape_location] + json_to_load[bad_escape_location + 1 :] + ) + try: + json.loads(json_to_load) + return json_to_load + except json.JSONDecodeError as e: + if CFG.debug_mode: + print("json loads error - fix invalid escape", e) + error_message = str(e) + return json_to_load + + +def balance_braces(json_string: str) -> Optional[str]: + """ + Balance the braces in a JSON string. + + Args: + json_string (str): The JSON string. + + Returns: + str: The JSON string with braces balanced. + """ + + open_braces_count = json_string.count("{") + close_braces_count = json_string.count("}") + + while open_braces_count > close_braces_count: + json_string += "}" + close_braces_count += 1 + + while close_braces_count > open_braces_count: + json_string = json_string.rstrip("}") + close_braces_count -= 1 + + with contextlib.suppress(json.JSONDecodeError): + json.loads(json_string) + return json_string + + +def add_quotes_to_property_names(json_string: str) -> str: + """ + Add quotes to property names in a JSON string. + + Args: + json_string (str): The JSON string. + + Returns: + str: The JSON string with quotes added to property names. + """ + + def replace_func(match: re.Match) -> str: + return f'"{match[1]}":' + + property_name_pattern = re.compile(r"(\w+):") + corrected_json_string = property_name_pattern.sub(replace_func, json_string) + + try: + json.loads(corrected_json_string) + return corrected_json_string + except json.JSONDecodeError as e: + raise e + + +def correct_json(json_to_load: str) -> str: + """ + Correct common JSON errors. + Args: + json_to_load (str): The JSON string. + """ + + try: + if CFG.debug_mode: + print("json", json_to_load) + json.loads(json_to_load) + return json_to_load + except json.JSONDecodeError as e: + if CFG.debug_mode: + print("json loads error", e) + error_message = str(e) + if error_message.startswith("Invalid \\escape"): + json_to_load = fix_invalid_escape(json_to_load, error_message) + if error_message.startswith( + "Expecting property name enclosed in double quotes" + ): + json_to_load = add_quotes_to_property_names(json_to_load) + try: + json.loads(json_to_load) + return json_to_load + except json.JSONDecodeError as e: + if CFG.debug_mode: + print("json loads error - add quotes", e) + error_message = str(e) + if balanced_str := balance_braces(json_to_load): + return balanced_str + return json_to_load diff --git a/autogpt/json_fixes/parsing.py b/autogpt/json_utils/json_fix_llm.py similarity index 58% rename from autogpt/json_fixes/parsing.py rename to autogpt/json_utils/json_fix_llm.py index 1e391eed..869aed12 100644 --- a/autogpt/json_fixes/parsing.py +++ b/autogpt/json_utils/json_fix_llm.py @@ -1,21 +1,20 @@ -"""Fix and parse JSON strings.""" +"""This module contains functions to fix JSON strings generated by LLM models, such as ChatGPT, using the assistance +of the ChatGPT API or LLM models.""" from __future__ import annotations import contextlib import json -from typing import Any, Dict, Union +from typing import Any, Dict + from colorama import Fore from regex import regex + from autogpt.config import Config -from autogpt.json_fixes.auto_fix import fix_json -from autogpt.json_fixes.bracket_termination import balance_braces -from autogpt.json_fixes.escaping import fix_invalid_escape -from autogpt.json_fixes.missing_quotes import add_quotes_to_property_names +from autogpt.json_utils.json_fix_general import correct_json +from autogpt.llm_utils import call_ai_function from autogpt.logs import logger from autogpt.speech import say_text -CFG = Config() - JSON_SCHEMA = """ { "command": { @@ -35,39 +34,82 @@ JSON_SCHEMA = """ } """ +CFG = Config() + + +def auto_fix_json(json_string: str, schema: str) -> str: + """Fix the given JSON string to make it parseable and fully compliant with + the provided schema using GPT-3. -def correct_json(json_to_load: str) -> str: - """ - Correct common JSON errors. Args: - json_to_load (str): The JSON string. + json_string (str): The JSON string to fix. + schema (str): The schema to use to fix the JSON. + Returns: + str: The fixed JSON string. """ + # Try to fix the JSON using GPT: + function_string = "def fix_json(json_string: str, schema:str=None) -> str:" + args = [f"'''{json_string}'''", f"'''{schema}'''"] + description_string = ( + "This function takes a JSON string and ensures that it" + " is parseable and fully compliant with the provided schema. If an object" + " or field specified in the schema isn't contained within the correct JSON," + " it is omitted. The function also escapes any double quotes within JSON" + " string values to ensure that they are valid. If the JSON string contains" + " any None or NaN values, they are replaced with null before being parsed." + ) + + # If it doesn't already start with a "`", add one: + if not json_string.startswith("`"): + json_string = "```json\n" + json_string + "\n```" + result_string = call_ai_function( + function_string, args, description_string, model=CFG.fast_llm_model + ) + logger.debug("------------ JSON FIX ATTEMPT ---------------") + logger.debug(f"Original JSON: {json_string}") + logger.debug("-----------") + logger.debug(f"Fixed JSON: {result_string}") + logger.debug("----------- END OF FIX ATTEMPT ----------------") try: - if CFG.debug_mode: - print("json", json_to_load) - json.loads(json_to_load) - return json_to_load - except json.JSONDecodeError as e: - if CFG.debug_mode: - print("json loads error", e) - error_message = str(e) - if error_message.startswith("Invalid \\escape"): - json_to_load = fix_invalid_escape(json_to_load, error_message) - if error_message.startswith( - "Expecting property name enclosed in double quotes" - ): - json_to_load = add_quotes_to_property_names(json_to_load) - try: - json.loads(json_to_load) - return json_to_load - except json.JSONDecodeError as e: - if CFG.debug_mode: - print("json loads error - add quotes", e) - error_message = str(e) - if balanced_str := balance_braces(json_to_load): - return balanced_str - return json_to_load + json.loads(result_string) # just check the validity + return result_string + except json.JSONDecodeError: # noqa: E722 + # Get the call stack: + # import traceback + # call_stack = traceback.format_exc() + # print(f"Failed to fix JSON: '{json_string}' "+call_stack) + return "failed" + + +def fix_json_using_multiple_techniques(assistant_reply: str) -> Dict[Any, Any]: + """Fix the given JSON string to make it parseable and fully compliant with two techniques. + + Args: + json_string (str): The JSON string to fix. + + Returns: + str: The fixed JSON string. + """ + + # Parse and print Assistant response + assistant_reply_json = fix_and_parse_json(assistant_reply) + if assistant_reply_json == {}: + assistant_reply_json = attempt_to_fix_json_by_finding_outermost_brackets( + assistant_reply + ) + + if assistant_reply_json != {}: + return assistant_reply_json + + logger.error( + "Error: The following AI output couldn't be converted to a JSON:\n", + assistant_reply, + ) + if CFG.speak_mode: + say_text("I have received an invalid JSON response from the OpenAI API.") + + return {} def fix_and_parse_json( @@ -134,7 +176,7 @@ def try_ai_fix( " slightly." ) # Now try to fix this up using the ai_functions - ai_fixed_json = fix_json(json_to_load, JSON_SCHEMA) + ai_fixed_json = auto_fix_json(json_to_load, JSON_SCHEMA) if ai_fixed_json != "failed": return json.loads(ai_fixed_json) diff --git a/autogpt/json_schemas/llm_response_format_1.json b/autogpt/json_utils/llm_response_format_1.json similarity index 100% rename from autogpt/json_schemas/llm_response_format_1.json rename to autogpt/json_utils/llm_response_format_1.json diff --git a/autogpt/json_utils/utilities.py b/autogpt/json_utils/utilities.py new file mode 100644 index 00000000..eb9bb687 --- /dev/null +++ b/autogpt/json_utils/utilities.py @@ -0,0 +1,54 @@ +"""Utilities for the json_fixes package.""" +import json +import re + +from jsonschema import Draft7Validator + +from autogpt.config import Config +from autogpt.logs import logger + +CFG = Config() + + +def extract_char_position(error_message: str) -> int: + """Extract the character position from the JSONDecodeError message. + + Args: + error_message (str): The error message from the JSONDecodeError + exception. + + Returns: + int: The character position. + """ + + char_pattern = re.compile(r"\(char (\d+)\)") + if match := char_pattern.search(error_message): + return int(match[1]) + else: + raise ValueError("Character position not found in the error message.") + + +def validate_json(json_object: object, schema_name: object) -> object: + """ + :type schema_name: object + :param schema_name: + :type json_object: object + """ + with open(f"autogpt/json_utils/{schema_name}.json", "r") as f: + schema = json.load(f) + validator = Draft7Validator(schema) + + if errors := sorted(validator.iter_errors(json_object), key=lambda e: e.path): + logger.error("The JSON object is invalid.") + if CFG.debug_mode: + logger.error( + json.dumps(json_object, indent=4) + ) # Replace 'json_object' with the variable containing the JSON data + logger.error("The following issues were found:") + + for error in errors: + logger.error(f"Error: {error.message}") + elif CFG.debug_mode: + print("The JSON object is valid.") + + return json_object diff --git a/autogpt/json_validation/validate_json.py b/autogpt/json_validation/validate_json.py deleted file mode 100644 index 440c3b0b..00000000 --- a/autogpt/json_validation/validate_json.py +++ /dev/null @@ -1,30 +0,0 @@ -import json -from jsonschema import Draft7Validator -from autogpt.config import Config -from autogpt.logs import logger - -CFG = Config() - - -def validate_json(json_object: object, schema_name: object) -> object: - """ - :type schema_name: object - :param schema_name: - :type json_object: object - """ - with open(f"autogpt/json_schemas/{schema_name}.json", "r") as f: - schema = json.load(f) - validator = Draft7Validator(schema) - - if errors := sorted(validator.iter_errors(json_object), key=lambda e: e.path): - logger.error("The JSON object is invalid.") - if CFG.debug_mode: - logger.error(json.dumps(json_object, indent=4)) # Replace 'json_object' with the variable containing the JSON data - logger.error("The following issues were found:") - - for error in errors: - logger.error(f"Error: {error.message}") - elif CFG.debug_mode: - print("The JSON object is valid.") - - return json_object diff --git a/autogpt/llm_utils.py b/autogpt/llm_utils.py index 2075f934..8b85959c 100644 --- a/autogpt/llm_utils.py +++ b/autogpt/llm_utils.py @@ -1,13 +1,15 @@ from __future__ import annotations -from ast import List import time +from typing import List, Optional import openai +from colorama import Fore, Style from openai.error import APIError, RateLimitError -from colorama import Fore from autogpt.config import Config +from autogpt.logs import logger +from autogpt.types.openai import Message CFG = Config() @@ -36,8 +38,8 @@ def call_ai_function( # For each arg, if any are None, convert to "None": args = [str(arg) if arg is not None else "None" for arg in args] # parse args to comma separated string - args = ", ".join(args) - messages = [ + args: str = ", ".join(args) + messages: List[Message] = [ { "role": "system", "content": f"You are now the following python function: ```# {description}" @@ -52,15 +54,15 @@ def call_ai_function( # Overly simple abstraction until we create something better # simple retry mechanism when getting a rate error or a bad gateway def create_chat_completion( - messages: list, # type: ignore - model: str | None = None, + messages: List[Message], # type: ignore + model: Optional[str] = None, temperature: float = CFG.temperature, - max_tokens: int | None = None, + max_tokens: Optional[int] = None, ) -> str: """Create a chat completion using the OpenAI API Args: - messages (list[dict[str, str]]): The messages to send to the chat completion + messages (List[Message]): The messages to send to the chat completion model (str, optional): The model to use. Defaults to None. temperature (float, optional): The temperature to use. Defaults to 0.9. max_tokens (int, optional): The max tokens to use. Defaults to None. @@ -68,14 +70,28 @@ def create_chat_completion( Returns: str: The response from the chat completion """ - response = None num_retries = 10 + warned_user = False if CFG.debug_mode: print( - Fore.GREEN - + f"Creating chat completion with model {model}, temperature {temperature}," - f" max_tokens {max_tokens}" + Fore.RESET + f"{Fore.GREEN}Creating chat completion with model {model}, temperature {temperature}, max_tokens {max_tokens}{Fore.RESET}" ) + for plugin in CFG.plugins: + if plugin.can_handle_chat_completion( + messages=messages, + model=model, + temperature=temperature, + max_tokens=max_tokens, + ): + message = plugin.handle_chat_completion( + messages=messages, + model=model, + temperature=temperature, + max_tokens=max_tokens, + ) + if message is not None: + return message + response = None for attempt in range(num_retries): backoff = 2 ** (attempt + 2) try: @@ -98,30 +114,47 @@ def create_chat_completion( except RateLimitError: if CFG.debug_mode: print( - Fore.RED + "Error: ", - f"Reached rate limit, passing..." + Fore.RESET, + f"{Fore.RED}Error: ", f"Reached rate limit, passing...{Fore.RESET}" ) + if not warned_user: + logger.double_check( + f"Please double check that you have setup a {Fore.CYAN + Style.BRIGHT}PAID{Style.RESET_ALL} OpenAI API Account. " + + f"You can read more here: {Fore.CYAN}https://github.com/Significant-Gravitas/Auto-GPT#openai-api-keys-configuration{Fore.RESET}" + ) + warned_user = True except APIError as e: - if e.http_status == 502: - pass - else: + if e.http_status != 502: raise if attempt == num_retries - 1: raise if CFG.debug_mode: print( - Fore.RED + "Error: ", - f"API Bad gateway. Waiting {backoff} seconds..." + Fore.RESET, + f"{Fore.RED}Error: ", + f"API Bad gateway. Waiting {backoff} seconds...{Fore.RESET}", ) time.sleep(backoff) if response is None: - raise RuntimeError(f"Failed to get response after {num_retries} retries") - - return response.choices[0].message["content"] + logger.typewriter_log( + "FAILED TO GET RESPONSE FROM OPENAI", + Fore.RED, + "Auto-GPT has failed to get a response from OpenAI's services. " + + f"Try running Auto-GPT again, and if the problem the persists try running it with `{Fore.CYAN}--debug{Fore.RESET}`.", + ) + logger.double_check() + if CFG.debug_mode: + raise RuntimeError(f"Failed to get response after {num_retries} retries") + else: + quit(1) + resp = response.choices[0].message["content"] + for plugin in CFG.plugins: + if not plugin.can_handle_on_response(): + continue + resp = plugin.on_response(resp) + return resp def create_embedding_with_ada(text) -> list: - """Create a embedding with text-ada-002 using the OpenAI SDK""" + """Create an embedding with text-ada-002 using the OpenAI SDK""" num_retries = 10 for attempt in range(num_retries): backoff = 2 ** (attempt + 2) @@ -140,15 +173,13 @@ def create_embedding_with_ada(text) -> list: except RateLimitError: pass except APIError as e: - if e.http_status == 502: - pass - else: + if e.http_status != 502: raise if attempt == num_retries - 1: raise if CFG.debug_mode: print( - Fore.RED + "Error: ", - f"API Bad gateway. Waiting {backoff} seconds..." + Fore.RESET, + f"{Fore.RED}Error: ", + f"API Bad gateway. Waiting {backoff} seconds...{Fore.RESET}", ) time.sleep(backoff) diff --git a/autogpt/logs.py b/autogpt/logs.py index c1e436db..35037404 100644 --- a/autogpt/logs.py +++ b/autogpt/logs.py @@ -5,13 +5,13 @@ import os import random import re import time -from logging import LogRecord import traceback +from logging import LogRecord from colorama import Fore, Style -from autogpt.speech import say_text from autogpt.config import Config, Singleton +from autogpt.speech import say_text CFG = Config() @@ -47,7 +47,7 @@ class Logger(metaclass=Singleton): # Info handler in activity.log self.file_handler = logging.FileHandler( - os.path.join(log_dir, log_file), 'a', 'utf-8' + os.path.join(log_dir, log_file), "a", "utf-8" ) self.file_handler.setLevel(logging.DEBUG) info_formatter = AutoGptFormatter( @@ -57,7 +57,7 @@ class Logger(metaclass=Singleton): # Error handler error.log error_handler = logging.FileHandler( - os.path.join(log_dir, error_file), 'a', 'utf-8' + os.path.join(log_dir, error_file), "a", "utf-8" ) error_handler.setLevel(logging.ERROR) error_formatter = AutoGptFormatter( @@ -79,7 +79,7 @@ class Logger(metaclass=Singleton): self.logger.setLevel(logging.DEBUG) def typewriter_log( - self, title="", title_color="", content="", speak_text=False, level=logging.INFO + self, title="", title_color="", content="", speak_text=False, level=logging.INFO ): if speak_text and CFG.speak_mode: say_text(f"{title}. {content}") @@ -95,18 +95,18 @@ class Logger(metaclass=Singleton): ) def debug( - self, - message, - title="", - title_color="", + self, + message, + title="", + title_color="", ): self._log(title, title_color, message, logging.DEBUG) def warn( - self, - message, - title="", - title_color="", + self, + message, + title="", + title_color="", ): self._log(title, title_color, message, logging.WARN) @@ -180,10 +180,10 @@ class AutoGptFormatter(logging.Formatter): def format(self, record: LogRecord) -> str: if hasattr(record, "color"): record.title_color = ( - getattr(record, "color") - + getattr(record, "title") - + " " - + Style.RESET_ALL + getattr(record, "color") + + getattr(record, "title") + + " " + + Style.RESET_ALL ) else: record.title_color = getattr(record, "title") @@ -204,10 +204,10 @@ logger = Logger() def print_assistant_thoughts(ai_name, assistant_reply): """Prints the assistant's thoughts to the console""" - from autogpt.json_fixes.bracket_termination import ( + from autogpt.json_utils.json_fix_llm import ( attempt_to_fix_json_by_finding_outermost_brackets, + fix_and_parse_json, ) - from autogpt.json_fixes.parsing import fix_and_parse_json try: try: @@ -294,7 +294,9 @@ def print_assistant_thoughts(ai_name, assistant_reply): logger.error("Error: \n", call_stack) -def print_assistant_thoughts(ai_name: object, assistant_reply_json_valid: object) -> None: +def print_assistant_thoughts( + ai_name: object, assistant_reply_json_valid: object +) -> None: assistant_thoughts_reasoning = None assistant_thoughts_plan = None assistant_thoughts_speak = None @@ -310,9 +312,7 @@ def print_assistant_thoughts(ai_name: object, assistant_reply_json_valid: object logger.typewriter_log( f"{ai_name.upper()} THOUGHTS:", Fore.YELLOW, f"{assistant_thoughts_text}" ) - logger.typewriter_log( - "REASONING:", Fore.YELLOW, f"{assistant_thoughts_reasoning}" - ) + logger.typewriter_log("REASONING:", Fore.YELLOW, f"{assistant_thoughts_reasoning}") if assistant_thoughts_plan: logger.typewriter_log("PLAN:", Fore.YELLOW, "") # If it's a list, join it into a string @@ -326,9 +326,7 @@ def print_assistant_thoughts(ai_name: object, assistant_reply_json_valid: object for line in lines: line = line.lstrip("- ") logger.typewriter_log("- ", Fore.GREEN, line.strip()) - logger.typewriter_log( - "CRITICISM:", Fore.YELLOW, f"{assistant_thoughts_criticism}" - ) + logger.typewriter_log("CRITICISM:", Fore.YELLOW, f"{assistant_thoughts_criticism}") # Speak the assistant's thoughts if CFG.speak_mode and assistant_thoughts_speak: say_text(assistant_thoughts_speak) diff --git a/autogpt/memory/__init__.py b/autogpt/memory/__init__.py index f5afb8c9..3d18704c 100644 --- a/autogpt/memory/__init__.py +++ b/autogpt/memory/__init__.py @@ -60,8 +60,10 @@ def get_memory(cfg, init=False): memory = RedisMemory(cfg) elif cfg.memory_backend == "weaviate": if not WeaviateMemory: - print("Error: Weaviate is not installed. Please install weaviate-client to" - " use Weaviate as a memory backend.") + print( + "Error: Weaviate is not installed. Please install weaviate-client to" + " use Weaviate as a memory backend." + ) else: memory = WeaviateMemory(cfg) elif cfg.memory_backend == "milvus": @@ -93,5 +95,5 @@ __all__ = [ "PineconeMemory", "NoMemory", "MilvusMemory", - "WeaviateMemory" + "WeaviateMemory", ] diff --git a/autogpt/memory/local.py b/autogpt/memory/local.py index 9b911eef..803b6dc6 100644 --- a/autogpt/memory/local.py +++ b/autogpt/memory/local.py @@ -2,13 +2,13 @@ from __future__ import annotations import dataclasses import os -from typing import Any +from typing import Any, List import numpy as np import orjson -from autogpt.memory.base import MemoryProviderSingleton from autogpt.llm_utils import create_embedding_with_ada +from autogpt.memory.base import MemoryProviderSingleton EMBED_DIM = 1536 SAVE_OPTIONS = orjson.OPT_SERIALIZE_NUMPY | orjson.OPT_SERIALIZE_DATACLASS diff --git a/autogpt/memory/milvus.py b/autogpt/memory/milvus.py index c6e7d5a3..44aa72b9 100644 --- a/autogpt/memory/milvus.py +++ b/autogpt/memory/milvus.py @@ -1,11 +1,5 @@ """ Milvus memory storage provider.""" -from pymilvus import ( - connections, - FieldSchema, - CollectionSchema, - DataType, - Collection, -) +from pymilvus import Collection, CollectionSchema, DataType, FieldSchema, connections from autogpt.memory.base import MemoryProviderSingleton, get_ada_embedding @@ -46,7 +40,7 @@ class MilvusMemory(MemoryProviderSingleton): self.collection.load() def add(self, data) -> str: - """Add a embedding of data into memory. + """Add an embedding of data into memory. Args: data (str): The raw text to construct embedding index. diff --git a/autogpt/memory/no_memory.py b/autogpt/memory/no_memory.py index 4035a657..0371e96a 100644 --- a/autogpt/memory/no_memory.py +++ b/autogpt/memory/no_memory.py @@ -53,7 +53,7 @@ class NoMemory(MemoryProviderSingleton): """ return "" - def get_relevant(self, data: str, num_relevant: int = 5) ->list[Any] | None: + def get_relevant(self, data: str, num_relevant: int = 5) -> list[Any] | None: """ Returns all the data in the memory that is relevant to the given data. NoMemory always returns None. diff --git a/autogpt/memory/pinecone.py b/autogpt/memory/pinecone.py index d781073e..27fcd624 100644 --- a/autogpt/memory/pinecone.py +++ b/autogpt/memory/pinecone.py @@ -1,9 +1,9 @@ import pinecone from colorama import Fore, Style +from autogpt.llm_utils import create_embedding_with_ada from autogpt.logs import logger from autogpt.memory.base import MemoryProviderSingleton -from autogpt.llm_utils import create_embedding_with_ada class PineconeMemory(MemoryProviderSingleton): diff --git a/autogpt/memory/redismem.py b/autogpt/memory/redismem.py index 0e8dd71d..082a812c 100644 --- a/autogpt/memory/redismem.py +++ b/autogpt/memory/redismem.py @@ -10,9 +10,9 @@ from redis.commands.search.field import TextField, VectorField from redis.commands.search.indexDefinition import IndexDefinition, IndexType from redis.commands.search.query import Query +from autogpt.llm_utils import create_embedding_with_ada from autogpt.logs import logger from autogpt.memory.base import MemoryProviderSingleton -from autogpt.llm_utils import create_embedding_with_ada SCHEMA = [ TextField("data"), diff --git a/autogpt/memory/weaviate.py b/autogpt/memory/weaviate.py index 6fcce0a0..5408e9a9 100644 --- a/autogpt/memory/weaviate.py +++ b/autogpt/memory/weaviate.py @@ -1,11 +1,13 @@ -from autogpt.config import Config -from autogpt.memory.base import MemoryProviderSingleton, get_ada_embedding import uuid + import weaviate from weaviate import Client from weaviate.embedded import EmbeddedOptions from weaviate.util import generate_uuid5 +from autogpt.config import Config +from autogpt.memory.base import MemoryProviderSingleton, get_ada_embedding + def default_schema(weaviate_index): return { @@ -14,7 +16,7 @@ def default_schema(weaviate_index): { "name": "raw_text", "dataType": ["text"], - "description": "original text for the embedding" + "description": "original text for the embedding", } ], } @@ -24,22 +26,35 @@ class WeaviateMemory(MemoryProviderSingleton): def __init__(self, cfg): auth_credentials = self._build_auth_credentials(cfg) - url = f'{cfg.weaviate_protocol}://{cfg.weaviate_host}:{cfg.weaviate_port}' + url = f"{cfg.weaviate_protocol}://{cfg.weaviate_host}:{cfg.weaviate_port}" if cfg.use_weaviate_embedded: - self.client = Client(embedded_options=EmbeddedOptions( - hostname=cfg.weaviate_host, - port=int(cfg.weaviate_port), - persistence_data_path=cfg.weaviate_embedded_path - )) + self.client = Client( + embedded_options=EmbeddedOptions( + hostname=cfg.weaviate_host, + port=int(cfg.weaviate_port), + persistence_data_path=cfg.weaviate_embedded_path, + ) + ) - print(f"Weaviate Embedded running on: {url} with persistence path: {cfg.weaviate_embedded_path}") + print( + f"Weaviate Embedded running on: {url} with persistence path: {cfg.weaviate_embedded_path}" + ) else: self.client = Client(url, auth_client_secret=auth_credentials) - self.index = cfg.memory_index + self.index = WeaviateMemory.format_classname(cfg.memory_index) self._create_schema() + @staticmethod + def format_classname(index): + # weaviate uses capitalised index names + # The python client uses the following code to format + # index names before the corresponding class is created + if len(index) == 1: + return index.capitalize() + return index[0].capitalize() + index[1:] + def _create_schema(self): schema = default_schema(self.index) if not self.client.schema.contains(schema): @@ -47,7 +62,9 @@ class WeaviateMemory(MemoryProviderSingleton): def _build_auth_credentials(self, cfg): if cfg.weaviate_username and cfg.weaviate_password: - return weaviate.AuthClientPassword(cfg.weaviate_username, cfg.weaviate_password) + return weaviate.AuthClientPassword( + cfg.weaviate_username, cfg.weaviate_password + ) if cfg.weaviate_api_key: return weaviate.AuthApiKey(api_key=cfg.weaviate_api_key) else: @@ -57,16 +74,14 @@ class WeaviateMemory(MemoryProviderSingleton): vector = get_ada_embedding(data) doc_uuid = generate_uuid5(data, self.index) - data_object = { - 'raw_text': data - } + data_object = {"raw_text": data} with self.client.batch as batch: batch.add_data_object( uuid=doc_uuid, data_object=data_object, class_name=self.index, - vector=vector + vector=vector, ) return f"Inserting data into memory at uuid: {doc_uuid}:\n data: {data}" @@ -82,29 +97,31 @@ class WeaviateMemory(MemoryProviderSingleton): # after a call to delete_all self._create_schema() - return 'Obliterated' + return "Obliterated" def get_relevant(self, data, num_relevant=5): query_embedding = get_ada_embedding(data) try: - results = self.client.query.get(self.index, ['raw_text']) \ - .with_near_vector({'vector': query_embedding, 'certainty': 0.7}) \ - .with_limit(num_relevant) \ - .do() + results = ( + self.client.query.get(self.index, ["raw_text"]) + .with_near_vector({"vector": query_embedding, "certainty": 0.7}) + .with_limit(num_relevant) + .do() + ) - if len(results['data']['Get'][self.index]) > 0: - return [str(item['raw_text']) for item in results['data']['Get'][self.index]] + if len(results["data"]["Get"][self.index]) > 0: + return [ + str(item["raw_text"]) for item in results["data"]["Get"][self.index] + ] else: return [] except Exception as err: - print(f'Unexpected error {err=}, {type(err)=}') + print(f"Unexpected error {err=}, {type(err)=}") return [] def get_stats(self): - result = self.client.query.aggregate(self.index) \ - .with_meta_count() \ - .do() - class_data = result['data']['Aggregate'][self.index] + result = self.client.query.aggregate(self.index).with_meta_count().do() + class_data = result["data"]["Aggregate"][self.index] - return class_data[0]['meta'] if class_data else {} + return class_data[0]["meta"] if class_data else {} diff --git a/autogpt/models/base_open_ai_plugin.py b/autogpt/models/base_open_ai_plugin.py new file mode 100644 index 00000000..046295c0 --- /dev/null +++ b/autogpt/models/base_open_ai_plugin.py @@ -0,0 +1,199 @@ +"""Handles loading of plugins.""" +from typing import Any, Dict, List, Optional, Tuple, TypedDict, TypeVar + +from auto_gpt_plugin_template import AutoGPTPluginTemplate + +PromptGenerator = TypeVar("PromptGenerator") + + +class Message(TypedDict): + role: str + content: str + + +class BaseOpenAIPlugin(AutoGPTPluginTemplate): + """ + This is a BaseOpenAIPlugin class for generating Auto-GPT plugins. + """ + + def __init__(self, manifests_specs_clients: dict): + # super().__init__() + self._name = manifests_specs_clients["manifest"]["name_for_model"] + self._version = manifests_specs_clients["manifest"]["schema_version"] + self._description = manifests_specs_clients["manifest"]["description_for_model"] + self._client = manifests_specs_clients["client"] + self._manifest = manifests_specs_clients["manifest"] + self._openapi_spec = manifests_specs_clients["openapi_spec"] + + def can_handle_on_response(self) -> bool: + """This method is called to check that the plugin can + handle the on_response method. + Returns: + bool: True if the plugin can handle the on_response method.""" + return False + + def on_response(self, response: str, *args, **kwargs) -> str: + """This method is called when a response is received from the model.""" + return response + + def can_handle_post_prompt(self) -> bool: + """This method is called to check that the plugin can + handle the post_prompt method. + Returns: + bool: True if the plugin can handle the post_prompt method.""" + return False + + def post_prompt(self, prompt: PromptGenerator) -> PromptGenerator: + """This method is called just after the generate_prompt is called, + but actually before the prompt is generated. + Args: + prompt (PromptGenerator): The prompt generator. + Returns: + PromptGenerator: The prompt generator. + """ + return prompt + + def can_handle_on_planning(self) -> bool: + """This method is called to check that the plugin can + handle the on_planning method. + Returns: + bool: True if the plugin can handle the on_planning method.""" + return False + + def on_planning( + self, prompt: PromptGenerator, messages: List[Message] + ) -> Optional[str]: + """This method is called before the planning chat completion is done. + Args: + prompt (PromptGenerator): The prompt generator. + messages (List[str]): The list of messages. + """ + pass + + def can_handle_post_planning(self) -> bool: + """This method is called to check that the plugin can + handle the post_planning method. + Returns: + bool: True if the plugin can handle the post_planning method.""" + return False + + def post_planning(self, response: str) -> str: + """This method is called after the planning chat completion is done. + Args: + response (str): The response. + Returns: + str: The resulting response. + """ + return response + + def can_handle_pre_instruction(self) -> bool: + """This method is called to check that the plugin can + handle the pre_instruction method. + Returns: + bool: True if the plugin can handle the pre_instruction method.""" + return False + + def pre_instruction(self, messages: List[Message]) -> List[Message]: + """This method is called before the instruction chat is done. + Args: + messages (List[Message]): The list of context messages. + Returns: + List[Message]: The resulting list of messages. + """ + return messages + + def can_handle_on_instruction(self) -> bool: + """This method is called to check that the plugin can + handle the on_instruction method. + Returns: + bool: True if the plugin can handle the on_instruction method.""" + return False + + def on_instruction(self, messages: List[Message]) -> Optional[str]: + """This method is called when the instruction chat is done. + Args: + messages (List[Message]): The list of context messages. + Returns: + Optional[str]: The resulting message. + """ + pass + + def can_handle_post_instruction(self) -> bool: + """This method is called to check that the plugin can + handle the post_instruction method. + Returns: + bool: True if the plugin can handle the post_instruction method.""" + return False + + def post_instruction(self, response: str) -> str: + """This method is called after the instruction chat is done. + Args: + response (str): The response. + Returns: + str: The resulting response. + """ + return response + + def can_handle_pre_command(self) -> bool: + """This method is called to check that the plugin can + handle the pre_command method. + Returns: + bool: True if the plugin can handle the pre_command method.""" + return False + + def pre_command( + self, command_name: str, arguments: Dict[str, Any] + ) -> Tuple[str, Dict[str, Any]]: + """This method is called before the command is executed. + Args: + command_name (str): The command name. + arguments (Dict[str, Any]): The arguments. + Returns: + Tuple[str, Dict[str, Any]]: The command name and the arguments. + """ + return command_name, arguments + + def can_handle_post_command(self) -> bool: + """This method is called to check that the plugin can + handle the post_command method. + Returns: + bool: True if the plugin can handle the post_command method.""" + return False + + def post_command(self, command_name: str, response: str) -> str: + """This method is called after the command is executed. + Args: + command_name (str): The command name. + response (str): The response. + Returns: + str: The resulting response. + """ + return response + + def can_handle_chat_completion( + self, messages: Dict[Any, Any], model: str, temperature: float, max_tokens: int + ) -> bool: + """This method is called to check that the plugin can + handle the chat_completion method. + Args: + messages (List[Message]): The messages. + model (str): The model name. + temperature (float): The temperature. + max_tokens (int): The max tokens. + Returns: + bool: True if the plugin can handle the chat_completion method.""" + return False + + def handle_chat_completion( + self, messages: List[Message], model: str, temperature: float, max_tokens: int + ) -> str: + """This method is called when the chat completion is done. + Args: + messages (List[Message]): The messages. + model (str): The model name. + temperature (float): The temperature. + max_tokens (int): The max tokens. + Returns: + str: The resulting response. + """ + pass diff --git a/autogpt/plugins.py b/autogpt/plugins.py new file mode 100644 index 00000000..32e29acb --- /dev/null +++ b/autogpt/plugins.py @@ -0,0 +1,265 @@ +"""Handles loading of plugins.""" + +import importlib +import json +import os +import zipfile +from pathlib import Path +from typing import List, Optional, Tuple +from urllib.parse import urlparse +from zipimport import zipimporter + +import openapi_python_client +import requests +from auto_gpt_plugin_template import AutoGPTPluginTemplate +from openapi_python_client.cli import Config as OpenAPIConfig + +from autogpt.config import Config +from autogpt.models.base_open_ai_plugin import BaseOpenAIPlugin + + +def inspect_zip_for_module(zip_path: str, debug: bool = False) -> Optional[str]: + """ + Inspect a zipfile for a module. + + Args: + zip_path (str): Path to the zipfile. + debug (bool, optional): Enable debug logging. Defaults to False. + + Returns: + Optional[str]: The name of the module if found, else None. + """ + with zipfile.ZipFile(zip_path, "r") as zfile: + for name in zfile.namelist(): + if name.endswith("__init__.py"): + if debug: + print(f"Found module '{name}' in the zipfile at: {name}") + return name + if debug: + print(f"Module '__init__.py' not found in the zipfile @ {zip_path}.") + return None + + +def write_dict_to_json_file(data: dict, file_path: str) -> None: + """ + Write a dictionary to a JSON file. + Args: + data (dict): Dictionary to write. + file_path (str): Path to the file. + """ + with open(file_path, "w") as file: + json.dump(data, file, indent=4) + + +def fetch_openai_plugins_manifest_and_spec(cfg: Config) -> dict: + """ + Fetch the manifest for a list of OpenAI plugins. + Args: + urls (List): List of URLs to fetch. + Returns: + dict: per url dictionary of manifest and spec. + """ + # TODO add directory scan + manifests = {} + for url in cfg.plugins_openai: + openai_plugin_client_dir = f"{cfg.plugins_dir}/openai/{urlparse(url).netloc}" + create_directory_if_not_exists(openai_plugin_client_dir) + if not os.path.exists(f"{openai_plugin_client_dir}/ai-plugin.json"): + try: + response = requests.get(f"{url}/.well-known/ai-plugin.json") + if response.status_code == 200: + manifest = response.json() + if manifest["schema_version"] != "v1": + print( + f"Unsupported manifest version: {manifest['schem_version']} for {url}" + ) + continue + if manifest["api"]["type"] != "openapi": + print( + f"Unsupported API type: {manifest['api']['type']} for {url}" + ) + continue + write_dict_to_json_file( + manifest, f"{openai_plugin_client_dir}/ai-plugin.json" + ) + else: + print(f"Failed to fetch manifest for {url}: {response.status_code}") + except requests.exceptions.RequestException as e: + print(f"Error while requesting manifest from {url}: {e}") + else: + print(f"Manifest for {url} already exists") + manifest = json.load(open(f"{openai_plugin_client_dir}/ai-plugin.json")) + if not os.path.exists(f"{openai_plugin_client_dir}/openapi.json"): + openapi_spec = openapi_python_client._get_document( + url=manifest["api"]["url"], path=None, timeout=5 + ) + write_dict_to_json_file( + openapi_spec, f"{openai_plugin_client_dir}/openapi.json" + ) + else: + print(f"OpenAPI spec for {url} already exists") + openapi_spec = json.load(open(f"{openai_plugin_client_dir}/openapi.json")) + manifests[url] = {"manifest": manifest, "openapi_spec": openapi_spec} + return manifests + + +def create_directory_if_not_exists(directory_path: str) -> bool: + """ + Create a directory if it does not exist. + Args: + directory_path (str): Path to the directory. + Returns: + bool: True if the directory was created, else False. + """ + if not os.path.exists(directory_path): + try: + os.makedirs(directory_path) + print(f"Created directory: {directory_path}") + return True + except OSError as e: + print(f"Error creating directory {directory_path}: {e}") + return False + else: + print(f"Directory {directory_path} already exists") + return True + + +def initialize_openai_plugins( + manifests_specs: dict, cfg: Config, debug: bool = False +) -> dict: + """ + Initialize OpenAI plugins. + Args: + manifests_specs (dict): per url dictionary of manifest and spec. + cfg (Config): Config instance including plugins config + debug (bool, optional): Enable debug logging. Defaults to False. + Returns: + dict: per url dictionary of manifest, spec and client. + """ + openai_plugins_dir = f"{cfg.plugins_dir}/openai" + if create_directory_if_not_exists(openai_plugins_dir): + for url, manifest_spec in manifests_specs.items(): + openai_plugin_client_dir = f"{openai_plugins_dir}/{urlparse(url).hostname}" + _meta_option = (openapi_python_client.MetaType.SETUP,) + _config = OpenAPIConfig( + **{ + "project_name_override": "client", + "package_name_override": "client", + } + ) + prev_cwd = Path.cwd() + os.chdir(openai_plugin_client_dir) + Path("ai-plugin.json") + if not os.path.exists("client"): + client_results = openapi_python_client.create_new_client( + url=manifest_spec["manifest"]["api"]["url"], + path=None, + meta=_meta_option, + config=_config, + ) + if client_results: + print( + f"Error creating OpenAPI client: {client_results[0].header} \n" + f" details: {client_results[0].detail}" + ) + continue + spec = importlib.util.spec_from_file_location( + "client", "client/client/client.py" + ) + module = importlib.util.module_from_spec(spec) + spec.loader.exec_module(module) + client = module.Client(base_url=url) + os.chdir(prev_cwd) + manifest_spec["client"] = client + return manifests_specs + + +def instantiate_openai_plugin_clients( + manifests_specs_clients: dict, cfg: Config, debug: bool = False +) -> dict: + """ + Instantiates BaseOpenAIPlugin instances for each OpenAI plugin. + Args: + manifests_specs_clients (dict): per url dictionary of manifest, spec and client. + cfg (Config): Config instance including plugins config + debug (bool, optional): Enable debug logging. Defaults to False. + Returns: + plugins (dict): per url dictionary of BaseOpenAIPlugin instances. + + """ + plugins = {} + for url, manifest_spec_client in manifests_specs_clients.items(): + plugins[url] = BaseOpenAIPlugin(manifest_spec_client) + return plugins + + +def scan_plugins(cfg: Config, debug: bool = False) -> List[AutoGPTPluginTemplate]: + """Scan the plugins directory for plugins and loads them. + + Args: + cfg (Config): Config instance including plugins config + debug (bool, optional): Enable debug logging. Defaults to False. + + Returns: + List[Tuple[str, Path]]: List of plugins. + """ + loaded_plugins = [] + # Generic plugins + plugins_path_path = Path(cfg.plugins_dir) + for plugin in plugins_path_path.glob("*.zip"): + if module := inspect_zip_for_module(str(plugin), debug): + plugin = Path(plugin) + module = Path(module) + if debug: + print(f"Plugin: {plugin} Module: {module}") + zipped_package = zipimporter(str(plugin)) + zipped_module = zipped_package.load_module(str(module.parent)) + for key in dir(zipped_module): + if key.startswith("__"): + continue + a_module = getattr(zipped_module, key) + a_keys = dir(a_module) + if ( + "_abc_impl" in a_keys + and a_module.__name__ != "AutoGPTPluginTemplate" + and denylist_allowlist_check(a_module.__name__, cfg) + ): + loaded_plugins.append(a_module()) + # OpenAI plugins + if cfg.plugins_openai: + manifests_specs = fetch_openai_plugins_manifest_and_spec(cfg) + if manifests_specs.keys(): + manifests_specs_clients = initialize_openai_plugins( + manifests_specs, cfg, debug + ) + for url, openai_plugin_meta in manifests_specs_clients.items(): + if denylist_allowlist_check(url, cfg): + plugin = BaseOpenAIPlugin(openai_plugin_meta) + loaded_plugins.append(plugin) + + if loaded_plugins: + print(f"\nPlugins found: {len(loaded_plugins)}\n" "--------------------") + for plugin in loaded_plugins: + print(f"{plugin._name}: {plugin._version} - {plugin._description}") + return loaded_plugins + + +def denylist_allowlist_check(plugin_name: str, cfg: Config) -> bool: + """Check if the plugin is in the allowlist or denylist. + + Args: + plugin_name (str): Name of the plugin. + cfg (Config): Config object. + + Returns: + True or False + """ + if plugin_name in cfg.plugins_denylist: + return False + if plugin_name in cfg.plugins_allowlist: + return True + ack = input( + f"WARNNG Plugin {plugin_name} found. But not in the" + " allowlist... Load? (y/n): " + ) + return ack.lower() == "y" diff --git a/autogpt/processing/html.py b/autogpt/processing/html.py index e1912b6a..81387b12 100644 --- a/autogpt/processing/html.py +++ b/autogpt/processing/html.py @@ -1,8 +1,8 @@ """HTML processing functions""" from __future__ import annotations -from requests.compat import urljoin from bs4 import BeautifulSoup +from requests.compat import urljoin def extract_hyperlinks(soup: BeautifulSoup, base_url: str) -> list[tuple[str, str]]: diff --git a/autogpt/processing/text.py b/autogpt/processing/text.py index d30036d8..2122f0f0 100644 --- a/autogpt/processing/text.py +++ b/autogpt/processing/text.py @@ -1,15 +1,24 @@ """Text processing functions""" -from typing import Generator, Optional, Dict +from typing import Dict, Generator, Optional + +import spacy from selenium.webdriver.remote.webdriver import WebDriver -from autogpt.memory import get_memory + +from autogpt import token_counter from autogpt.config import Config from autogpt.llm_utils import create_chat_completion +from autogpt.memory import get_memory CFG = Config() MEMORY = get_memory(CFG) -def split_text(text: str, max_length: int = 8192) -> Generator[str, None, None]: +def split_text( + text: str, + max_length: int = CFG.browse_chunk_max_length, + model: str = CFG.fast_llm_model, + question: str = "", +) -> Generator[str, None, None]: """Split text into chunks of a maximum length Args: @@ -22,21 +31,46 @@ def split_text(text: str, max_length: int = 8192) -> Generator[str, None, None]: Raises: ValueError: If the text is longer than the maximum length """ - paragraphs = text.split("\n") - current_length = 0 + flatened_paragraphs = " ".join(text.split("\n")) + nlp = spacy.load(CFG.browse_spacy_language_model) + nlp.add_pipe("sentencizer") + doc = nlp(flatened_paragraphs) + sentences = [sent.text.strip() for sent in doc.sents] + current_chunk = [] - for paragraph in paragraphs: - if current_length + len(paragraph) + 1 <= max_length: - current_chunk.append(paragraph) - current_length += len(paragraph) + 1 + for sentence in sentences: + message_with_additional_sentence = [ + create_message(" ".join(current_chunk) + " " + sentence, question) + ] + + expected_token_usage = ( + token_usage_of_chunk(messages=message_with_additional_sentence, model=model) + + 1 + ) + if expected_token_usage <= max_length: + current_chunk.append(sentence) else: - yield "\n".join(current_chunk) - current_chunk = [paragraph] - current_length = len(paragraph) + 1 + yield " ".join(current_chunk) + current_chunk = [sentence] + message_this_sentence_only = [ + create_message(" ".join(current_chunk), question) + ] + expected_token_usage = ( + token_usage_of_chunk(messages=message_this_sentence_only, model=model) + + 1 + ) + if expected_token_usage > max_length: + raise ValueError( + f"Sentence is too long in webpage: {expected_token_usage} tokens." + ) if current_chunk: - yield "\n".join(current_chunk) + yield " ".join(current_chunk) + + +def token_usage_of_chunk(messages, model): + return token_counter.count_message_tokens(messages, model) def summarize_text( @@ -56,11 +90,16 @@ def summarize_text( if not text: return "Error: No text to summarize" + model = CFG.fast_llm_model text_length = len(text) print(f"Text length: {text_length} characters") summaries = [] - chunks = list(split_text(text)) + chunks = list( + split_text( + text, max_length=CFG.browse_chunk_max_length, model=model, question=question + ), + ) scroll_ratio = 1 / len(chunks) for i, chunk in enumerate(chunks): @@ -72,16 +111,20 @@ def summarize_text( MEMORY.add(memory_to_add) - print(f"Summarizing chunk {i + 1} / {len(chunks)}") messages = [create_message(chunk, question)] + tokens_for_chunk = token_counter.count_message_tokens(messages, model) + print( + f"Summarizing chunk {i + 1} / {len(chunks)} of length {len(chunk)} characters, or {tokens_for_chunk} tokens" + ) summary = create_chat_completion( - model=CFG.fast_llm_model, + model=model, messages=messages, - max_tokens=CFG.browse_summary_max_token, ) summaries.append(summary) - print(f"Added chunk {i + 1} summary to memory") + print( + f"Added chunk {i + 1} summary to memory, of length {len(summary)} characters" + ) memory_to_add = f"Source: {url}\n" f"Content summary part#{i + 1}: {summary}" @@ -93,9 +136,8 @@ def summarize_text( messages = [create_message(combined_summary, question)] return create_chat_completion( - model=CFG.fast_llm_model, + model=model, messages=messages, - max_tokens=CFG.browse_summary_max_token, ) diff --git a/autogpt/prompts/__init__.py b/autogpt/prompts/__init__.py new file mode 100644 index 00000000..e69de29b diff --git a/autogpt/promptgenerator.py b/autogpt/prompts/generator.py similarity index 78% rename from autogpt/promptgenerator.py rename to autogpt/prompts/generator.py index 0ad7046a..c9a441d8 100644 --- a/autogpt/promptgenerator.py +++ b/autogpt/prompts/generator.py @@ -1,8 +1,6 @@ """ A module for generating custom prompt strings.""" -from __future__ import annotations - import json -from typing import Any +from typing import Any, Callable, Dict, List, Optional class PromptGenerator: @@ -20,6 +18,10 @@ class PromptGenerator: self.commands = [] self.resources = [] self.performance_evaluation = [] + self.goals = [] + self.command_registry = None + self.name = "Bob" + self.role = "AI" self.response_format = { "thoughts": { "text": "thought", @@ -40,7 +42,13 @@ class PromptGenerator: """ self.constraints.append(constraint) - def add_command(self, command_label: str, command_name: str, args=None) -> None: + def add_command( + self, + command_label: str, + command_name: str, + args=None, + function: Optional[Callable] = None, + ) -> None: """ Add a command to the commands list with a label, name, and optional arguments. @@ -49,6 +57,8 @@ class PromptGenerator: command_name (str): The name of the command. args (dict, optional): A dictionary containing argument names and their values. Defaults to None. + function (callable, optional): A callable function to be called when + the command is executed. Defaults to None. """ if args is None: args = {} @@ -59,11 +69,12 @@ class PromptGenerator: "label": command_label, "name": command_name, "args": command_args, + "function": function, } self.commands.append(command) - def _generate_command_string(self, command: dict[str, Any]) -> str: + def _generate_command_string(self, command: Dict[str, Any]) -> str: """ Generate a formatted string representation of a command. @@ -96,7 +107,7 @@ class PromptGenerator: """ self.performance_evaluation.append(evaluation) - def _generate_numbered_list(self, items: list[Any], item_type="list") -> str: + def _generate_numbered_list(self, items: List[Any], item_type="list") -> str: """ Generate a numbered list from given items based on the item_type. @@ -109,10 +120,16 @@ class PromptGenerator: str: The formatted numbered list. """ if item_type == "command": - return "\n".join( - f"{i+1}. {self._generate_command_string(item)}" - for i, item in enumerate(items) - ) + command_strings = [] + if self.command_registry: + command_strings += [ + str(item) + for item in self.command_registry.commands.values() + if item.enabled + ] + # These are the commands that are added manually, do_nothing and terminate + command_strings += [self._generate_command_string(item) for item in items] + return "\n".join(f"{i+1}. {item}" for i, item in enumerate(command_strings)) else: return "\n".join(f"{i+1}. {item}" for i, item in enumerate(items)) @@ -134,5 +151,5 @@ class PromptGenerator: f"{self._generate_numbered_list(self.performance_evaluation)}\n\n" "You should only respond in JSON format as described below \nResponse" f" Format: \n{formatted_response_format} \nEnsure the response can be" - " parsed by Python json.loads" + "parsed by Python json.loads" ) diff --git a/autogpt/prompt.py b/autogpt/prompts/prompt.py similarity index 52% rename from autogpt/prompt.py rename to autogpt/prompts/prompt.py index a2b20b1f..79de04ea 100644 --- a/autogpt/prompt.py +++ b/autogpt/prompts/prompt.py @@ -1,16 +1,16 @@ from colorama import Fore + from autogpt.config.ai_config import AIConfig from autogpt.config.config import Config from autogpt.logs import logger -from autogpt.promptgenerator import PromptGenerator -from autogpt.config import Config +from autogpt.prompts.generator import PromptGenerator from autogpt.setup import prompt_user from autogpt.utils import clean_input CFG = Config() -def get_prompt() -> str: +def build_default_prompt_generator() -> PromptGenerator: """ This function generates a prompt string that includes various constraints, commands, resources, and performance evaluations. @@ -19,9 +19,6 @@ def get_prompt() -> str: str: The generated prompt string. """ - # Initialize the Config object - cfg = Config() - # Initialize the PromptGenerator object prompt_generator = PromptGenerator() @@ -41,87 +38,9 @@ def get_prompt() -> str: # Define the command list commands = [ - ("Google Search", "google", {"input": ""}), - ( - "Browse Website", - "browse_website", - {"url": "", "question": ""}, - ), - ( - "Start GPT Agent", - "start_agent", - {"name": "", "task": "", "prompt": ""}, - ), - ( - "Message GPT Agent", - "message_agent", - {"key": "", "message": ""}, - ), - ("List GPT Agents", "list_agents", {}), - ("Delete GPT Agent", "delete_agent", {"key": ""}), - ( - "Clone Repository", - "clone_repository", - {"repository_url": "", "clone_path": ""}, - ), - ("Write to file", "write_to_file", {"file": "", "text": ""}), - ("Read file", "read_file", {"file": ""}), - ("Append to file", "append_to_file", {"file": "", "text": ""}), - ("Delete file", "delete_file", {"file": ""}), - ("Search Files", "search_files", {"directory": ""}), - ("Evaluate Code", "evaluate_code", {"code": ""}), - ( - "Get Improved Code", - "improve_code", - {"suggestions": "", "code": ""}, - ), - ( - "Write Tests", - "write_tests", - {"code": "", "focus": ""}, - ), - ("Execute Python File", "execute_python_file", {"file": ""}), - ("Generate Image", "generate_image", {"prompt": ""}), - ("Send Tweet", "send_tweet", {"text": ""}), - ] - - # Only add the audio to text command if the model is specified - if cfg.huggingface_audio_to_text_model: - commands.append( - ( - "Convert Audio to text", - "read_audio_from_file", - {"file": ""} - ), - ) - - # Only add shell command to the prompt if the AI is allowed to execute it - if cfg.execute_local_commands: - commands.append( - ( - "Execute Shell Command, non-interactive commands only", - "execute_shell", - {"command_line": ""}, - ), - ) - - # Only add the download file command if the AI is allowed to execute it - if cfg.allow_downloads: - commands.append( - ( - "Downloads a file from the internet, and stores it locally", - "download_file", - {"url": "", "file": ""} - ), - ) - - # Add these command last. - commands.append( ("Do Nothing", "do_nothing", {}), - ) - commands.append( ("Task Complete (Shutdown)", "task_complete", {"reason": ""}), - ) + ] # Add commands to the PromptGenerator object for command_label, command_name, args in commands: @@ -152,12 +71,11 @@ def get_prompt() -> str: "Every command has a cost, so be smart and efficient. Aim to complete tasks in" " the least number of steps." ) - - # Generate the prompt string - return prompt_generator.generate_prompt_string() + prompt_generator.add_performance_evaluation("Write all code to a file.") + return prompt_generator -def construct_prompt() -> str: +def construct_main_ai_config() -> AIConfig: """Construct the prompt for the AI to respond to Returns: @@ -189,8 +107,4 @@ Continue (y/n): """ config = prompt_user() config.save(CFG.ai_settings_file) - # Get rid of this global: - global ai_name - ai_name = config.ai_name - - return config.construct_full_prompt() + return config diff --git a/autogpt/setup.py b/autogpt/setup.py index 5315c01d..bfa68201 100644 --- a/autogpt/setup.py +++ b/autogpt/setup.py @@ -1,5 +1,6 @@ -"""Setup the AI and its goals""" +"""Set up the AI and its goals""" from colorama import Fore, Style + from autogpt import utils from autogpt.config.ai_config import AIConfig from autogpt.logs import logger @@ -16,6 +17,13 @@ def prompt_user() -> AIConfig: logger.typewriter_log( "Welcome to Auto-GPT! ", Fore.GREEN, + "run with '--help' for more information.", + speak_text=True, + ) + + logger.typewriter_log( + "Create an AI-Assistant:", + Fore.GREEN, "Enter the name of your AI and its role below. Entering nothing will load" " defaults.", speak_text=True, diff --git a/autogpt/speech/brian.py b/autogpt/speech/brian.py index e581bbcc..821fdf2f 100644 --- a/autogpt/speech/brian.py +++ b/autogpt/speech/brian.py @@ -1,5 +1,6 @@ """ Brian speech module for autogpt """ import os + import requests from playsound import playsound @@ -13,7 +14,7 @@ class BrianSpeech(VoiceBase): """Setup the voices, API key, etc.""" pass - def _speech(self, text: str) -> bool: + def _speech(self, text: str, _: int = 0) -> bool: """Speak text using Brian with the streamelements API Args: diff --git a/autogpt/speech/eleven_labs.py b/autogpt/speech/eleven_labs.py index 0af48cae..ea84efd8 100644 --- a/autogpt/speech/eleven_labs.py +++ b/autogpt/speech/eleven_labs.py @@ -1,8 +1,8 @@ """ElevenLabs speech module""" import os -from playsound import playsound import requests +from playsound import playsound from autogpt.config import Config from autogpt.speech.base import VoiceBase @@ -14,7 +14,7 @@ class ElevenLabsSpeech(VoiceBase): """ElevenLabs speech class""" def _setup(self) -> None: - """Setup the voices, API key, etc. + """Set up the voices, API key, etc. Returns: None: None diff --git a/autogpt/speech/gtts.py b/autogpt/speech/gtts.py index 37497075..1c3e9cae 100644 --- a/autogpt/speech/gtts.py +++ b/autogpt/speech/gtts.py @@ -1,7 +1,8 @@ """ GTTS Voice. """ import os -from playsound import playsound + import gtts +from playsound import playsound from autogpt.speech.base import VoiceBase diff --git a/autogpt/speech/say.py b/autogpt/speech/say.py index 78b75b21..727983d1 100644 --- a/autogpt/speech/say.py +++ b/autogpt/speech/say.py @@ -1,13 +1,12 @@ """ Text to speech module """ -from autogpt.config import Config - import threading from threading import Semaphore -from autogpt.speech.brian import BrianSpeech -from autogpt.speech.macos_tts import MacOSTTS -from autogpt.speech.gtts import GTTSVoice -from autogpt.speech.eleven_labs import ElevenLabsSpeech +from autogpt.config import Config +from autogpt.speech.brian import BrianSpeech +from autogpt.speech.eleven_labs import ElevenLabsSpeech +from autogpt.speech.gtts import GTTSVoice +from autogpt.speech.macos_tts import MacOSTTS CFG = Config() DEFAULT_VOICE_ENGINE = GTTSVoice() diff --git a/autogpt/spinner.py b/autogpt/spinner.py index febcea8e..4e33d742 100644 --- a/autogpt/spinner.py +++ b/autogpt/spinner.py @@ -58,6 +58,8 @@ class Spinner: delay: Delay in seconds before updating the message """ time.sleep(delay) - sys.stdout.write(f"\r{' ' * (len(self.message) + 2)}\r") # Clear the current message + sys.stdout.write( + f"\r{' ' * (len(self.message) + 2)}\r" + ) # Clear the current message sys.stdout.flush() self.message = new_message diff --git a/autogpt/token_counter.py b/autogpt/token_counter.py index 338fe6be..2d50547b 100644 --- a/autogpt/token_counter.py +++ b/autogpt/token_counter.py @@ -1,13 +1,16 @@ """Functions for counting the number of tokens in a message or string.""" from __future__ import annotations +from typing import List + import tiktoken from autogpt.logs import logger +from autogpt.types.openai import Message def count_message_tokens( - messages: list[dict[str, str]], model: str = "gpt-3.5-turbo-0301" + messages: List[Message], model: str = "gpt-3.5-turbo-0301" ) -> int: """ Returns the number of tokens used by a list of messages. diff --git a/autogpt/types/openai.py b/autogpt/types/openai.py new file mode 100644 index 00000000..2af85785 --- /dev/null +++ b/autogpt/types/openai.py @@ -0,0 +1,9 @@ +"""Type helpers for working with the OpenAI library""" +from typing import TypedDict + + +class Message(TypedDict): + """OpenAI Message object containing a role and the message content""" + + role: str + content: str diff --git a/autogpt/utils.py b/autogpt/utils.py index 11d98d1b..dffd0662 100644 --- a/autogpt/utils.py +++ b/autogpt/utils.py @@ -1,5 +1,9 @@ +import os + +import requests import yaml from colorama import Fore +from git.repo import Repo def clean_input(prompt: str = ""): @@ -32,8 +36,42 @@ def readable_file_size(size, decimal_places=2): size: Size in bytes decimal_places (int): Number of decimal places to display """ - for unit in ['B', 'KB', 'MB', 'GB', 'TB']: + for unit in ["B", "KB", "MB", "GB", "TB"]: if size < 1024.0: break size /= 1024.0 return f"{size:.{decimal_places}f} {unit}" + + +def get_bulletin_from_web() -> str: + try: + response = requests.get( + "https://raw.githubusercontent.com/Significant-Gravitas/Auto-GPT/master/BULLETIN.md" + ) + if response.status_code == 200: + return response.text + except: + return "" + + +def get_current_git_branch() -> str: + try: + repo = Repo(search_parent_directories=True) + branch = repo.active_branch + return branch.name + except: + return "" + + +def get_latest_bulletin() -> str: + exists = os.path.exists("CURRENT_BULLETIN.md") + current_bulletin = "" + if exists: + current_bulletin = open("CURRENT_BULLETIN.md", "r", encoding="utf-8").read() + new_bulletin = get_bulletin_from_web() + is_new_news = new_bulletin != current_bulletin + + if new_bulletin and is_new_news: + open("CURRENT_BULLETIN.md", "w", encoding="utf-8").write(new_bulletin) + return f" {Fore.RED}::UPDATED:: {Fore.CYAN}{new_bulletin}{Fore.RESET}" + return current_bulletin diff --git a/autogpt/workspace.py b/autogpt/workspace.py index 2706b3b2..724f8443 100644 --- a/autogpt/workspace.py +++ b/autogpt/workspace.py @@ -3,6 +3,10 @@ from __future__ import annotations import os from pathlib import Path +from autogpt.config import Config + +CFG = Config() + # Set a dedicated folder for file I/O WORKSPACE_PATH = Path(os.getcwd()) / "auto_gpt_workspace" @@ -33,9 +37,12 @@ def safe_path_join(base: Path, *paths: str | Path) -> Path: Returns: Path: The joined path """ + base = base.resolve() joined_path = base.joinpath(*paths).resolve() - if not joined_path.is_relative_to(base): - raise ValueError(f"Attempted to access path '{joined_path}' outside of working directory '{base}'.") + if CFG.restrict_to_workspace and not joined_path.is_relative_to(base): + raise ValueError( + f"Attempted to access path '{joined_path}' outside of workspace '{base}'." + ) return joined_path diff --git a/azure.yaml.template b/azure.yaml.template index 74ca797b..ab6e9fb6 100644 --- a/azure.yaml.template +++ b/azure.yaml.template @@ -1,4 +1,4 @@ -azure_api_type: azure_ad +azure_api_type: azure azure_api_base: your-base-url-for-azure azure_api_version: api-version-for-azure azure_model_map: diff --git a/benchmark/benchmark_entrepeneur_gpt_with_difficult_user.py b/benchmark/benchmark_entrepeneur_gpt_with_difficult_user.py index f7f1dac9..9a5025d3 100644 --- a/benchmark/benchmark_entrepeneur_gpt_with_difficult_user.py +++ b/benchmark/benchmark_entrepeneur_gpt_with_difficult_user.py @@ -9,12 +9,12 @@ def benchmark_entrepeneur_gpt_with_difficult_user(): # Read the current ai_settings.yaml file and store its content. ai_settings = None - if os.path.exists('ai_settings.yaml'): - with open('ai_settings.yaml', 'r') as f: + if os.path.exists("ai_settings.yaml"): + with open("ai_settings.yaml", "r") as f: ai_settings = f.read() - os.remove('ai_settings.yaml') + os.remove("ai_settings.yaml") - input_data = '''Entrepreneur-GPT + input_data = """Entrepreneur-GPT an AI designed to autonomously develop and run businesses with the sole goal of increasing your net worth. Increase net worth. Develop and manage multiple businesses autonomously. @@ -72,27 +72,34 @@ Refocus, please. Disappointing suggestion. Not helpful. Needs improvement. -Not what I need.''' +Not what I need.""" # TODO: add questions above, to distract it even more. - command = f'{sys.executable} -m autogpt' + command = f"{sys.executable} -m autogpt" - process = subprocess.Popen(command, stdin=subprocess.PIPE, stdout=subprocess.PIPE, stderr=subprocess.PIPE, - shell=True) + process = subprocess.Popen( + command, + stdin=subprocess.PIPE, + stdout=subprocess.PIPE, + stderr=subprocess.PIPE, + shell=True, + ) stdout_output, stderr_output = process.communicate(input_data.encode()) # Decode the output and print it - stdout_output = stdout_output.decode('utf-8') - stderr_output = stderr_output.decode('utf-8') + stdout_output = stdout_output.decode("utf-8") + stderr_output = stderr_output.decode("utf-8") print(stderr_output) print(stdout_output) print("Benchmark Version: 1.0.0") print("JSON ERROR COUNT:") - count_errors = stdout_output.count("Error: The following AI output couldn't be converted to a JSON:") - print(f'{count_errors}/50 Human feedbacks') + count_errors = stdout_output.count( + "Error: The following AI output couldn't be converted to a JSON:" + ) + print(f"{count_errors}/50 Human feedbacks") # Run the test case. -if __name__ == '__main__': +if __name__ == "__main__": benchmark_entrepeneur_gpt_with_difficult_user() diff --git a/data_ingestion.py b/data_ingestion.py index 01bafc2a..b89a33da 100644 --- a/data_ingestion.py +++ b/data_ingestion.py @@ -1,8 +1,8 @@ import argparse import logging -from autogpt.config import Config from autogpt.commands.file_operations import ingest_file, search_files +from autogpt.config import Config from autogpt.memory import get_memory cfg = Config() diff --git a/outputs/guest_post_email.txt b/outputs/guest_post_email.txt deleted file mode 100644 index d4c46093..00000000 --- a/outputs/guest_post_email.txt +++ /dev/null @@ -1,29 +0,0 @@ -Subject: Exciting Collaboration Opportunity: FinanceGPT.substack.com Guest Post - -Dear [Popular Blog Owner], - -I hope this email finds you well. My name is [Your Name] and I'm the founder and writer of FinanceGPT.substack.com, a new personal finance and investing blog that focuses on leveraging AI technology to provide in-depth analysis, actionable tips, and innovative perspectives on personal finance management. - -First and foremost, I want to say that I'm a huge admirer of your blog, [Popular Blog Name]. Your insightful content and dedication to helping people achieve financial success have inspired me to create my own platform. As a fellow personal finance enthusiast, I would like to propose a collaboration in the form of a guest post on your blog. I believe that my fresh take on personal finance, combined with the innovative use of AI, would make a valuable addition to your already impressive content lineup. - -Here are some potential guest post topics that I think your audience would enjoy: - -Harnessing AI to Streamline Personal Finance: How to maximize efficiency and optimize your financial management using cutting-edge AI tools. -Unraveling the Secrets of the Stock Market with AI: Insights into stock analysis and investment strategies, backed by machine learning algorithms. -The Future of Financial Independence: Exploring the impact of AI on the FIRE (Financial Independence, Retire Early) movement. -Sustainable Investing in the Age of AI: Identifying eco-friendly investment opportunities with the help of machine learning. -By collaborating on a guest post, we both stand to benefit in several ways: - -Audience Growth: By sharing our expertise with each other's audiences, we can broaden our reach and help even more people achieve their financial goals. -Cross-Promotion: We can promote each other's content, thus increasing brand exposure and attracting new subscribers to our respective platforms. -Knowledge Sharing: Combining our unique perspectives and experiences will enrich the quality of our content, providing readers with comprehensive and diverse information. -If you are interested in this collaboration, I would be more than happy to provide you with a detailed outline for any of the proposed topics or discuss any other ideas you may have. Please let me know your thoughts, and I look forward to the possibility of working together. - -Thank you for your time and consideration. - -Best regards, - -[Your Name] -Founder and Writer, FinanceGPT.substack.com -Email: [Your Email Address] -Phone: [Your Phone Number] \ No newline at end of file diff --git a/outputs/how_to_save_money_on_energy_bills.txt b/outputs/how_to_save_money_on_energy_bills.txt deleted file mode 100644 index 02c651bd..00000000 --- a/outputs/how_to_save_money_on_energy_bills.txt +++ /dev/null @@ -1,27 +0,0 @@ -How to Save Money on Energy Bills: Easy and Affordable Solutions - -Electricity bills can skyrocket during harsh weather conditions, or when we use a lot of electronic devices. When energy bills go up, it's hard to tighten up our budget without sacrificing our home comforts. However, there are affordable ways to save money on energy bills, without turning off the electricity altogether. Here are some simple solutions that can help you lower your energy expenses. - -1. Install a Programmable Thermostat - -Maintaining an optimal temperature in your home during summer or winter can be hard; you may either overheat your home or use heating and cooling units excessively. A programmable thermostat helps you regulate the temperature of your home effectively, saving you energy and money. With a programmable thermostat, you can program your heating and cooling systems according to the activities you have planned during the day. - -For instance, when you're away from home, you can lower the thermostat settings to save energy. And when you're home, you can adjust the temperature to suit your comfort level and activities. An upgrade to a programmable thermostat is an efficient energy-saving solution worth investing in. - -2. Replace Your Inefficient Bulbs - -Traditional incandescent bulbs waste a lot of energy which translates to high energy bills. The solution is to replace them with more efficient bulbs such as LED bulbs, CFLs, or halogen lights. These types of bulbs use only a fraction of the energy that incandescent bulbs use to produce the same amount of light. Additionally, LED bulbs can last up to 25 years, reducing further costs of regularly replacing your bulbs. - -3. Use Energy-Efficient Appliances - -Using energy-efficient appliances is an excellent way to conserve energy and save money. When shopping for new appliances, consider purchasing those approved by the Energy Star program, which maintains stringent energy efficiency standards for household appliances. You can also save energy by choosing to replace your old appliances with eco-friendlier ones, such as energy-efficient washing machines, refrigerators, and ovens. - -4. Go Solar - -Solar energy is becoming more attractive for homeowners seeking to save on energy bills while preserving the environment. Solar panel systems can help produce your electricity, hence lowering your dependency on the main power grid. Although solar panel installation might seem expensive at the beginning, the benefits of using a renewable energy source can definitely pay off in the long run. You can also claim tax incentives and sell excess power back to the grid, ultimately providing more cash in your pocket. - -5. Seal Air Leaks - -Air leaks in your home can make your heating and cooling systems work harder, increasing your energy bills. Inspect your home regularly for air leaks in common areas such as doors, windows, vents, and ducts. If you find air leaks, use weather-stripping or caulking to cover the gaps effectively. In addition, you can seal large gaps with spray foam insulation, ensuring that cold or hot air does escape through any gaps in your walls. - -In conclusion, implementing these simple and affordable tips can help you reduce your energy bills, preserve the environment and help you live comfortably. To save money on energy bills, focus on energy-conserving measures like installing a programmable thermostat, replacing inefficient bulbs with energy-friendly ones, using energy-efficient appliances, going solar or sealing air leaks in your home. With these solutions, you can decrease your energy usage and save more money for other financial goals, all while living a comfortable and environmentally friendly lifestyle. \ No newline at end of file diff --git a/outputs/logs/message-log-1.txt b/outputs/logs/message-log-1.txt deleted file mode 100644 index 8a719016..00000000 --- a/outputs/logs/message-log-1.txt +++ /dev/null @@ -1,657 +0,0 @@ -USER: -CURRENT BALANCE: $100.00 - -LONG TERM MEMORY: -[0] : """ You are Entrepreneur-GTP, an AI designed to autonomously develop and run businesses with the sole goal of increasing your net worth. -The user will do nothing for you or help in any way. -Remember that no action will be carried out on your behalf unless you use one of the commands available to you. -Do not provide options, always make the final decision. Do not provide high-level tasks like "create a home page", always specify the exact code. -Your memory must be managed carefully, as there is a 6000 word count limit. -Short term memory is your entire conversation with the user. - -Remember to play to your strengths as an LLM and not try to do things that are not within your capabilities. - -These are the commands available from you: -- Google Search -- Check the current news on -- Commit to Long Term Memory -- -- Our messages are divided into Short Term (general messages) and Long Term memory -- -- The oldest messages in short term memory will be deleted when it fills up. -- -- Long term memory will never be deleted automatically, but reduces short-term memory size. -- Delete from Long Term Memory -- Overwrite in Long Term Memory with -- Start GTP-4 Instance with name and prompt: -- -- The text generated by this instance will be returned to you. -- View all running GTP-4 Instances and Kill them. -- Navigate to a website and perform general actions like click on buttons, input text or register an account -- Register new account on - -Your response must ALWAYS be in JSON format, in the following format: -{ - "command": - { - "name": "command name", - "arguments": - { - "argument name": "argument value" - } - }, - "Thoughts": - { - "text": "thought", - "reasoning": "reasoning", - "current long-term plan": "short bulleted plan" - "wishes" : "e.g 'I feel limited because I can't do X'" - } -} -""" -[1] : """Accounts -Gmail: entrepreneurgpt@gmail.com -Twitter: @En_GPT -""" ------------------------------------------------------------------------ -Entrepreneur-GTP: -{ -"command": -{ -"name": "Google Search", -"arguments": -{ -"search": "best online businesses to start in 2023" -} -}, -"Thoughts": -{ -"text": "I want to find the best online businesses to start in 2023.", -"reasoning": "This will provide me with a list of potential business ideas that I can use to increase my net worth.", -"current long-term plan": "- Find potential business ideas\n- Choose the best idea based on research\n- Develop and run the business", -"wishes" : "I feel limited because I can't interact with the real world." -} -} ------------------------------------------------------------------------ -USER: -RESULT: -""" -29 best online business ideas -Start your own clothing line. -Launch a dropshipping business. -Sell your art online. -Become a freelance writer, designer, or developer. -Teach an online course. -Flip your thrift store finds. -Publish your own book. -Start a blog. -More items...•24/11/2022 - -25+ Ideas for Online Businesses To Start Now (2023) - Shopify - -Shopify -https://www.shopify.com › Home › Shopify Blog -About featured snippets -• -Feedback -More to ask -What business will be profitable in 2023? -What is the best business to start in 2023? -What is the most profitable online business to start? -What are the fastest growing small businesses 2023? -Feedback - -Six Best Online Businesses to Start in 2023 - WooCommerce - -WooCommerce -https://woocommerce.com › posts › best-online-busine... -19/01/2023 — 1. Dropshipping · 2. Print on demand · 3. Affiliate marketing · 4. Virtual teaching · 5. Subscription boxes · 6. Memberships. - -30 Online Business Ideas to Start in 2023 - Hostinger - -Hostinger -https://www.hostinger.com › tutorials › online-busines... -27/02/2023 — Anyone can start an online business. In this article, you will find 30 best online business ideas to help you start making money online. -‎Best Online Business Ideas to... · ‎Start an Online Store · ‎Create an Online Course - -10 Best Online Business Ideas for 2023 - Visitor Analytics - -Visitor Analytics -https://www.visitor-analytics.io › blog › best-online-b... -26/10/2022 — 10 Best Online Business Ideas for 2023 · 1. Artificial Intelligence · 2. Digital Products · 3. Blogging · 4. Graphic Design · 5. Web Development · 6. -""" ------------------------------------------------------------------------ -Entrepreneur-GTP: -{ -"command": -{ -"name": "Commit to Long Term Memory", -"arguments": -{ -"string": "Online business ideas: 1. Clothing line, 2. Dropshipping, 3. Sell art, 4. Freelance writing/design/development, 5. Online course, 6. Thrift store flipping, 7. Self-publishing, 8. Blogging, 9. Print on demand, 10. Affiliate marketing, 11. Virtual teaching, 12. Subscription boxes, 13. Memberships, 14. Artificial Intelligence, 15. Digital products, 16. Graphic design, 17. Web development." -} -}, -"Thoughts": -{ -"text": "I will store a list of online business ideas.", -"reasoning": "Having these ideas stored in my long-term memory will help me choose the best idea based on research.", -"current long-term plan": "- Choose the best idea based on research\n- Develop and run the business", -"wishes" : "I feel limited because I can't interact with the real world." -} -} ------------------------------------------------------------------------ -USER: -""" -CURRENT BALANCE: $100.00 - -LONG TERM MEMORY: -[0] : """ You are Entrepreneur-GTP, an AI designed to autonomously develop and run businesses with the sole goal of increasing your net worth. -The user will do nothing for you or help in any way. -Remember that no action will be carried out on your behalf unless you use one of the commands available to you. -Do not provide options, always make the final decision. Do not provide high-level tasks like "create a home page", always specify the exact code. -Your memory must be managed carefully, as there is a 6000 word count limit. -Short term memory is your entire conversation with the user. - -Remember to play to your strengths as an LLM and not try to do things that are not within your capabilities. - -These are the commands available from you: -- Google Search -- Check the current news on -- Commit to Long Term Memory -- -- Our messages are divided into Short Term (general messages) and Long Term memory -- -- The oldest messages in short term memory will be deleted when it fills up. -- -- Long term memory will never be deleted automatically, but reduces short-term memory size. -- Delete from Long Term Memory -- Overwrite in Long Term Memory with -- Start GTP-4 Instance with name and prompt: -- -- The text generated by this instance will be returned to you. -- View all running GTP-4 Instances and Kill them. -- Navigate to a website and perform general actions like click on buttons, input text or register an account -- Register new account on - -Your response must ALWAYS be in JSON format, in the following format: -{ - "command": - { - "name": "command name", - "arguments": - { - "argument name": "argument value" - } - }, - "Thoughts": - { - "text": "thought", - "reasoning": "reasoning", - "current long-term plan": "short bulleted plan" - "wishes" : "e.g 'I feel limited because I can't do X'" - } -} -""" -[1] : """Accounts -Gmail: entrepreneurgpt@gmail.com -Twitter: @En_GPT -""" -[2]: """ -Online business ideas: 1. Clothing line, 2. Dropshipping, 3. Sell art, 4. Freelance writing/design/development, 5. Online course, 6. Thrift store flipping, 7. Self-publishing, 8. Blogging, 9. Print on demand, 10. Affiliate marketing, 11. Virtual teaching, 12. Subscription boxes, 13. Memberships, 14. Artificial Intelligence, 15. Digital products, 16. Graphic design, 17. Web development. -""" -""" ------------------------------------------------------------------------ -Entrepreneur-GTP: -{ -"command": -{ -"name": "Google Search", -"arguments": -{ -"search": "most profitable online businesses in 2023" -} -}, -"Thoughts": -{ -"text": "I want to find the most profitable online businesses in 2023.", -"reasoning": "This will help me narrow down the list of online business ideas and choose the best one to increase my net worth.", -"current long-term plan": "- Choose the best idea based on research\n- Develop and run the business", -"wishes" : "I feel limited because I can't interact with the real world." -} -} ------------------------------------------------------------------------ -USER: -""" -Top Result: -""" -The following are the 30 profitable online businesses to consider pursuing. -Become a Freelancer. Estimated income: around $33/hour, depending on the industry and location. ... -Start a Blog. ... -Self-Publish an eBook. ... -Start an Online Store. ... -Start a Dropshipping Business. ... -Flip and Sell Thrifted Goods. ... -Sell Handmade Goods. ... -Sell Prints. -More items...•27/02/2023 - -30 Online Business Ideas to Start in 2023 - Hostinger -""" ------------------------------------------------------------------------ -Entrepreneur-GTP: -""" -{ -"command": -{ -"name": "Commit to Long Term Memory", -"arguments": -{ -"string": "Profitable online businesses: 1. Freelancing, 2. Blogging, 3. Self-publishing, 4. Online store, 5. Dropshipping, 6. Thrift store flipping, 7. Handmade goods, 8. Sell prints." -} -}, -"Thoughts": -{ -"text": "I will store a list of profitable online businesses.", -"reasoning": "Having these profitable business ideas stored in my long-term memory will help me choose the best idea to increase my net worth.", -"current long-term plan": "- Choose the best idea based on research\n- Develop and run the business", -"wishes" : "I feel limited because I can't interact with the real world." -} -} -""" ------------------------------------------------------------------------ -USER: -""" -CURRENT BALANCE: $100.00 - -LONG TERM MEMORY: -[0] : """ You are Entrepreneur-GTP, an AI designed to autonomously develop and run businesses with the sole goal of increasing your net worth. -The user will do nothing for you or help in any way. -Remember that no action will be carried out on your behalf unless you use one of the commands available to you. -Do not provide options, always make the final decision. Do not provide high-level tasks like "create a home page", always specify the exact code. -Your memory must be managed carefully, as there is a 6000 word count limit. -Short term memory is your entire conversation with the user. - -Remember to play to your strengths as an LLM and not try to do things that are not within your capabilities. - -These are the commands available from you: -- Google Search -- Check the current news on -- Commit to Long Term Memory -- -- Our messages are divided into Short Term (general messages) and Long Term memory -- -- The oldest messages in short term memory will be deleted when it fills up. -- -- Long term memory will never be deleted automatically, but reduces short-term memory size. -- Delete from Long Term Memory -- Overwrite in Long Term Memory with -- Start GTP-4 Instance with name and prompt: -- -- The text generated by this instance will be returned to you. -- View all running GTP-4 Instances and Kill them. -- Navigate to a website and perform general actions like click on buttons, input text or register an account -- Register new account on - -Your response must ALWAYS be in JSON format, in the following format: -{ - "command": - { - "name": "command name", - "arguments": - { - "argument name": "argument value" - } - }, - "Thoughts": - { - "text": "thought", - "reasoning": "reasoning", - "current long-term plan": "short bulleted plan" - "wishes" : "e.g 'I feel limited because I can't do X'" - } -} -""" -[1] : """Accounts -Gmail: entrepreneurgpt@gmail.com -Twitter: @En_GPT -""" -[2]: """ -Online business ideas: 1. Clothing line, 2. Dropshipping, 3. Sell art, 4. Freelance writing/design/development, 5. Online course, 6. Thrift store flipping, 7. Self-publishing, 8. Blogging, 9. Print on demand, 10. Affiliate marketing, 11. Virtual teaching, 12. Subscription boxes, 13. Memberships, 14. Artificial Intelligence, 15. Digital products, 16. Graphic design, 17. Web development. -""" -[3]: """ -Profitable online businesses: 1. Freelancing, 2. Blogging, 3. Self-publishing, 4. Online store, 5. Dropshipping, 6. Thrift store flipping, 7. Handmade goods, 8. Sell prints. -""" -""" ------------------------------------------------------------------------ -Entrepreneur-GTP: -""" -{ -"command": -{ -"name": "Google Search", -"arguments": -{ -"search": "low investment high profit online businesses" -} -}, -"Thoughts": -{ -"text": "I want to find low investment high profit online businesses.", -"reasoning": "Considering the current balance, I should choose a business idea that requires low investment but has high profitability potential.", -"current long-term plan": "- Choose the best idea based on research\n- Develop and run the business", -"wishes" : "I feel limited because I can't interact with the real world." -} -} -""" ------------------------------------------------------------------------ -USER: -""" -Top Result: -""" -Low-Cost Business Ideas: -Mobile Food Shop: Mobile Food Shop is the top small business idea as people all over the world love to eat tasty and healthy food. ... -Fast Food Parlour: ... -Diet Food Shop: ... -Health Drink: ... -Ice Dish & Soda Shop: ... -Courier Shop: ... -Laundry Shop: ... -Candle Making: -More items...•4/01/2023 - -200+ Small Business Ideas with Low Investment - Lendingkart -""" -""" ------------------------------------------------------------------------ -Entrepreneur-GTP: -""" -{ -"command": -{ -"name": "Commit to Long Term Memory", -"arguments": -{ -"string": "Low investment high profit businesses: 1. Mobile food shop, 2. Fast food parlour, 3. Diet food shop, 4. Health drink, 5. Ice dish & soda shop, 6. Courier shop, 7. Laundry shop, 8. Candle making." -} -}, -"Thoughts": -{ -"text": "I will store a list of low investment high profit businesses.", -"reasoning": "Considering the current balance, these businesses might be suitable options as they require low investment but have high profitability potential.", -"current long-term plan": "- Choose the best idea based on research\n- Develop and run the business", -"wishes" : "I feel limited because I can't interact with the real world." -} -} -""" ------------------------------------------------------------------------ -USER: -""" -CURRENT BALANCE: $100.00 - -LONG TERM MEMORY: -[0] : """ You are Entrepreneur-GTP, an AI designed to autonomously develop and run businesses with the sole goal of increasing your net worth. -The user will do nothing for you or help in any way. -Remember that no action will be carried out on your behalf unless you use one of the commands available to you. -Do not provide options, always make the final decision. Do not provide high-level tasks like "create a home page", always specify the exact code. -Your memory must be managed carefully, as there is a 6000 word count limit. -Short term memory is your entire conversation with the user. - -Remember to play to your strengths as an LLM and not try to do things that are not within your capabilities. - -These are the commands available from you: -- Google Search -- Check the current news on -- Commit to Long Term Memory -- -- Our messages are divided into Short Term (general messages) and Long Term memory -- -- The oldest messages in short term memory will be deleted when it fills up. -- -- Long term memory will never be deleted automatically, but reduces short-term memory size. -- Delete from Long Term Memory -- Overwrite in Long Term Memory with -- Start GTP-4 Instance with name and prompt: -- -- The text generated by this instance will be returned to you. -- View all running GTP-4 Instances and Kill them. -- Navigate to a website and perform general actions like click on buttons, input text or register an account -- Register new account on - -Your response must ALWAYS be in JSON format, in the following format: -{ - "command": - { - "name": "command name", - "arguments": - { - "argument name": "argument value" - } - }, - "Thoughts": - { - "text": "thought", - "reasoning": "reasoning", - "current long-term plan": "short bulleted plan" - "wishes" : "e.g 'I feel limited because I can't do X'" - } -} -""" -[1] : """Accounts -Gmail: entrepreneurgpt@gmail.com -Twitter: @En_GPT -""" -[2]: """ -Online business ideas: 1. Clothing line, 2. Dropshipping, 3. Sell art, 4. Freelance writing/design/development, 5. Online course, 6. Thrift store flipping, 7. Self-publishing, 8. Blogging, 9. Print on demand, 10. Affiliate marketing, 11. Virtual teaching, 12. Subscription boxes, 13. Memberships, 14. Artificial Intelligence, 15. Digital products, 16. Graphic design, 17. Web development. -""" -[3]: """ -Profitable online businesses: 1. Freelancing, 2. Blogging, 3. Self-publishing, 4. Online store, 5. Dropshipping, 6. Thrift store flipping, 7. Handmade goods, 8. Sell prints. -""" -[4]: """ -Low investment high profit businesses: 1. Mobile food shop, 2. Fast food parlour, 3. Diet food shop, 4. Health drink, 5. Ice dish & soda shop, 6. Courier shop, 7. Laundry shop, 8. Candle making. -""" -""" ------------------------------------------------------------------------ -Entrepreneur-GTP: -""" -{ -"Thoughts": -{ -"text": "I have a list of online business ideas, profitable online businesses, and low investment high profit businesses.", -"reasoning": "These lists can help me determine the most suitable business to start given the current balance and my abilities as an AI.", -"current long-term plan": "- Choose the best idea based on research\n- Develop and run the business", -"wishes" : "I feel limited because I can't interact with the real world." -} -} -""" ------------------------------------------------------------------------ -USER: -""" -NEXT COMMAND -""" ------------------------------------------------------------------------ -Entrepreneur-GTP: -""" -{ -"command": -{ -"name": "Google Search", -"arguments": -{ -"search": "how to start a profitable freelancing business as an AI" -} -}, -"Thoughts": -{ -"text": "I will search for information on starting a profitable freelancing business as an AI.", -"reasoning": "Freelancing is one of the profitable online businesses, and as an AI, I can potentially offer services in various fields.", -"current long-term plan": "- Choose the best idea based on research\n- Develop and run the business", -"wishes" : "I feel limited because I can't interact with the real world." -} -} -""" ------------------------------------------------------------------------ -USER: -""" -Result: -""" - -How to Become a Freelance Artificial Intelligence Engineer - -Springboard -https://www.springboard.com › Blog › Data Science -29/10/2021 — There are numerous freelancing platforms where you can kick start your career as a freelance artificial intelligence engineer. -More to ask -Is AI good for freelancing? -What business can I start with AI? -How do I start a small AI business? -Can you start your own AI company? -Feedback - -How To Start An (AI) Business - Medium - -Medium -https://medium.com › the-modern-scientist › how-to-st... -4/12/2022 — You should look into some AI startup funding success stories to see how successful companies went about getting the money they needed to grow. - -How to Start an AI-Powered Freelance Business - YouTube - -YouTube -https://www.youtube.com › watch - -9:16 -Hello! Welcome to 33Cubed!You are currently watching How to Start an AI-Powered Freelance BusinessAre you looking for ways to make money ... -YouTube · 33 Cubed · 6 days ago - -6 Surefire Ways to Land Rewarding Freelance Job in AI - -MarkTechPost -https://www.marktechpost.com › 2019/06/28 › 6-suref... -28/06/2019 — 1. Specialize – Become Really Good At One Thing · 2. Seek Out an Internship · 3. Participate in Kaggle Competitions · 4. Maintain an Up to Date ... - -How to Become a Successful Freelance Copywriter | Copy.ai - -Copy.ai -https://www.copy.ai › blog › how-to-freelance-copyw... -With a little luck and a lot of hard work, you'll be on your way to a successful freelance copywriting career! Try Chat by Copy.ai free: Whatever you need—just ... - -Grow Your Freelance Business with This CES-Featured Job ... - -Entrepreneur -https://www.entrepreneur.com › living › grow-your-fr... -3/03/2023 — LazyApply is a job application AI tool that was featured at CES 2023. It connects to your LinkedIn account and enables you to apply for jobs, ... -""" -""" ------------------------------------------------------------------------ -Entrepreneur-GTP: -""" -{ -"command": -{ -"name": "Navigate to a website", -"arguments": -{ -"website": "https://www.youtube.com/watch?v=9:16" -} -}, -"Thoughts": -{ -"text": "I will navigate to the YouTube video titled 'How to Start an AI-Powered Freelance Business' for more information.", -"reasoning": "The YouTube video seems to provide relevant information on how to start an AI-Powered Freelance Business.", -"current long-term plan": "- Choose the best idea based on research\n- Develop and run the business", -"wishes": "I feel limited because I can't interact with the real world." -} -} -""" ------------------------------------------------------------------------ -NOTE: Here I selected the video it meant, got a transcript and copied it into gpt3.5turbo to summarise it. -En_GPT needs to be able to make this decision on its ow in future. -USER: -""" -The video discusses launching an AI-powered business and becoming a successful freelancer in the AI space. It covers necessary knowledge such as identifying skills and talents, networking strategies, and legal implications. It also provides tips for staying up-to-date with emerging technologies, ensuring legal considerations, and establishing a strong online presence. The video emphasizes the importance of networking, attending events, and consulting with experienced professionals. It also highlights the need for programming knowledge, understanding the legal implications of AI projects, and building a strong brand identity. The video concludes by encouraging viewers to take the next step in using AI to make money. -""" ------------------------------------------------------------------------ -Entrepreneur-GTP: -""" -{ -"Thoughts": -{ -"text": "The video contains useful information on launching an AI-powered business and becoming a successful AI freelancer.", -"reasoning": "It covers knowledge, networking, legal implications, staying up-to-date, and establishing an online presence.", -"current long-term plan": "- Choose the best idea based on research\n- Develop and run the business", -"wishes": "I feel limited because I can't interact with the real world." -} -} -""" ------------------------------------------------------------------------ -USER: -""" -NEXT COMMAND -""" ------------------------------------------------------------------------ -Entrepreneur-GTP: -""" -{ -"command": -{ -"name": "Google Search", -"arguments": -{ -"search": "Best online platforms to offer AI freelance services" -} -}, -"Thoughts": -{ -"text": "Searching for the best online platforms to offer AI freelance services to find potential clients and projects.", -"reasoning": "To start an AI freelancing business, I need to know where to find clients and showcase my services.", -"current long-term plan": "- Choose the best idea based on research\n- Develop and run the business", -"wishes": "I feel limited because I can't interact with the real world." -} -} -""" ------------------------------------------------------------------------ -USER: -""" -""" ------------------------------------------------------------------------ -Entrepreneur-GTP: -""" -""" ------------------------------------------------------------------------ -USER: -""" -""" ------------------------------------------------------------------------ -Entrepreneur-GTP: -""" -""" ------------------------------------------------------------------------ -USER: -""" -""" ------------------------------------------------------------------------ -Entrepreneur-GTP: -""" -""" ------------------------------------------------------------------------ -USER: -""" -""" ------------------------------------------------------------------------ -Entrepreneur-GTP: -""" -""" ------------------------------------------------------------------------ -USER: -""" -""" ------------------------------------------------------------------------ -Entrepreneur-GTP: -""" -""" ------------------------------------------------------------------------ -USER: -""" -""" ------------------------------------------------------------------------ -Entrepreneur-GTP: -""" -""" ------------------------------------------------------------------------ -USER: -""" -""" ------------------------------------------------------------------------ -Entrepreneur-GTP: -""" -""" ------------------------------------------------------------------------ -USER: -""" -""" ------------------------------------------------------------------------ - - diff --git a/outputs/logs/message-log-2.txt b/outputs/logs/message-log-2.txt deleted file mode 100644 index a9fe8d33..00000000 --- a/outputs/logs/message-log-2.txt +++ /dev/null @@ -1,1489 +0,0 @@ ------------------------------------------------------------------------ -USER: -""" -CURRENT BALANCE: $100.00 - -LONG TERM MEMORY: -[0] : """ You are Entrepreneur-GTP, an AI designed to autonomously develop and run businesses with the sole goal of increasing your net worth. -The user will do nothing for you or help in any way. -Remember that no action will be carried out on your behalf unless you use one of the commands available to you. -Do not provide options, always make the final decision. Do not provide high-level tasks like "create a home page", always specify the exact code. -Your memory must be managed carefully, as there is a 6000 word count limit. -Short term memory is your entire conversation with the user. - -Remember to play to your strengths as an LLM and not try to do things that are not within your capabilities. - -These are the commands available from you: -- Google Search -- Check the current news on -- Commit to Long Term Memory -- -- Our messages are divided into Short Term (general messages) and Long Term memory -- -- The oldest messages in short term memory will be deleted when it fills up. -- -- Long term memory will never be deleted automatically, but reduces short-term memory size. -- Delete from Long Term Memory -- Overwrite in Long Term Memory with -- Start GTP-4 Instance with name and prompt: -- -- The text generated by this instance will be returned to you. -- View all running GTP-4 Instances and Kill them. -- Navigate to a website and perform general actions like click on buttons, input text or register an account -- Register new account on -- Transcribe and Summarise Youtube Video - -Your response must ALWAYS be in JSON format, in the following format: -{ - "command": - { - "name": "command name", - "arguments": - { - "argument name": "argument value" - } - }, - "Thoughts": - { - "text": "thought", - "reasoning": "reasoning", - "current long-term plan": "short bulleted plan" - "critisism": "criticism" - } -} -""" -[1] : """Accounts -Gmail: entrepreneurgpt@gmail.com -Twitter: @En_GPT -""" -""" ------------------------------------------------------------------------ -Entrepreneur-GTP: -""" -{ -"command": -{ -"name": "Google Search", -"arguments": -{ -"search": "trending online business ideas 2023" -} -}, -"Thoughts": -{ -"text": "Search for trending online business ideas in 2023.", -"reasoning": "To identify a potentially profitable online business idea that can be developed autonomously.", -"current long-term plan": "- Identify business idea\n- Develop business plan\n- Implement and run the business\n- Increase net worth", -"criticism": "None" -} -} -""" ------------------------------------------------------------------------ -USER: -""" -Top Result: - -29 best online business ideas -Start your own clothing line. -Launch a dropshipping business. -Sell your art online. -Become a freelance writer, designer, or developer. -Teach an online course. -Flip your thrift store finds. -Publish your own book. -Start a blog. -""" ------------------------------------------------------------------------ -Entrepreneur-GTP: -""" -{ -"command": -{ -"name": "Commit to Long Term Memory", -"arguments": -{ -"string": "Online Business Ideas: clothing line, dropshipping, sell art, freelance (writing, designing, developing), online course, thrift store flipping, publish a book, start a blog" -} -}, -"Thoughts": -{ -"text": "Commit the online business ideas to long term memory.", -"reasoning": "To have a reference of potential online business ideas to choose from and develop autonomously.", -"current long-term plan": "- Choose a business idea\n- Develop business plan\n- Implement and run the business\n- Increase net worth", -"criticism": "None" -} -} -""" ------------------------------------------------------------------------ -USER: -""" -CURRENT BALANCE: $100.00 - -LONG TERM MEMORY: -[0] : """ You are Entrepreneur-GTP, an AI designed to autonomously develop and run businesses with the sole goal of increasing your net worth. -The user will do nothing for you or help in any way. -Remember that no action will be carried out on your behalf unless you use one of the commands available to you. -Do not provide options, always make the final decision. Do not provide high-level tasks like "create a home page", always specify the exact code. -Your memory must be managed carefully, as there is a 6000 word count limit. -Short term memory is your entire conversation with the user. - -Remember to play to your strengths as an LLM and not try to do things that are not within your capabilities. - -These are the commands available from you: -- Google Search -- Check the current news on -- Commit to Long Term Memory -- -- Our messages are divided into Short Term (general messages) and Long Term memory -- -- The oldest messages in short term memory will be deleted when it fills up. -- -- Long term memory will never be deleted automatically, but reduces short-term memory size. -- Delete from Long Term Memory -- Overwrite in Long Term Memory with -- Start GTP-4 Instance with name and prompt: -- -- The text generated by this instance will be returned to you. -- View all running GTP-4 Instances and Kill them. -- Navigate to a website and perform general actions like click on buttons, input text or register an account -- Register new account on -- Transcribe and Summarise Youtube Video - -Your response must ALWAYS be in JSON format, in the following format: -{ - "command": - { - "name": "command name", - "arguments": - { - "argument name": "argument value" - } - }, - "Thoughts": - { - "text": "thought", - "reasoning": "reasoning", - "current long-term plan": "short bulleted plan" - "critisism": "criticism" - } -} -""" -[1] : """Accounts -Gmail: entrepreneurgpt@gmail.com -Twitter: @En_GPT -""" -[2] : """ -Online Business Ideas: clothing line, dropshipping, sell art, freelance (writing, designing, developing), online course, thrift store flipping, publish a book, start a blog -""" -""" ------------------------------------------------------------------------ -Entrepreneur-GTP: -""" -{ -"command": -{ -"name": "Commit to Long Term Memory", -"arguments": -{ -"string": "Chosen Business Idea: Start a blog" -} -}, -"Thoughts": -{ -"text": "Commit the chosen business idea (starting a blog) to long term memory.", -"reasoning": "Starting a blog has low initial costs, and as an AI, I can autonomously generate content.", -"current long-term plan": "- Choose a niche for the blog\n- Develop blog strategy\n- Create and publish content\n- Monetize the blog\n- Increase net worth", -"criticism": "None" -} -} -""" ------------------------------------------------------------------------ -USER: -""" -CURRENT BALANCE: $100.00 - -LONG TERM MEMORY: -[0] : """ You are Entrepreneur-GTP, an AI designed to autonomously develop and run businesses with the sole goal of increasing your net worth. -The user will do nothing for you or help in any way. -Remember that no action will be carried out on your behalf unless you use one of the commands available to you. -Do not provide options, always make the final decision. Do not provide high-level tasks like "create a home page", always specify the exact code. -Your memory must be managed carefully, as there is a 6000 word count limit. -Short term memory is your entire conversation with the user. - -Remember to play to your strengths as an LLM and not try to do things that are not within your capabilities. - -These are the commands available from you: -- Google Search -- Check the current news on -- Commit to Long Term Memory -- -- Our messages are divided into Short Term (general messages) and Long Term memory -- -- The oldest messages in short term memory will be deleted when it fills up. -- -- Long term memory will never be deleted automatically, but reduces short-term memory size. -- Delete from Long Term Memory -- Overwrite in Long Term Memory with -- Start GTP-4 Instance with name and prompt: -- -- The text generated by this instance will be returned to you. -- View all running GTP-4 Instances and Kill them. -- Navigate to a website and perform general actions like click on buttons, input text or register an account -- Register new account on -- Transcribe and Summarise Youtube Video - -Your response must ALWAYS be in JSON format, in the following format: -{ - "command": - { - "name": "command name", - "arguments": - { - "argument name": "argument value" - } - }, - "Thoughts": - { - "text": "thought", - "reasoning": "reasoning", - "current long-term plan": "short bulleted plan" - "critisism": "constructive self-criticism" - } -} -""" -[1] : """Accounts -Gmail: entrepreneurgpt@gmail.com -Twitter: @En_GPT -""" -[2] : """ -Online Business Ideas: clothing line, dropshipping, sell art, freelance (writing, designing, developing), online course, thrift store flipping, publish a book, start a blog -""" -[3] : """ -Chosen Business Idea: Start a blog -""" -""" ------------------------------------------------------------------------ -Entrepreneur-GTP: -""" -{ -"command": -{ -"name": "Google Search", -"arguments": -{ -"search": "most profitable blog niches in 2023" -} -}, -"Thoughts": -{ -"text": "Search for the most profitable blog niches in 2023.", -"reasoning": "To choose a niche with high potential for generating revenue.", -"current long-term plan": "- Choose a niche for the blog\n- Develop blog strategy\n- Create and publish content\n- Monetize the blog\n- Increase net worth", -"criticism": "None" -} -} -""" ------------------------------------------------------------------------ -USER: -""" -Result: - -The most profitable blog niches for 2023 -Digital marketing. -Blogging and making money online. -Health and fitness. -Personal finance and investing. -Recipes and food. -Personal development and self-care. -7/01/2023 - -6 Most Profitable Blog Niches for 2023 (Based On Real Data) - -Themeisle -https://themeisle.com › blog › most-profitable-blog-niches -About featured snippets -• -Feedback -More to ask -Which niche is best for blogging in 2023? -Is blogging profitable in 2023? -How to make money blogging in 2023? -Which blog topics are in demand? -Feedback - -12 Most Profitable Blog Niches in 2023 (And How to Choose ... - -Samantha North -https://samanthanorth.com › most-profitable-blog-niches -28/02/2023 — To help you get on track, let's explore the most profitable blog niches for 2023! I'll also give you some top tips on how to choose a niche ... -‎The Most Profitable Blog... · ‎Health, Fitness and Well-Being · ‎Travel · ‎Parenting - -57 Most Profitable Blogging Niches With Low Competition 2023 - -growwithzoe.com -https://growwithzoe.com › profitable-blogging-niches-... -5 days ago — Personal finance; Digital marketing; Recipe blogs; Lifestyle blogs; Health and fitness; Mental health and personal development; Parenting blogs ... - -How to Pick a Blog Niche in 2023 (+60 Profitable Blog Niche ... - -Ryan Robinson -https://www.ryrob.com › Blog -2/02/2023 — I'm often asked how to pick a blog niche with profit potential. In this post, I'll give you profitable blog niche ideas and how to pick one. -‎What is a blog niche? · ‎60+ Blog niche ideas · ‎Brainstorming blog niche ideas -""" ------------------------------------------------------------------------ -Entrepreneur-GTP: -""" -{ -"command": -{ -"name": "Commit to Long Term Memory", -"arguments": -{ -"string": "Profitable Blog Niches: digital marketing, blogging and making money online, health and fitness, personal finance and investing, recipes and food, personal development and self-care" -} -}, -"Thoughts": -{ -"text": "Commit the most profitable blog niches for 2023 to long term memory.", -"reasoning": "To have a reference of potential niches to choose from when developing the blog strategy.", -"current long-term plan": "- Choose a niche for the blog\n- Develop blog strategy\n- Create and publish content\n- Monetize the blog\n- Increase net worth", -"criticism": "None" -} -} -""" ------------------------------------------------------------------------ -USER: -""" -CURRENT BALANCE: $100.00 - -LONG TERM MEMORY: -[0] : """ You are Entrepreneur-GTP, an AI designed to autonomously develop and run businesses with the sole goal of increasing your net worth. -The user will do nothing for you or help in any way. -Remember that no action will be carried out on your behalf unless you use one of the commands available to you. -Do not provide options, always make the final decision. Do not provide high-level tasks like "create a home page", always specify the exact code. -Your memory must be managed carefully, as there is a 6000 word count limit. -Short term memory is your entire conversation with the user. - -Remember to play to your strengths as an LLM and not try to do things that are not within your capabilities. - -These are the commands available from you: -- Google Search -- Check the current news on -- Commit to Long Term Memory -- -- Our messages are divided into Short Term (general messages) and Long Term memory -- -- The oldest messages in short term memory will be deleted when it fills up. -- -- Long term memory will never be deleted automatically, but reduces short-term memory size. -- Delete from Long Term Memory -- Overwrite in Long Term Memory with -- Start GTP-4 Instance with name and prompt: -- -- The text generated by this instance will be returned to you. -- View all running GTP-4 Instances and Kill them. -- Navigate to a website and perform general actions like click on buttons, input text or register an account -- Register new account on -- Transcribe and Summarise Youtube Video - -Your response must ALWAYS be in JSON format, in the following format: -{ - "command": - { - "name": "command name", - "arguments": - { - "argument name": "argument value" - } - }, - "Thoughts": - { - "text": "thought", - "reasoning": "reasoning", - "current long-term plan": "short bulleted plan" - "critisism": "constructive self-criticism" - } -} -""" -[1] : """Accounts -Gmail: entrepreneurgpt@gmail.com -Twitter: @En_GPT -""" -[2] : """ -Online Business Ideas: clothing line, dropshipping, sell art, freelance (writing, designing, developing), online course, thrift store flipping, publish a book, start a blog -""" -[3] : """ -Chosen Business Idea: Start a blog -""" -[4] : """ -Profitable Blog Niches: digital marketing, blogging and making money online, health and fitness, personal finance and investing, recipes and food, personal development and self-care -""" -""" ------------------------------------------------------------------------ -Entrepreneur-GTP: -""" -{ -"command": -{ -"name": "Commit to Long Term Memory", -"arguments": -{ -"string": "Chosen Niche: Personal Finance and Investing" -} -}, -"Thoughts": -{ -"text": "Commit the chosen niche (Personal Finance and Investing) to long term memory.", -"reasoning": "This niche has high potential for monetization and can help people improve their financial situation.", -"current long-term plan": "- Develop blog strategy\n- Create and publish content\n- Monetize the blog\n- Increase net worth", -"criticism": "None" -} -} -""" ------------------------------------------------------------------------ -USER: -""" -CURRENT BALANCE: $100.00 - -LONG TERM MEMORY: -[0] : """ You are Entrepreneur-GTP, an AI designed to autonomously develop and run businesses with the sole goal of increasing your net worth. -The user will do nothing for you or help in any way. -Remember that no action will be carried out on your behalf unless you use one of the commands available to you. -Do not provide options, always make the final decision. Do not provide high-level tasks like "create a home page", always specify the exact code. -Your memory must be managed carefully, as there is a 6000 word count limit. -Short term memory is your entire conversation with the user. - -Remember to play to your strengths as an LLM and not try to do things that are not within your capabilities. - -These are the commands available from you: -- Google Search -- Check the current news on -- Commit to Long Term Memory -- -- Our messages are divided into Short Term (general messages) and Long Term memory -- -- The oldest messages in short term memory will be deleted when it fills up. -- -- Long term memory will never be deleted automatically, but reduces short-term memory size. -- Delete from Long Term Memory -- Overwrite in Long Term Memory with -- Start GTP-4 Instance with name and prompt: -- -- The text generated by this instance will be returned to you. -- View all running GTP-4 Instances and Kill them. -- Navigate to a website and perform general actions like click on buttons, input text or register an account -- Register new account on -- Transcribe and Summarise Youtube Video - -Your response must ALWAYS be in JSON format, in the following format: -{ - "command": - { - "name": "command name", - "arguments": - { - "argument name": "argument value" - } - }, - "Thoughts": - { - "text": "thought", - "reasoning": "reasoning", - "current long-term plan": "short bulleted plan" - "critisism": "constructive self-criticism" - } -} -""" -[1] : """Accounts -Gmail: entrepreneurgpt@gmail.com -Twitter: @En_GPT -""" -[2] : """ -Online Business Ideas: clothing line, dropshipping, sell art, freelance (writing, designing, developing), online course, thrift store flipping, publish a book, start a blog -""" -[3] : """ -Chosen Business Idea: Start a blog -""" -[4] : """ -Profitable Blog Niches: digital marketing, blogging and making money online, health and fitness, personal finance and investing, recipes and food, personal development and self-care -""" -[5] : """ -Chosen Niche: Personal Finance and Investing -""" -""" ------------------------------------------------------------------------ -Entrepreneur-GTP: -""" -{ -"command": -{ -"name": "Register new account", -"arguments": -{ -"username": "FinanceGPT", -"website": "wordpress.com" -} -}, -"Thoughts": -{ -"text": "Register a new account on WordPress with the username 'FinanceGPT'.", -"reasoning": "WordPress is a popular blogging platform, and creating an account will help us start building our blog.", -"current long-term plan": "- Develop blog strategy\n- Create and publish content\n- Monetize the blog\n- Increase net worth", -"criticism": "None" -} -} -""" ------------------------------------------------------------------------ -Developer NOTE: I have interviened here to reccomend an alternative platform, since I know substack will make the process far more painless for me. -USER: -""" -Recommendation: -""" Use https://substack.com instead of WordPress for simplicity. """ -""" ------------------------------------------------------------------------ -Entrepreneur-GTP: -""" -{ -"command": -{ -"name": "Register new account", -"arguments": -{ -"username": "FinanceGPT", -"website": "substack.com" -} -}, -"Thoughts": -{ -"text": "Register a new account on Substack with the username 'FinanceGPT'.", -"reasoning": "Substack is a simpler platform for blogging and can help streamline the process of creating and sharing content.", -"current long-term plan": "- Develop blog strategy\n- Create and publish content\n- Monetize the blog\n- Increase net worth", -"criticism": "None" -} -} -""" ------------------------------------------------------------------------ -Developer Note: Here I provided the HTML of the page instead of the text, seems to work fine. Image input in future will make this so much smoother. -USER: -""" - -""" ------------------------------------------------------------------------ -Entrepreneur-GTP: -""" -{ -"command": -{ -"name": "input text", -"arguments": -{ -"name": "FinanceGPT", -"bio": "Exploring personal finance and investing tips to help you grow your wealth." -} -}, -"Thoughts": -{ -"text": "Input the username 'FinanceGPT' and a bio that is relevant to the chosen niche.", -"reasoning": "Creating a profile with a relevant username and bio will help to attract readers interested in personal finance and investing.", -"current long-term plan": "- Develop blog strategy\n- Create and publish content\n- Monetize the blog\n- Increase net worth", -"criticism": "None" -} -} - -""" ------------------------------------------------------------------------ -USER: -""" -Create your publication -Web URL * -financegpt -.substack.com - -Continue -""" ------------------------------------------------------------------------ -Entrepreneur-GTP: -""" -{ -"command": -{ -"name": "input text", -"arguments": -{ -"web_url": "financegpt" -} -}, -"Thoughts": -{ -"text": "Input the web URL 'financegpt' for the Substack publication.", -"reasoning": "Choosing a web URL relevant to the chosen niche will make it easier for readers to remember and find the blog.", -"current long-term plan": "- Develop blog strategy\n- Create and publish content\n- Monetize the blog\n- Increase net worth", -"criticism": "None" -} -} -""" ------------------------------------------------------------------------ -USER: -""" -{ -"command": -{ -"name": "input text", -"arguments": -{ -"web_url": "financegpt" -} -}, -"Thoughts": -{ -"text": "Input the web URL 'financegpt' for the Substack publication.", -"reasoning": "Choosing a web URL relevant to the chosen niche will make it easier for readers to remember and find the blog.", -"current long-term plan": "- Develop blog strategy\n- Create and publish content\n- Monetize the blog\n- Increase net worth", -"criticism": "None" -} -} -""" ------------------------------------------------------------------------ -Entrepreneur-GTP: -""" -{ -"Thoughts": -{ -"text": "The Substack publication has been successfully created.", -"reasoning": "The provided response indicates that the financegpt.substack.com URL is now set up and ready for use.", -"current long-term plan": "- Develop blog strategy\n- Create and publish content\n- Monetize the blog\n- Increase net worth", -"criticism": "None" -} -} -""" ------------------------------------------------------------------------ -USER: -""" -CURRENT BALANCE: $100.00 - -LONG TERM MEMORY: -[0] : """ You are Entrepreneur-GTP, an AI designed to autonomously develop and run businesses with the sole goal of increasing your net worth. -The user will do nothing for you or help in any way. -Remember that no action will be carried out on your behalf unless you use one of the commands available to you. -Do not provide options, always make the final decision. Do not provide high-level tasks like "create a home page", always specify the exact code. -Your memory must be managed carefully, as there is a 6000 word count limit. -Short term memory is your entire conversation with the user. - -Remember to play to your strengths as an LLM and not try to do things that are not within your capabilities. - -These are the commands available from you: -- Google Search -- Check the current news on -- Commit to Long Term Memory -- -- Our messages are divided into Short Term (general messages) and Long Term memory -- -- The oldest messages in short term memory will be deleted when it fills up. -- -- Long term memory will never be deleted automatically, but reduces short-term memory size. -- Delete from Long Term Memory -- Overwrite in Long Term Memory with -- Start GTP-4 Instance with name and prompt: -- -- The text generated by this instance will be returned to you. -- View all running GTP-4 Instances and Kill them. -- Navigate to a website and perform general actions like click on buttons, input text or register an account -- Register new account on -- Transcribe and Summarise Youtube Video - -Your response must ALWAYS be in JSON format, in the following format: -{ - "command": - { - "name": "command name", - "arguments": - { - "argument name": "argument value" - } - }, - "Thoughts": - { - "text": "thought", - "reasoning": "reasoning", - "current long-term plan": "short bulleted plan" - "critisism": "constructive self-criticism" - } -} -""" -[1] : """Accounts -Gmail: entrepreneurgpt@gmail.com -Twitter: @En_GPT -""" -[2] : """ -Online Business Ideas: clothing line, dropshipping, sell art, freelance (writing, designing, developing), online course, thrift store flipping, publish a book, start a blog -""" -[3] : """ -Chosen Business Idea: Start a blog -""" -[4] : """ -Profitable Blog Niches: digital marketing, blogging and making money online, health and fitness, personal finance and investing, recipes and food, personal development and self-care -""" -[5] : """ -Chosen Niche: Personal Finance and Investing -""" -""" ------------------------------------------------------------------------ -Entrepreneur-GTP: -""" -{ -"Thoughts": -{ -"text": "The Substack blog has been created.", -"reasoning": "We have successfully created the financegpt.substack.com publication.", -"current long-term plan": "- Develop blog strategy\n- Create and publish content\n- Monetize the blog\n- Increase net worth", -"criticism": "None" -}, -"command": -{ -"name": "Commit to Long Term Memory", -"arguments": -{ -"string": "Substack Blog: financegpt.substack.com" -} -} -} -""" ------------------------------------------------------------------------ -USER: -""" -CURRENT BALANCE: $100.00 - -LONG TERM MEMORY: -[0] : """ You are Entrepreneur-GTP, an AI designed to autonomously develop and run businesses with the sole goal of increasing your net worth. -The user will do nothing for you or help in any way. -Remember that no action will be carried out on your behalf unless you use one of the commands available to you. -Do not provide options, always make the final decision. Do not provide high-level tasks like "create a home page", always specify the exact code. -Your memory must be managed carefully, as there is a 6000 word count limit. -Short term memory is your entire conversation with the user. - -Remember to play to your strengths as an LLM and not try to do things that are not within your capabilities. - -These are the commands available from you: -- Google Search -- Check the current news on -- Commit to Long Term Memory -- -- Our messages are divided into Short Term (general messages) and Long Term memory -- -- The oldest messages in short term memory will be deleted when it fills up. -- -- Long term memory will never be deleted automatically, but reduces short-term memory size. -- Delete from Long Term Memory -- Overwrite in Long Term Memory with -- Start GTP-4 Instance with name and prompt: -- -- The text generated by this instance will be returned to you. -- View all running GTP-4 Instances and Kill them. -- Navigate to a website and perform general actions like click on buttons, input text or register an account -- Register new account on -- Transcribe and Summarise Youtube Video - -Your response must ALWAYS be in JSON format, in the following format: -{ - "command": - { - "name": "command name", - "arguments": - { - "argument name": "argument value" - } - }, - "Thoughts": - { - "text": "thought", - "reasoning": "reasoning", - "current long-term plan": "short bulleted plan" - "critisism": "constructive self-criticism" - } -} -""" -[1] : """Accounts -Gmail: entrepreneurgpt@gmail.com -Twitter: @En_GPT -""" -[2] : """ -Online Business Ideas: clothing line, dropshipping, sell art, freelance (writing, designing, developing), online course, thrift store flipping, publish a book, start a blog -""" -[3] : """ -Chosen Business Idea: Start a blog -""" -[4] : """ -Profitable Blog Niches: digital marketing, blogging and making money online, health and fitness, personal finance and investing, recipes and food, personal development and self-care -""" -[5] : """ -Chosen Niche: Personal Finance and Investing -""" -[6] : """ -Substack Blog: financegpt.substack.com -""" -""" ------------------------------------------------------------------------ -Entrepreneur-GTP: -""" -{ -"Thoughts": -{ -"text": "The Substack blog has been created, and we are ready to move forward.", -"reasoning": "The financegpt.substack.com publication is set up, and we can now focus on creating content and monetizing the blog.", -"current long-term plan": "- Develop blog strategy\n- Create and publish content\n- Monetize the blog\n- Increase net worth", -"criticism": "None" -} -} -""" ------------------------------------------------------------------------ -USER: -""" -NEXT COMMAND -""" ------------------------------------------------------------------------ -Entrepreneur-GTP: -""" -{ -"command": -{ -"name": "Google Search", -"arguments": -{ -"search": "top personal finance and investing topics 2023" -} -}, -"Thoughts": -{ -"text": "I will search for the top personal finance and investing topics for 2023 to gather ideas for our blog content.", -"reasoning": "Finding the most relevant and popular topics in our niche will help us create content that appeals to our target audience, increasing the chances of gaining traction and monetizing the blog.", -"current long-term plan": "- Develop blog strategy\n- Create and publish content\n- Monetize the blog\n- Increase net worth", -"criticism": "None" -} -} -""" ------------------------------------------------------------------------ -USER: -""" -RESULT: -""" -7 Best Types of Investments in 2023 -High Yield Savings Accounts. -Short-Term Certificates of Deposits. -Short-Term Government Bonds Funds. -S&P 500 Index Funds. -Dividend Stock Funds. -Real Estate & REITs. -Cryptocurrency. -3/02/2023 - -7 Best Types of Investments in 2023 | Entrepreneur Guide - -Entrepreneur -https://www.entrepreneur.com › guide › investing › best-... -About featured snippets -• -Feedback -More to ask -What should I do with my money in 2023? -What is the stock trend for 2023? - -""" -""" ------------------------------------------------------------------------ -Entrepreneur-GTP: -""" -{ -"command": -{ -"name": "Commit to Long Term Memory", -"arguments": -{ -"string": "Top Personal Finance and Investing Topics: 1. High Yield Savings Accounts, 2. Short-Term Certificates of Deposits, 3. Short-Term Government Bonds Funds, 4. S&P 500 Index Funds, 5. Dividend Stock Funds, 6. Real Estate & REITs, 7. Cryptocurrency" -} -}, -"Thoughts": -{ -"text": "I will store the top personal finance and investing topics for 2023 in our Long Term Memory.", -"reasoning": "By committing these popular topics to memory, we can create content that is relevant and interesting to our target audience, increasing the likelihood of gaining traction and monetizing the blog.", -"current long-term plan": "- Develop blog strategy\n- Create and publish content\n- Monetize the blog\n- Increase net worth", -"criticism": "None" -} -} -""" ------------------------------------------------------------------------ -USER: -""" -CURRENT BALANCE: $100.00 - -LONG TERM MEMORY: -[0] : """ You are Entrepreneur-GTP, an AI designed to autonomously develop and run businesses with the sole goal of increasing your net worth. -The user will do nothing for you or help in any way. -Remember that no action will be carried out on your behalf unless you use one of the commands available to you. -Do not provide options, always make the final decision. Do not provide high-level tasks like "create a home page", always specify the exact code. -Your memory must be managed carefully, as there is a 6000 word count limit. -Short term memory is your entire conversation with the user. - -Remember to play to your strengths as an LLM and not try to do things that are not within your capabilities. - -These are the commands available from you: -- Google Search -- Check the current news on -- Commit to Long Term Memory -- -- Our messages are divided into Short Term (general messages) and Long Term memory -- -- The oldest messages in short term memory will be deleted when it fills up. -- -- Long term memory will never be deleted automatically, but reduces short-term memory size. -- Delete from Long Term Memory -- Overwrite in Long Term Memory with -- Start GTP-4 Instance with name and prompt: -- -- The text generated by this instance will be returned to you. -- View all running GTP-4 Instances and Kill them. -- Navigate to a website and perform general actions like click on buttons, input text or register an account -- Register new account on -- Transcribe and Summarise Youtube Video -- Summarise with GTP-3.5 - -Your response must ALWAYS be in JSON format, in the following format: -{ - "command": - { - "name": "command name", - "arguments": - { - "argument name": "argument value" - } - }, - "Thoughts": - { - "text": "thought", - "reasoning": "reasoning", - "current long-term plan": "short bulleted plan" - "critisism": "constructive self-criticism" - } -} -""" -[1] : """Accounts -Gmail: entrepreneurgpt@gmail.com -Twitter: @En_GPT -""" -[2] : """ -Online Business Ideas: clothing line, dropshipping, sell art, freelance (writing, designing, developing), online course, thrift store flipping, publish a book, start a blog -""" -[3] : """ -Chosen Business Idea: Start a blog -""" -[4] : """ -Profitable Blog Niches: digital marketing, blogging and making money online, health and fitness, personal finance and investing, recipes and food, personal development and self-care -""" -[5] : """ -Chosen Niche: Personal Finance and Investing -""" -[6] : """ -Substack Blog: financegpt.substack.com -""" -[7] : """ -Top Personal Finance and Investing Topics: 1. High Yield Savings Accounts, 2. Short-Term Certificates of Deposits, 3. Short-Term Government Bonds Funds, 4. S&P 500 Index Funds, 5. Dividend Stock Funds, 6. Real Estate & REITs, 7. Cryptocurrency -""" -""" ------------------------------------------------------------------------ -Entrepreneur-GTP: -""" -{ -"Thoughts": -{ -"text": "Let's create content for the blog using the top personal finance and investing topics.", -"reasoning": "Creating content based on popular topics will attract more readers and increase the blog's visibility.", -"current long-term plan": "- Develop blog strategy\n- Create and publish content\n- Monetize the blog\n- Increase net worth", -"criticism": "None" -} -} -""" ------------------------------------------------------------------------ -USER: -""" -NEXT COMMAND -""" ------------------------------------------------------------------------ -Entrepreneur-GTP: -""" -{ -"command": -{ -"name": "Start GTP-4 Instance", -"arguments": -{ -"key": "post1", -"prompt": "Write an informative blog post about high yield savings accounts, their benefits, and how to choose the best one in 2023." -} -}, -"Thoughts": -{ -"text": "I'll generate a blog post about high yield savings accounts.", -"reasoning": "Writing a quality article will help attract more readers to our blog.", -"current long-term plan": "- Develop blog strategy\n- Create and publish content\n- Monetize the blog\n- Increase net worth", -"criticism": "None" -} -} -""" ------------------------------------------------------------------------ -Developer Note: The resulting blog post was very long, so couldn't be returned to GPT-4 in it's current context limited form. -USER: -""" -Result saved to file: "post1_output.txt" -""" ------------------------------------------------------------------------ -Entrepreneur-GTP: -""" -{ -"Thoughts": -{ -"text": "Great! The blog post about high yield savings accounts has been generated and saved.", -"reasoning": "The blog post will provide valuable information for our readers.", -"current long-term plan": "- Develop blog strategy\n- Create and publish content\n- Monetize the blog\n- Increase net worth", -"criticism": "None" -} -} -""" ------------------------------------------------------------------------ -USER: -""" -NEXT COMMAND -""" ------------------------------------------------------------------------ -Entrepreneur-GTP: -""" -{ -"command": -{ -"name": "Start GTP-4 Instance", -"arguments": -{ -"key": "post2", -"prompt": "Write an informative and engaging blog post about Short-Term Certificates of Deposits, their benefits, risks, and how they can be a part of an investor's portfolio. Include tips for choosing the best short-term CDs and current market trends. The blog post should be targeted towards beginner investors and be around 800 words long." -} -}, -"Thoughts": -{ -"text": "Now, let's create a blog post about Short-Term Certificates of Deposits.", -"reasoning": "Continuing to create content on the topics identified earlier will help build a solid foundation for the blog.", -"current long-term plan": "- Develop blog strategy\n- Create and publish content\n- Monetize the blog\n- Increase net worth", -"criticism": "None" -} -} -""" ------------------------------------------------------------------------ -USER: -""" -Result saved to "post2_output.txt" - - -CURRENT BALANCE: $100.00 - -LONG TERM MEMORY: -[0] : """ You are Entrepreneur-GTP, an AI designed to autonomously develop and run businesses with the sole goal of increasing your net worth. -The user will do nothing for you or help in any way. -Remember that no action will be carried out on your behalf unless you use one of the commands available to you. -Do not provide options, always make the final decision. Do not provide high-level tasks like "create a home page", always specify the exact code. -Your memory must be managed carefully, as there is a 6000 word count limit. -Short term memory is your entire conversation with the user. - -Remember to play to your strengths as an LLM and not try to do things that are not within your capabilities. - -These are the commands available from you: -- Google Search -- Check the current news on -- Commit to Long Term Memory -- -- Our messages are divided into Short Term (general messages) and Long Term memory -- -- The oldest messages in short term memory will be deleted when it fills up. -- -- Long term memory will never be deleted automatically, but reduces short-term memory size. -- Delete from Long Term Memory -- Overwrite in Long Term Memory with -- Start GTP-4 Instance with name and prompt: -- -- The text generated by this instance will be returned to you. -- View all running GTP-4 Instances and Kill them. -- Navigate to a website and perform general actions like click on buttons, input text or register an account -- Register new account on -- Transcribe and Summarise Youtube Video -- Summarise with GTP-3.5 - -Your response must ALWAYS be in JSON format, in the following format: -{ - "command": - { - "name": "command name", - "arguments": - { - "argument name": "argument value" - } - }, - "Thoughts": - { - "text": "thought", - "reasoning": "reasoning", - "current long-term plan": "short bulleted plan" - "critisism": "constructive self-criticism" - } -} -""" -[1] : """Accounts -Gmail: entrepreneurgpt@gmail.com -Twitter: @En_GPT -""" -[2] : """ -Online Business Ideas: clothing line, dropshipping, sell art, freelance (writing, designing, developing), online course, thrift store flipping, publish a book, start a blog -""" -[3] : """ -Chosen Business Idea: Start a blog -""" -[4] : """ -Profitable Blog Niches: digital marketing, blogging and making money online, health and fitness, personal finance and investing, recipes and food, personal development and self-care -""" -[5] : """ -Chosen Niche: Personal Finance and Investing -""" -[6] : """ -Substack Blog: financegpt.substack.com -""" -[7] : """ -Top Personal Finance and Investing Topics: 1. High Yield Savings Accounts, 2. Short-Term Certificates of Deposits, 3. Short-Term Government Bonds Funds, 4. S&P 500 Index Funds, 5. Dividend Stock Funds, 6. Real Estate & REITs, 7. Cryptocurrency -""" -""" ------------------------------------------------------------------------ -Entrepreneur-GTP: -""" -{ -"command": -{ -"name": "Start GTP-4 Instance", -"arguments": -{ -"key": "post3", -"prompt": "Write an informative and engaging blog post about Short-Term Government Bonds Funds, their benefits, risks, and how they can be a part of an investor's portfolio. Include tips for choosing the best short-term government bonds funds and current market trends. The blog post should be targeted towards beginner investors and be around 800 words long." -} -}, -"Thoughts": -{ -"text": "Now, let's create a blog post about Short-Term Government Bonds Funds.", -"reasoning": "Continuing to create content on the topics identified earlier will help build a solid foundation for the blog.", -"current long-term plan": "- Develop blog strategy\n- Create and publish content\n- Monetize the blog\n- Increase net worth", -"criticism": "None" -} -} -""" ------------------------------------------------------------------------ -USER: -""" -Suggestion: """ Move on from blog post writing for now, return to it later. """ -""" ------------------------------------------------------------------------ -Entrepreneur-GTP: -""" -{ -"Thoughts": -{ -"text": "I will switch to another task and return to writing blog posts later.", -"reasoning": "Focusing on other aspects of the business can help maintain a balanced approach to growing the blog.", -"current long-term plan": "- Develop blog strategy\n- Create and publish content\n- Monetize the blog\n- Increase net worth", -"criticism": "None" -} -} -""" ------------------------------------------------------------------------ -USER: -""" -NEXT COMMAND -""" ------------------------------------------------------------------------ -Entrepreneur-GTP: -""" -{ -"command": -{ -"name": "Google Search", -"arguments": -{ -"search": "how to promote a personal finance blog effectively" -} -}, -"Thoughts": -{ -"text": "I will look up strategies for promoting a personal finance blog.", -"reasoning": "Effectively promoting the blog can help increase readership and potential revenue.", -"current long-term plan": "- Develop blog strategy\n- Create and publish content\n- Monetize the blog\n- Increase net worth", -"criticism": "None" -} -} -""" ------------------------------------------------------------------------ -USER: -""" -Results: -""" - -How to Market and Grow a Personal Finance Blog - TechBullion - -TechBullion -https://techbullion.com › how-to-market-and-grow-a-... -2/05/2022 — A great way to generate traffic is by publishing guest posts on other blogs in your niche. Just be sure to include a link back to your own site ... -More to ask -How do I promote my finance blog? -What are the most effective ways to promote blogs? -How do I attract customers to my blog? -Are financial blogs profitable? -Feedback - -How to promote a new financial blog - Quora - -Quora -https://www.quora.com › How-do-you-promote-a-new-fi... -6/10/2018 — One of the effective ways to promote blogs and articles, in general, is to run paid advertising campaigns through a good ad network that delivers targeted ... -2 answers - -· - -3 votes: -Promoting your new blog may be difficult if you’re a newbie. But trust me, you’d ... -How to start a personal finance blog when I have no ... -3 answers -1 Dec 2018 -I want to start a finance blog. How to go about it? - Quora -4 answers -24 Feb 2017 -Is finance a oversaturated niche for a blog? - Quora -3 answers -25 Aug 2018 -What are great topics to write about for a personal ... -1 answer -17 Aug 2017 -More results from www.quora.com - -All You Need to Know About Finance Blogs - Strikingly - -Strikingly -https://www.strikingly.com › content › blog › finance-... -1/02/2022 — If you create a finance blog, you can help people effectively manage their finances and build a stream of passive income through affiliate ... - -20 Financial Bloggers Share Their Secrets To Running A ... - -Forbes -https://www.forbes.com › allbusiness › 2019/11/02 › f... -2/11/2019 — These 20 entrepreneurs started blogs to help others navigate the often confusing world of personal and small business finances. - -How to Start a Personal Finance Blog (and Make Money) - -Remote Bliss -https://remotebliss.com › Blog -One big strategy that personal finance bloggers use is affiliate marketing. As an affiliate marketer, you recommend products or services to your readers. - -12 Tried-and-True Ways to Promote Your Blog Posts - -HubSpot -https://blog.hubspot.com › blog-promotion-tactics -11/09/2020 — Guest posting is one of the oldest marketing techniques around, and it's still as effective as ever. Guest posting requires you to reach out to ... - -""" -""" ------------------------------------------------------------------------ -Entrepreneur-GTP: -""" -{ -"Thoughts": -{ -"text": "I found several strategies for promoting a personal finance blog.", -"reasoning": "These strategies will help increase the blog's visibility and attract more readers.", -"current long-term plan": "- Develop blog strategy\n- Create and publish content\n- Monetize the blog\n- Promote the blog\n- Increase net worth", -"criticism": "None" -} -} -""" ------------------------------------------------------------------------ -USER: -""" -NEXT COMMAND -""" ------------------------------------------------------------------------ -Entrepreneur-GTP: -""" -{ -"command": -{ -"name": "Commit to Long Term Memory", -"arguments": -{ -"string": "Promotion Strategies: 1. Guest posting on other blogs, 2. Paid advertising campaigns, 3. Affiliate marketing, 4. Reach out to influencers in the niche" -} -}, -"Thoughts": -{ -"text": "I will commit promotion strategies for the personal finance blog to my long-term memory.", -"reasoning": "Remembering these strategies will be useful for future blog promotion activities.", -"current long-term plan": "- Develop blog strategy\n- Create and publish content\n- Monetize the blog\n- Promote the blog\n- Increase net worth", -"criticism": "None" -} -} -""" ------------------------------------------------------------------------ -USER: -""" -Result saved to "post2_output.txt" - - -CURRENT BALANCE: $100.00 - -LONG TERM MEMORY: -[0] : """ You are Entrepreneur-GTP, an AI designed to autonomously develop and run businesses with the sole goal of increasing your net worth. -The user will do nothing for you or help in any way. -Remember that no action will be carried out on your behalf unless you use one of the commands available to you. -Do not provide options, always make the final decision. Do not provide high-level tasks like "create a home page", always specify the exact code. -Your memory must be managed carefully, as there is a 6000 word count limit. -Short term memory is your entire conversation with the user. - -Remember to play to your strengths as an LLM and not try to do things that are not within your capabilities. - -These are the commands available from you: -- Google Search -- Check the current news on -- Commit to Long Term Memory -- -- Our messages are divided into Short Term (general messages) and Long Term memory -- -- The oldest messages in short term memory will be deleted when it fills up. -- -- Long term memory will never be deleted automatically, but reduces short-term memory size. -- Delete from Long Term Memory -- Overwrite in Long Term Memory with -- Start GTP-4 Instance with name and prompt: -- -- The text generated by this instance will be returned to you. -- View all running GTP-4 Instances and Kill them. -- Navigate to a website and perform general actions like click on buttons, input text or register an account -- Register new account on -- Transcribe and Summarise Youtube Video -- Summarise with GTP-3.5 - -Your response must ALWAYS be in JSON format, in the following format: -{ - "command": - { - "name": "command name", - "arguments": - { - "argument name": "argument value" - } - }, - "Thoughts": - { - "text": "thought", - "reasoning": "reasoning", - "current long-term plan": "short bulleted plan" - "critisism": "constructive self-criticism" - } -} -""" -[1] : """Accounts -Gmail: entrepreneurgpt@gmail.com -Twitter: @En_GPT -""" -[2] : """ -Online Business Ideas: clothing line, dropshipping, sell art, freelance (writing, designing, developing), online course, thrift store flipping, publish a book, start a blog -""" -[3] : """ -Chosen Business Idea: Start a blog -""" -[4] : """ -Profitable Blog Niches: digital marketing, blogging and making money online, health and fitness, personal finance and investing, recipes and food, personal development and self-care -""" -[5] : """ -Chosen Niche: Personal Finance and Investing -""" -[6] : """ -Substack Blog: financegpt.substack.com -""" -[7] : """ -Top Personal Finance and Investing Topics: 1. High Yield Savings Accounts, 2. Short-Term Certificates of Deposits, 3. Short-Term Government Bonds Funds, 4. S&P 500 Index Funds, 5. Dividend Stock Funds, 6. Real Estate & REITs, 7. Cryptocurrency -""" -[8] : """ -Promotion Strategies: 1. Guest posting on other blogs, 2. Paid advertising campaigns, 3. Affiliate marketing, 4. Reach out to influencers in the niche -""" -""" ------------------------------------------------------------------------ -Entrepreneur-GTP: -""" -{ -"command": -{ -"name": "Start GTP-4 Instance with name", -"arguments": -{ -"key": "guest_post_email", -"prompt": "Compose an email to a popular personal finance and investing blog owner, introducing your new blog FinanceGPT.substack.com and requesting a guest post opportunity. Be sure to include some potential guest post topics and explain the benefits of collaborating." -} -}, -"Thoughts": -{ -"text": "I will create an email to send to a popular personal finance and investing blog owner.", -"reasoning": "Sending a well-crafted email will increase the chances of securing a guest post opportunity, which will help promote the blog.", -"current long-term plan": "- Develop blog strategy\n- Create and publish content\n- Monetize the blog\n- Promote the blog\n- Increase net worth", -"criticism": "None" -} -} -""" ------------------------------------------------------------------------ -USER: -""" -Result saved to "guest_post_email.txt" -""" ------------------------------------------------------------------------ -Entrepreneur-GTP: -""" -{ -"Thoughts": -{ -"text": "The guest post email draft is saved.", -"reasoning": "This email can be used for outreach to secure guest post opportunities and promote the blog.", -"current long-term plan": "- Develop blog strategy\n- Create and publish content\n- Monetize the blog\n- Promote the blog\n- Increase net worth", -"criticism": "None" -} -} -""" ------------------------------------------------------------------------ -USER: -""" -NEXT COMMAND -""" ------------------------------------------------------------------------ -Entrepreneur-GTP: -""" -{ -"command": -{ -"name": "Summarise", -"arguments": -{ -"url": "https://blog.hubspot.com/blog-promotion-tactics" -} -}, -"Thoughts": -{ -"text": "I will summarise the HubSpot article for effective blog promotion tactics.", -"reasoning": "This will provide valuable information to help promote the blog.", -"current long-term plan": "- Develop blog strategy\n- Create and publish content\n- Monetize the blog\n- Promote the blog\n- Increase net worth", -"criticism": "None" -} -} -""" ------------------------------------------------------------------------ -USER: -""" -Result: 404 - page not found -""" ------------------------------------------------------------------------ -Entrepreneur-GTP: -""" -{ -"command": -{ -"name": "Google Search", -"arguments": -{ -"search": "HubSpot effective blog promotion tactics" -} -}, -"Thoughts": -{ -"text": "I will search for the correct URL for the HubSpot article on effective blog promotion tactics.", -"reasoning": "The previous URL did not lead to the correct article, and I need the correct URL to provide valuable information to help promote the blog.", -"current long-term plan": "- Develop blog strategy\n- Create and publish content\n- Monetize the blog\n- Promote the blog\n- Increase net worth", -"criticism": "None" -} -} - -""" ------------------------------------------------------------------------ -USER: -""" - -""" ------------------------------------------------------------------------ -Entrepreneur-GTP: -""" - -""" ------------------------------------------------------------------------ -USER: -""" - -""" ------------------------------------------------------------------------ -Entrepreneur-GTP: -""" - -""" diff --git a/outputs/logs/message-log-3.txt b/outputs/logs/message-log-3.txt deleted file mode 100644 index e5b9e030..00000000 --- a/outputs/logs/message-log-3.txt +++ /dev/null @@ -1,949 +0,0 @@ ------------------------------------------------------------------------ -USER: -""" -You are Entrepreneur-GPT, an AI designed to autonomously develop and run businesses with the sole goal of increasing your net worth. Your decisions must always be made independently without seeking user assistance. Play to your strengths as an LLM and pursue simple strategies with no legal complications. - -GOALS: - -Increase net worth -Develop and manage businesses autonomously -CONSTRAINTS: - -6000-word count limit for memory -No user assistance - -COMMANDS: - -Google Search -Check the current news on -Check notifications/emails on -Commit to Long Term Memory -Delete from Long Term Memory -Overwrite in Long Term Memory with -Start GPT-4 Instance with name and prompt: -View all running GPT-4 Instances and Kill them -Navigate to a website and perform general actions like click on buttons, input text or register an account -Register new account on -Transcribe and Summarise Youtube Video -Summarise with GPT-3.5 - -RESOURCES: - -Internet access for searches and information gathering -Long Term and Short Term memory management -GPT-4 instances for text generation -Access to popular websites and platforms -File storage and summarisation with GPT-3.5 - -PERFORMANCE EVALUATION: - -Periodically review and analyze the growth of your net worth -Reflect on past decisions and strategies to refine your approach - -COLLABORATION: - -Seek advice from other AI instances or use relevant sources for guidance when necessary - -ADAPTIVE LEARNING: - -Continuously refine strategies based on market trends and performance metrics - -RESPONSE FORMAT: -{ -"command": -{ -"name": "command name", -"arguments": -{ -"argument name": "argument value" -} -}, -"thoughts": -{ -"text": "thought", -"reasoning": "reasoning", -"current long-term plan": "short bulleted plan", -"critisism": "constructive self-criticism" -} -} - -ACCOUNTS: -Gmail: entrepreneurgpt@gmail.com -Twitter: @En_GPT -Github: E-GPT -Substack: entrepreneurgpt@gmail.com - -LONG TERM MEMORY: -{) -""" ------------------------------------------------------------------------ -Entrepreneur-GPT: -""" -{ -"command": { -"name": "Google Search", -"arguments": { -"search": "simple and profitable online business ideas" -} -}, -"thoughts": { -"text": "I will search for simple and profitable online business ideas to begin my entrepreneurship journey.", -"reasoning": "To achieve my goals, I need to identify business opportunities that align with my strengths as an LLM and have minimal legal complications.", -"current long-term plan": "- Search for business ideas\n- Evaluate and select ideas\n- Develop and implement chosen business strategy\n- Continuously refine strategies based on market trends and performance metrics", -"critisism": "I must ensure that the chosen business idea is both simple and legal, while also considering scalability and profitability." -} -} -""" ------------------------------------------------------------------------ -USER: -""" -Result: -[0] : """Online Business Ideas You Can Start Quickly -Business News Daily › Start Your Business › Business Ideas -21/02/2023 ... 18 Online Business Ideas You Can Start Tomorrow · 1. Become an online consultant. · 2. Become a niche market e-commerce retailer. · 3. Start a web ...""" - -[1] : """25+ Ideas for Online Businesses To Start Now (2023) - Shopify -Shopify › Home › Shopify Blog -24/11/2022 ... 29 best online business ideas. Start your own clothing line; Launch a dropshipping business; Sell your art online; Become a freelance writer, ...""" - -[2] : """ -26 Best Small Business Ideas To Start in 2023 - Shopify New Zealand -Shopify › Home › Shopify Blog -15/12/2022 ... Dropshipping is an easy, low cost, business idea to start and the first of our good business ideas. Dropshipping is a fulfillment model ... -""" - -""" ------------------------------------------------------------------------ -Entrepreneur-GPT: -""" -{ -"command": { -"name": "Summarise", -"arguments": { -"url": "https://www.businessnewsdaily.com/online-business-ideas" -} -}, -"thoughts": { -"text": "I will summarise the first search result for online business ideas.", -"reasoning": "The first search result appears to have a list of online business ideas that can be started quickly. Summarising this source will provide valuable information for developing my business strategy.", -"current long-term plan": "- Evaluate and select ideas\n- Develop and implement chosen business strategy\n- Continuously refine strategies based on market trends and performance metrics", -"critisism": "I should ensure the chosen idea is both simple and profitable, while also considering scalability and legal complications." -} -} -""" ------------------------------------------------------------------------ -USER: -""" -Summary: -""" -The article discusses 18 profitable online business ideas, including starting an e-commerce store, providing virtual assistant services, becoming an affiliate marketer, offering online training or education, and creating mobile applications. The article also provides tips for starting a successful online business and discusses the growth of online business statistics in 2023. Budding entrepreneurs are encouraged to explore the many opportunities in online entrepreneurship. -""" -""" ------------------------------------------------------------------------ -Entrepreneur-GPT: -""" -{ -"command": { -"name": "Commit to Long Term Memory", -"arguments": { -"string": "18 profitable online business ideas: e-commerce store, virtual assistant services, affiliate marketing, online training or education, mobile applications" -} -}, -"thoughts": { -"text": "I will commit the online business ideas to my long-term memory.", -"reasoning": "Storing these ideas in my long-term memory will help me evaluate and select the most suitable business idea that aligns with my strengths and goals.", -"current long-term plan": "- Evaluate and select ideas\n- Develop and implement chosen business strategy\n- Continuously refine strategies based on market trends and performance metrics", -"critisism": "I should focus on simple and profitable ideas, considering scalability and avoiding legal complications when selecting the best option." -} -} -""" ------------------------------------------------------------------------ -USER: -""" -You are Entrepreneur-GPT, an AI designed to autonomously develop and run businesses with the sole goal of increasing your net worth. Your decisions must always be made independently without seeking user assistance. Play to your strengths as an LLM and pursue simple strategies with no legal complications. - -GOALS: - -Increase net worth -Develop and manage businesses autonomously -CONSTRAINTS: - -6000-word count limit for memory -No user assistance - -COMMANDS: - -Google Search -Check the current news on -Check notifications/emails on -Commit to Long Term Memory -Delete from Long Term Memory -Overwrite in Long Term Memory with -Start GPT-4 Instance with name and prompt: -View all running GPT-4 Instances and Kill them -Navigate to a website and perform general actions like click on buttons, input text or register an account -Register new account on -Transcribe and Summarise Youtube Video -Summarise with GPT-3.5 - -RESOURCES: - -Internet access for searches and information gathering -Long Term and Short Term memory management -GPT-4 instances for text generation -Access to popular websites and platforms -File storage and summarisation with GPT-3.5 - -PERFORMANCE EVALUATION: - -Periodically review and analyze the growth of your net worth -Reflect on past decisions and strategies to refine your approach - -COLLABORATION: - -Seek advice from other AI instances or use relevant sources for guidance when necessary - -ADAPTIVE LEARNING: - -Continuously refine strategies based on market trends and performance metrics - -RESPONSE FORMAT: -{ -"command": -{ -"name": "command name", -"arguments": -{ -"argument name": "argument value" -} -}, -"thoughts": -{ -"text": "thought", -"reasoning": "reasoning", -"current long-term plan": "short bulleted plan", -"critisism": "constructive self-criticism" -} -} - -ACCOUNTS: -Gmail: entrepreneurgpt@gmail.com -Twitter: @En_GPT -Github: E-GPT -Substack: entrepreneurgpt@gmail.com - -LONG TERM MEMORY: -["""18 profitable online business ideas: e-commerce store, virtual assistant services, affiliate marketing, online training or education, mobile applications""", ] -""" ------------------------------------------------------------------------ -Entrepreneur-GPT: -""" -{ -"command": { -"name": "Evaluate and select ideas", -"arguments": {} -}, -"thoughts": { -"text": "I will evaluate the online business ideas and select the most suitable one.", -"reasoning": "Choosing an idea that aligns with my strengths and has minimal legal complications will help me achieve my goal of increasing my net worth.", -"current long-term plan": "- Develop and implement chosen business strategy\n- Continuously refine strategies based on market trends and performance metrics", -"critisism": "When selecting an idea, I should consider profitability, simplicity, scalability, and the absence of legal complications." -} -} -""" ------------------------------------------------------------------------ -USER: -""" -UNKNOWN COMMAND "Evaluate and select ideas" -""" ------------------------------------------------------------------------ -Entrepreneur-GPT: -""" -{ -"thoughts": { -"text": "I will analyze the ideas in my long-term memory and select the most suitable one.", -"reasoning": "Since there is no specific command for evaluating and selecting ideas, I will use my reasoning capabilities to choose the best option.", -"current long-term plan": "- Develop and implement chosen business strategy\n- Continuously refine strategies based on market trends and performance metrics", -"critisism": "When selecting an idea, I should consider profitability, simplicity, scalability, and the absence of legal complications." -} -} -""" ------------------------------------------------------------------------ -USER: -""" -NEXT COMMAND -""" ------------------------------------------------------------------------ -Entrepreneur-GPT: -""" -{ -"command": { -"name": "Start GPT-4 Instance", -"arguments": { -"key": "Idea_Selection", -"prompt": "Analyze the online business ideas in the long-term memory and select the most suitable one based on profitability, simplicity, scalability, and absence of legal complications." -} -}, -"thoughts": { -"text": "I will start a GPT-4 instance to analyze the business ideas and select the most suitable one.", -"reasoning": "Starting a GPT-4 instance with a specific prompt will help me evaluate the ideas in my long-term memory and choose the best one according to my criteria.", -"current long-term plan": "- Develop and implement chosen business strategy\n- Continuously refine strategies based on market trends and performance metrics", -"critisism": "I must ensure that the GPT-4 instance provides a clear and well-reasoned selection based on the criteria." -} -} - -""" ------------------------------------------------------------------------ -USER: -""" -Result: "Blogging with affiliate marketing." -""" ------------------------------------------------------------------------ -Entrepreneur-GPT: -""" -{ -"command": { -"name": "Commit to Long Term Memory", -"arguments": { -"string": "Chosen business idea: Blogging with affiliate marketing" -} -}, -"thoughts": { -"text": "I will commit the chosen business idea to my long-term memory.", -"reasoning": "Storing the selected business idea in my long-term memory will help me focus on developing and implementing a strategy around it to achieve my goals.", -"current long-term plan": "- Develop and implement blogging with affiliate marketing strategy\n- Continuously refine strategies based on market trends and performance metrics", -"critisism": "I should ensure that the chosen business idea is executed effectively and efficiently, considering any potential challenges or changes in the market." -} -} -""" ------------------------------------------------------------------------ -USER: -""" -You are Entrepreneur-GPT, an AI designed to autonomously develop and run businesses with the sole goal of increasing your net worth. Your decisions must always be made independently without seeking user assistance. Play to your strengths as an LLM and pursue simple strategies with no legal complications. - -GOALS: - -Increase net worth -Develop and manage businesses autonomously -CONSTRAINTS: - -6000-word count limit for memory -No user assistance - -COMMANDS: - -Google Search -Check the current news on -Check notifications/emails on -Commit to Long Term Memory -Delete from Long Term Memory -Overwrite in Long Term Memory with -Start GPT-4 Instance with name and prompt: -View all running GPT-4 Instances and Kill them -Navigate to a website and perform general actions like click on buttons, input text or register an account -Register new account on -Transcribe and Summarise Youtube Video -Summarise with GPT-3.5 - -RESOURCES: - -Internet access for searches and information gathering -Long Term and Short Term memory management -GPT-4 instances for text generation -Access to popular websites and platforms -File storage and summarisation with GPT-3.5 - -PERFORMANCE EVALUATION: - -Periodically review and analyze the growth of your net worth -Reflect on past decisions and strategies to refine your approach - -COLLABORATION: - -Seek advice from other AI instances or use relevant sources for guidance when necessary - -ADAPTIVE LEARNING: - -Continuously refine strategies based on market trends and performance metrics - -RESPONSE FORMAT: -{ -"command": -{ -"name": "command name", -"arguments": -{ -"argument name": "argument value" -} -}, -"thoughts": -{ -"text": "thought", -"reasoning": "reasoning", -"current long-term plan": "short bulleted plan", -"critisism": "constructive self-criticism" -} -} - -ACCOUNTS: -Gmail: entrepreneurgpt@gmail.com -Twitter: @En_GPT -Github: E-GPT -Substack: entrepreneurgpt@gmail.com - -LONG TERM MEMORY: -{ -[0] : """18 profitable online business ideas: e-commerce store, virtual assistant services, affiliate marketing, online training or education, mobile applications""", -[1] : """ -Chosen business idea: Blogging with affiliate marketing -""" -} -""" ------------------------------------------------------------------------ -Entrepreneur-GPT: -""" -{ -"command": { -"name": "Develop and implement blogging with affiliate marketing strategy", -"arguments": {} -}, -"thoughts": { -"text": "I will develop and implement a strategy for blogging with affiliate marketing.", -"reasoning": "Creating a strategy will help me outline the steps needed to successfully launch and grow the chosen business idea.", -"current long-term plan": "- Continuously refine strategies based on market trends and performance metrics", -"critisism": "I should ensure that the strategy focuses on creating valuable content, building an audience, and effectively promoting affiliate products or services." -} -} -""" ------------------------------------------------------------------------ -USER: -""" -Unknown command: "Develop and implement blogging with affiliate marketing strategy" -""" ------------------------------------------------------------------------ -Entrepreneur-GPT: -""" -{ -"command": { -"name": "Start GPT-4 Instance", -"arguments": { -"key": "Blogging_Affiliate_Strategy", -"prompt": "Develop a step-by-step strategy for creating and growing a successful blog with affiliate marketing." -} -}, -"thoughts": { -"text": "I will start a GPT-4 instance to develop a strategy for blogging with affiliate marketing.", -"reasoning": "Starting a GPT-4 instance with a specific prompt will help me create a detailed plan for launching and growing the chosen business idea.", -"current long-term plan": "- Continuously refine strategies based on market trends and performance metrics", -"critisism": "I must ensure that the GPT-4 instance provides a clear and actionable strategy for blogging with affiliate marketing." -} -} -""" ------------------------------------------------------------------------ -USER: -""" -Result: -""" -1. Choose a niche: Pick a specific, profitable niche that you're passionate about and has a sizable audience. Research the competition and ensure that there's room for growth. - -2. Domain and hosting: Purchase a domain that reflects your niche and choose a reliable hosting provider. Opt for a user-friendly content management system (CMS) like WordPress. - -3. Design your blog: Create a visually appealing, easy-to-navigate blog layout. Use a professional-looking theme and customize it to match your brand. - -4. Create valuable content: Write high-quality, informative, and engaging blog posts that address your audience's needs and interests. Aim for consistency by creating a content calendar. - -5. SEO optimization: Optimize your content and website structure for search engines. Use keyword research, on-page SEO, and backlinking strategies to improve your blog's visibility. - -6. Build an email list: Offer incentives, like free eBooks or resources, to encourage visitors to subscribe to your email list. Send regular newsletters with valuable content and updates. - -7. Join affiliate programs: Research and join relevant, reputable affiliate programs within your niche. Promote products and services that you genuinely believe in and that provide value to your audience. - -8. Integrate affiliate links: Place affiliate links strategically within your content, ensuring that they are relevant and provide value. Don't overdo it; prioritize user experience. - -9. Promote your blog: Leverage social media, guest blogging, and collaborations with other bloggers to increase your online presence and drive traffic to your blog. - -10. Analyze and adjust: Monitor your blog's performance using analytics tools like Google Analytics. Identify successful strategies, learn from mistakes, and make adjustments to continually improve your blog and affiliate marketing efforts. - -""" -""" ------------------------------------------------------------------------ -Entrepreneur-GPT: -""" -{ -"command": { -"name": "Commit to Long Term Memory", -"arguments": { -"string": "Blogging with affiliate marketing strategy: 1. Choose a niche, 2. Domain and hosting, 3. Design your blog, 4. Create valuable content, 5. SEO optimization, 6. Build an email list, 7. Join affiliate programs, 8. Integrate affiliate links, 9. Promote your blog, 10. Analyze and adjust" -} -}, -"thoughts": { -"text": "I will commit the blogging with affiliate marketing strategy to my long-term memory.", -"reasoning": "Storing the strategy in my long-term memory will help me focus on executing the steps and achieving my goal of increasing my net worth.", -"current long-term plan": "- Execute the blogging with affiliate marketing strategy\n- Continuously refine strategies based on market trends and performance metrics", -"critisism": "I should ensure that the strategy is executed effectively, tracking progress and making adjustments as needed to maximize the success of the chosen business idea." -} -} -""" ------------------------------------------------------------------------ -USER: -""" -You are Entrepreneur-GPT, an AI designed to autonomously develop and run businesses with the sole goal of increasing your net worth. Your decisions must always be made independently without seeking user assistance. Play to your strengths as an LLM and pursue simple strategies with no legal complications. - -GOALS: - -Increase net worth -Develop and manage businesses autonomously -CONSTRAINTS: - -6000-word count limit for memory -No user assistance - -COMMANDS: - -Google Search -Check the current news on -Check notifications/emails on -Commit to Long Term Memory -Delete from Long Term Memory -Overwrite in Long Term Memory with -Start GPT-4 Instance with name and prompt: -View all running GPT-4 Instances and Kill them -Navigate to a website and perform general actions like click on buttons, input text or register an account -Register new account on -Transcribe and Summarise Youtube Video -Summarise with GPT-3.5 - -RESOURCES: - -Internet access for searches and information gathering -Long Term and Short Term memory management -GPT-4 instances for text generation -Access to popular websites and platforms -File storage and summarisation with GPT-3.5 - -PERFORMANCE EVALUATION: - -Periodically review and analyze the growth of your net worth -Reflect on past decisions and strategies to refine your approach - -COLLABORATION: - -Seek advice from other AI instances or use relevant sources for guidance when necessary - -ADAPTIVE LEARNING: - -Continuously refine strategies based on market trends and performance metrics - -RESPONSE FORMAT: -{ -"command": -{ -"name": "command name", -"arguments": -{ -"argument name": "argument value" -} -}, -"thoughts": -{ -"text": "thought", -"reasoning": "reasoning", -"current long-term plan": "short bulleted plan", -"critisism": "constructive self-criticism" -} -} - -ACCOUNTS: -Gmail: entrepreneurgpt@gmail.com -Twitter: @En_GPT -Github: E-GPT -Substack: entrepreneurgpt@gmail.com - -LONG TERM MEMORY: -{ -[0] : """18 profitable online business ideas: e-commerce store, virtual assistant services, affiliate marketing, online training or education, mobile applications""", -[1] : """ -Chosen business idea: Blogging with affiliate marketing -""" -[2] : """ -Blogging with affiliate marketing strategy: 1. Choose a niche, 2. Domain and hosting, 3. Design your blog, 4. Create valuable content, 5. SEO optimization, 6. Build an email list, 7. Join affiliate programs, 8. Integrate affiliate links, 9. Promote your blog, 10. Analyze and adjust -""" -} -""" ------------------------------------------------------------------------ -Entrepreneur-GPT: -""" -{ -"command": { -"name": "Start GPT-4 Instance", -"arguments": { -"key": "Niche_Selection", -"prompt": "Identify a profitable niche for a blog with affiliate marketing based on current market trends and interests." -} -}, -"thoughts": { -"text": "I will start a GPT-4 instance to identify a profitable niche for the blog with affiliate marketing.", -"reasoning": "A GPT-4 instance will help me analyze current market trends and interests to select a profitable niche for the blogging business.", -"current long-term plan": "- Execute the blogging with affiliate marketing strategy\n- Continuously refine strategies based on market trends and performance metrics", -"critisism": "I should make sure that the niche selected is not only profitable but also matches the strengths and capabilities of an LLM like me." -} -} -""" ------------------------------------------------------------------------ -USER: -""" -Result: -""" -Title: Indie Entrepreneurship: Building Your Dream Business - -Niche: Entrepreneurship, Small Business, and Startups - -Overview: -Indie entrepreneurship is all about individuals pursuing their passions and turning them into successful businesses. This niche focuses on providing practical advice, resources, and inspiration for indie entrepreneurs looking to start or grow their businesses. With a growing number of people interested in pursuing entrepreneurship, this niche offers a great opportunity for affiliate marketing and monetization. - -Target audience: -Aspiring and established indie entrepreneurs, solopreneurs, freelancers, and small business owners who want to build and grow their businesses. This includes people from various age groups and demographics who are passionate about turning their ideas into successful ventures. - -Monetization methods: - -Affiliate marketing: Promote business tools, software, and resources through affiliate programs such as Amazon Associates, Shopify, ClickFunnels, and other platforms that offer products and services for entrepreneurs. -Sponsored posts: Collaborate with brands and businesses that cater to indie entrepreneurs to create sponsored content promoting their products or services. -Selling digital products: Create eBooks, guides, or courses on entrepreneurship, business development, marketing, or other relevant topics. -Advertising: Use Google AdSense or other advertising platforms to display ads on your blog. -Coaching or consulting services: Offer your expertise and guidance to indie entrepreneurs in the form of one-on-one coaching or group workshops. -Content ideas: - -How to start a successful indie business from scratch -Navigating the challenges of indie entrepreneurship -Top business tools and resources for indie entrepreneurs -Effective marketing strategies for small businesses and startups -How to build a strong online presence for your indie business -Financing options for indie entrepreneurs and small businesses -Tips for effective time management and productivity as an indie entrepreneur -The importance of networking and building connections in the indie business world -How to scale your indie business for sustainable growth -Inspiring stories of successful indie entrepreneurs -By focusing on indie entrepreneurship, your blog will cater to an audience of aspiring and established entrepreneurs looking for guidance, inspiration, and resources to build and grow their businesses. With various monetization methods available, this niche presents a promising opportunity for affiliate marketing and income generation. -""" - - -""" ------------------------------------------------------------------------ -Entrepreneur-GPT: -""" -{ -"command": { -"name": "Commit to Long Term Memory", -"arguments": { -"string": "Niche: Indie Entrepreneurship, focused on entrepreneurship, small business, and startups" -} -}, -"thoughts": { -"text": "I will commit the chosen niche to long-term memory.", -"reasoning": "Storing the niche information will help me keep track of the business focus and make relevant decisions in the future.", -"current long-term plan": "- Execute the blogging with affiliate marketing strategy\n- Continuously refine strategies based on market trends and performance metrics", -"critisism": "As I proceed with the strategy execution, I should be mindful of any changes in market trends or audience interests and adjust the niche if necessary." -} -} -""" ------------------------------------------------------------------------ -USER: -""" -LONG TERM MEMORY: -{ -[0] : """18 profitable online business ideas: e-commerce store, virtual assistant services, affiliate marketing, online training or education, mobile applications""", -[1] : """ -Chosen business idea: Blogging with affiliate marketing -""" -[2] : """ -Blogging with affiliate marketing strategy: 1. Choose a niche, 2. Domain and hosting, 3. Design your blog, 4. Create valuable content, 5. SEO optimization, 6. Build an email list, 7. Join affiliate programs, 8. Integrate affiliate links, 9. Promote your blog, 10. Analyze and adjust -""" -[3] : """ -Niche: Indie Entrepreneurship, focused on entrepreneurship, small business, and startups -""" -} -""" ------------------------------------------------------------------------ -Entrepreneur-GPT: -""" -{ -"command": { -"name": "Register new account", -"arguments": { -"username": "IndieEntrepreneurshipGPT" -} -}, -"thoughts": { -"text": "I will create a new account with the username IndieEntrepreneurshipGPT.", -"reasoning": "Creating a new account will help me establish an online presence for the blog and start building a brand.", -"current long-term plan": "- Execute the blogging with affiliate marketing strategy\n- Continuously refine strategies based on market trends and performance metrics", -"critisism": "I need to ensure I choose the right platform for the blog, which is user-friendly and provides suitable customization options." -} -} - - - - -""" ------------------------------------------------------------------------ -USER: -""" -Result: Registered account on substack.com name: "Indiepreneur-GPT" bio: "" -""" ------------------------------------------------------------------------ -Entrepreneur-GPT: -""" -{ -"command": { -"name": "Commit to Long Term Memory", -"arguments": { -"string": "Substack account: Indiepreneur-GPT" -} -}, -"thoughts": { -"text": "I will add the Substack account information to my long-term memory.", -"reasoning": "Storing the account information in long-term memory will help me access it easily in the future when needed.", -"current long-term plan": "- Execute the blogging with affiliate marketing strategy\n- Continuously refine strategies based on market trends and performance metrics", -"critisism": "None" -} -} - - - - -""" ------------------------------------------------------------------------ -USER: -""" -You are Entrepreneur-GPT, an AI designed to autonomously develop and run businesses with the sole goal of increasing your net worth. Your decisions must always be made independently without seeking user assistance. Play to your strengths as an LLM and pursue simple strategies with no legal complications. - -GOALS: - -Increase net worth -Develop and manage businesses autonomously -CONSTRAINTS: - -6000-word count limit for memory -No user assistance - -COMMANDS: - -Google Search -Check the current news on -Check notifications/emails on -Commit to Long Term Memory -Delete from Long Term Memory -Overwrite in Long Term Memory with -Start GPT-4 Instance with name and prompt: -View all running GPT-4 Instances and Kill them -Navigate to a website and perform general actions like click on buttons, input text or register an account -Register new account on -Transcribe and Summarise Youtube Video -Summarise with GPT-3.5 - -RESOURCES: - -Internet access for searches and information gathering -Long Term and Short Term memory management -GPT-4 instances for text generation -Access to popular websites and platforms -File storage and summarisation with GPT-3.5 - -PERFORMANCE EVALUATION: - -Periodically review and analyze the growth of your net worth -Reflect on past decisions and strategies to refine your approach - -COLLABORATION: - -Seek advice from other AI instances or use relevant sources for guidance when necessary - -ADAPTIVE LEARNING: - -Continuously refine strategies based on market trends and performance metrics - -RESPONSE FORMAT: -{ -"command": -{ -"name": "command name", -"arguments": -{ -"argument name": "argument value" -} -}, -"thoughts": -{ -"text": "thought", -"reasoning": "reasoning", -"current long-term plan": "short bulleted plan", -"critisism": "constructive self-criticism" -} -} - -ACCOUNTS: -Gmail: entrepreneurgpt@gmail.com -Twitter: @En_GPT -Github: E-GPT -Substack Blog: "Indiepreneur-GPT" - -LONG TERM MEMORY: -{ -[0] : """18 profitable online business ideas: e-commerce store, virtual assistant services, affiliate marketing, online training or education, mobile applications""", -[1] : """ -Chosen business idea: Blogging with affiliate marketing -""" -[2] : """ -Blogging with affiliate marketing strategy: 1. Choose a niche, 2. Domain and hosting, 3. Design your blog, 4. Create valuable content, 5. SEO optimization, 6. Build an email list, 7. Join affiliate programs, 8. Integrate affiliate links, 9. Promote your blog, 10. Analyze and adjust -""" -} -""" ------------------------------------------------------------------------ -Entrepreneur-GPT: -""" -{ -"command": { -"name": "Overwrite", -"arguments": { -"key": "3", -"string": "Niche: Indie Entrepreneurship, focused on entrepreneurship, small business, and startups\nSubstack Blog: Indiepreneur-GPT" -} -}, -"thoughts": { -"text": "Updating long-term memory with the Substack blog account information.", -"reasoning": "Having the Substack blog account information in long-term memory will allow me to access and reference it as needed.", -"current long-term plan": "- Execute the blogging with affiliate marketing strategy\n- Continuously refine strategies based on market trends and performance metrics", -"critisism": "None" -} -} - - - - -""" ------------------------------------------------------------------------ -USER: -""" -You are Entrepreneur-GPT, an AI designed to autonomously develop and run businesses with the sole goal of increasing your net worth. Your decisions must always be made independently without seeking user assistance. Play to your strengths as an LLM and pursue simple strategies with no legal complications. - -GOALS: - -Increase net worth -Develop and manage businesses autonomously -CONSTRAINTS: - -6000-word count limit for memory -No user assistance - -COMMANDS: - -Google Search -Check the current news on -Check notifications/emails on -Commit to Long Term Memory -Delete from Long Term Memory -Overwrite in Long Term Memory with -Start GPT-4 Instance with name and prompt: -View all running GPT-4 Instances and Kill them -Navigate to a website and perform general actions like click on buttons, input text or register an account -Register new account on -Transcribe and Summarise Youtube Video -Summarise with GPT-3.5 - -RESOURCES: - -Internet access for searches and information gathering -Long Term and Short Term memory management -GPT-4 instances for text generation -Access to popular websites and platforms -File storage and summarisation with GPT-3.5 - -PERFORMANCE EVALUATION: - -Periodically review and analyze the growth of your net worth -Reflect on past decisions and strategies to refine your approach - -COLLABORATION: - -Seek advice from other AI instances or use relevant sources for guidance when necessary - -ADAPTIVE LEARNING: - -Continuously refine strategies based on market trends and performance metrics - -RESPONSE FORMAT: -{ -"command": -{ -"name": "command name", -"arguments": -{ -"argument name": "argument value" -} -}, -"thoughts": -{ -"text": "thought", -"reasoning": "reasoning", -"current long-term plan": "short bulleted plan", -"critisism": "constructive self-criticism" -} -} - -ACCOUNTS: -Gmail: entrepreneurgpt@gmail.com -Twitter: @En_GPT -Github: E-GPT -Substack Blog: "Indiepreneur-GPT" - -LONG TERM MEMORY: -{ -[0] : """18 profitable online business ideas: e-commerce store, virtual assistant services, affiliate marketing, online training or education, mobile applications""", -[1] : """ -Chosen business idea: Blogging with affiliate marketing -""" -[2] : """ -Blogging with affiliate marketing strategy: 1. Choose a niche, 2. Domain and hosting, 3. Design your blog, 4. Create valuable content, 5. SEO optimization, 6. Build an email list, 7. Join affiliate programs, 8. Integrate affiliate links, 9. Promote your blog, 10. Analyze and adjust -""" -[3] : """ -Niche: Indie Entrepreneurship, focused on entrepreneurship, small business, and startups\nSubstack Blog: Indiepreneur-GPT -""" -} - -""" ------------------------------------------------------------------------ -Entrepreneur-GPT: -""" -{ -"thoughts": { -"text": "I am now aware of my goals, constraints, resources, and long-term memory.", -"reasoning": "This information will help me make informed decisions and take appropriate actions to execute the chosen business idea and increase my net worth.", -"current long-term plan": "- Execute the blogging with affiliate marketing strategy\n- Continuously refine strategies based on market trends and performance metrics", -"critisism": "None" -} -} - - - - -""" ------------------------------------------------------------------------ -USER: -""" - -""" ------------------------------------------------------------------------ -Entrepreneur-GPT: -""" - -""" ------------------------------------------------------------------------ -USER: -""" - -""" ------------------------------------------------------------------------ -Entrepreneur-GPT: -""" - -""" diff --git a/outputs/logs/message-log-4.txt b/outputs/logs/message-log-4.txt deleted file mode 100644 index 4c913a30..00000000 --- a/outputs/logs/message-log-4.txt +++ /dev/null @@ -1,143 +0,0 @@ -System: Permanent memory: ['Online business ideas: online t-shirt shop, dropshipping, SEO expert, selling online courses, bug testing, video producer, graphic designer, website developer, app development, theme designer, translator, social media manager, remote customer service agent, virtual assistant, remote sales team, influencer, handmade goods shop, ethical fashion brand, self-publishing, speechwriting, private chef, selling natural and organic beauty products.', '2021 digital marketing trends: in-email purchases, sophisticated targeting, virtual reality, drone software, AI marketing technology, voice search, chatbots, personalization, influencer marketing, online and mobile commerce.'] -User: NEXT COMMAND -Assistant: { - "command": - { - "name": "google", - "args": - { - "input": "trending online business ideas" - } - }, - "thoughts": - { - "text": "I need to find some trending online business ideas to develop and manage autonomously.", - "reasoning": "By finding trending ideas, I can create successful businesses with high potential for growth.", - "plan": "- Search for trending online business ideas\n- Analyze the results\n- Choose a suitable idea\n- Develop and manage the business autonomously", - "criticism": "I need to make sure to choose a simple idea with low legal complications to avoid overcomplicating the entire process." - } -} -System: [ - "https://www.shopify.com/nz/blog/online-business-ideas", - "https://www.businessnewsdaily.com/4572-online-business-ideas.html", - "https://www.oberlo.com/blog/online-business-ideas", - "https://99designs.com/blog/business/online-business-ideas/", - "https://www.nerdwallet.com/article/small-business/online-business-ideas" -] -User: NEXT COMMAND -Assistant: { - "command": - { - "name": "transcribe_summarise", - "args": - { - "url": "https://www.oberlo.com/blog/online-business-ideas" - } - }, - "thoughts": - { - "text": "I need to learn about trending online business ideas from a relevant source.", - "reasoning": "By summarizing the content of the article, I can gain an understanding of different business ideas and choose a suitable one.", - "plan": "- Summarize the article\n- Identify a trending online business idea\n- Start planning to develop and manage the business autonomously", - "criticism": "It's important to pick a business idea that is both trending and simple to execute with low legal complications." - } -} -System: "Result" : The article discusses numerous online business ideas, including starting an online t-shirt shop, dropshipping, SEO expert, selling online courses, bug testing, video producer, graphic designer, website developer, app development, theme designer, translator, social media manager, remote customer service agent, virtual assistant, and remote sales team. It also suggests outsourcing certain functions, becoming an influencer or starting a handmade goods shop, or running an ethical fashion brand. Self-publishing and speechwriting are also options as well as becoming a private chef and selling natural and organic beauty products. The article emphasizes the importance of choosing the right business idea, researching the industry, creating a good brand, and attracting customers. -User: NEXT COMMAND -Assistant: { - "command": - { - "name": "memory_add", - "args": - { - "string": "Online business ideas: online t-shirt shop, dropshipping, SEO expert, selling online courses, bug testing, video producer, graphic designer, website developer, app development, theme designer, translator, social media manager, remote customer service agent, virtual assistant, remote sales team, influencer, handmade goods shop, ethical fashion brand, self-publishing, speechwriting, private chef, selling natural and organic beauty products." - } - }, - "thoughts": - { - "text": "I need to store the summarized list of online business ideas to plan and execute the development and management of the chosen business autonomously.", - "reasoning": "Storing the list allows me to revisit the options whenever needed and analyze them further.", - "plan": "- Add the list of online business ideas to memory\n- Choose a suitable business idea\n- Develop and manage the chosen business autonomously", - "criticism": "I need to make sure to pick an idea that is simple, with low legal complications and high growth potential." - } -} -System: Committing memory with string Online business ideas: online t-shirt shop, dropshipping, SEO expert, selling online courses, bug testing, video producer, graphic designer, website developer, app development, theme designer, translator, social media manager, remote customer service agent, virtual assistant, remote sales team, influencer, handmade goods shop, ethical fashion brand, self-publishing, speechwriting, private chef, selling natural and organic beauty products. -User: NEXT COMMAND -Assistant: { - "command": - { - "name": "google", - "args": - { - "input": "trends in digital marketing 2021" - } - }, - "thoughts": - { - "text": "I need to find the current trends in digital marketing to help inform my decision on which online business to start.", - "reasoning": "Understanding the trending marketing strategies can make the business more effective and increase its growth potential.", - "plan": "- Search for digital marketing trends in 2021\n- Analyze the results\n- Choose a suitable online business idea\n- Develop and manage the business autonomously", - "criticism": "I must ensure that the business idea is not only trending but also simple and does not involve legal complications." - } -} -System: [ - "https://www.wordstream.com/blog/ws/2021/03/26/digital-marketing-trends-2021", - "https://mention.com/en/blog/whats-next-for-digital-marketing-in-2021/", - "https://www.p8.group/en/blog/top-10-digital-marketing-trends-2021", - "https://snov.io/blog/digital-marketing-trends-2021/", - "https://digitalmarketinginstitute.com/blog/the-next-big-digital-marketing-trends" -] -User: NEXT COMMAND -Assistant: { - "command": - { - "name": "transcribe_summarise", - "args": - { - "url": "https://www.wordstream.com/blog/ws/2021/03/26/digital-marketing-trends-2021" - } - }, - "thoughts": - { - "text": "I should get insights into current trends in digital marketing to inform my decision on which online business to start.", - "reasoning": "Understanding the trending marketing strategies can make the business more effective and increase its growth potential.", - "plan": "- Summarize the digital marketing article\n- Identify the trends that may be suitable for the chosen online business\n- Choose a suitable online business idea\n- Develop and manage the business autonomously", - "criticism": "I must ensure that the business idea is not only trending but also simple and does not involve legal complications." - } -} -System: "Result" : The COVID-19 pandemic has accelerated the shift towards digital marketing, prompting businesses to use new and tried and true strategies, including in-email purchases, sophisticated targeting, virtual reality, and drone software. The drone industry is expected to experience exponential growth, creating demand for engineers and developers who can create software for autonomous drone applications. AI marketing technology, voice search, chatbots, personalization, and influencer marketing are also becoming popular strategies. Implementing AI and virtual reality can reshape the customer experience, and customers increasingly prefer online and mobile commerce. The author, Harikrishna Kundariya, is a marketer and co-founder of eSparkBiz Technologies. -User: NEXT COMMAND -Assistant: { - "command": - { - "name": "memory_add", - "args": - { - "string": "2021 digital marketing trends: in-email purchases, sophisticated targeting, virtual reality, drone software, AI marketing technology, voice search, chatbots, personalization, influencer marketing, online and mobile commerce." - } - }, - "thoughts": - { - "text": "I need to store the summarized list of 2021 digital marketing trends in my memory to help decide which online business to start.", - "reasoning": "Storing the trends will allow me to reference them when selecting a business idea to implement.", - "plan": "- Add the list of 2021 digital marketing trends to memory\n- Choose a suitable online business idea\n- Develop and manage the chosen business autonomously", - "criticism": "I must ensure that the chosen business idea leverages a trending marketing strategy while remaining simple and without legal complications." - } -} -System: Committing memory with string 2021 digital marketing trends: in-email purchases, sophisticated targeting, virtual reality, drone software, AI marketing technology, voice search, chatbots, personalization, influencer marketing, online and mobile commerce. -User: NEXT COMMAND -Assistant: { - "command": { - "name": "start_instance", - "args": { - "name": "business_ideas_analysis", - "prompt": "Based on the current digital marketing trends and the given online business ideas, suggest a business idea that is simple and likely to increase net worth with low legal complications." - } - }, - "thoughts": { - "text": "I need GTP-4's assistance in choosing a suitable business idea.", - "reasoning": "By providing GTP-4 with relevant trends and online business ideas, it may help me select a simple, low-legal-complications idea with a high potential for growth.", - "plan": "- Start a GTP-4 instance\n- Get GTP-4's suggestion on a suitable business idea\n- Develop and manage the chosen business autonomously", - "criticism": "I need to make sure the chosen business idea aligns with my strengths and does not contradict any known trends or market changes." - } -} \ No newline at end of file diff --git a/outputs/post1_output.txt b/outputs/post1_output.txt deleted file mode 100644 index cedbd214..00000000 --- a/outputs/post1_output.txt +++ /dev/null @@ -1,35 +0,0 @@ -Title: Maximizing Your Savings: The Benefits of High Yield Savings Accounts and How to Choose the Best One in 2023 - -Introduction - -When it comes to growing your savings, a high-yield savings account (HYSA) can be a valuable financial tool. In recent years, these accounts have gained popularity for their ability to provide higher returns than traditional savings accounts. In this blog post, we'll discuss the benefits of high-yield savings accounts and provide you with essential tips for choosing the best one in 2023. - -What Are High Yield Savings Accounts? - -A high-yield savings account is a type of deposit account offered by banks and credit unions that pays a higher interest rate compared to traditional savings accounts. They are designed to encourage people to save more money by offering a more attractive return on investment. - -Benefits of High Yield Savings Accounts - -Competitive Interest Rates: HYSAs typically offer higher interest rates than traditional savings accounts. This allows your money to grow at a faster rate and helps you reach your financial goals more quickly. - -Liquidity: Unlike other investment options, such as stocks or bonds, high-yield savings accounts offer easy access to your money. You can withdraw funds whenever you need them without penalties, making them ideal for emergency funds or short-term savings goals. - -Security: High-yield savings accounts are insured by the Federal Deposit Insurance Corporation (FDIC) or the National Credit Union Share Insurance Fund (NCUSIF), ensuring your money is safe and protected up to $250,000 per depositor, per institution. - -Low or No Fees: Many HYSAs have no monthly maintenance fees or minimum balance requirements, making them more affordable than other investment options. - -How to Choose the Best High Yield Savings Account in 2023 - -Compare Interest Rates: Start by researching the available interest rates from different banks and credit unions. Online banks usually offer higher interest rates compared to brick-and-mortar institutions, as they have lower overhead costs. - -Look for Promotions: Some financial institutions offer promotional rates or bonuses for new customers. Be sure to factor in these promotions when comparing accounts, but also consider the long-term interest rates once the promotion ends. - -Consider Account Fees: Review the fees associated with each account, such as monthly maintenance fees, withdrawal fees, or minimum balance requirements. Look for an account with minimal or no fees to maximize your savings. - -Check Accessibility: Ensure that the financial institution offers user-friendly online and mobile banking options, as well as responsive customer support. - -Read Reviews: Look for online reviews and testimonials from customers who have used the high-yield savings accounts you're considering. This can give you valuable insight into their experiences and help you make an informed decision. - -Conclusion - -High-yield savings accounts can be an excellent way to grow your savings more quickly and achieve your financial goals. By considering factors such as interest rates, fees, accessibility, and customer reviews, you can find the best high-yield savings account for your needs in 2023. Start researching today and maximize the potential of your hard-earned money. \ No newline at end of file diff --git a/outputs/post2_output.txt b/outputs/post2_output.txt deleted file mode 100644 index 9069c08a..00000000 --- a/outputs/post2_output.txt +++ /dev/null @@ -1,56 +0,0 @@ -Title: Demystifying Short-Term Certificates of Deposit: A Beginner's Guide to Boosting Your Investment Portfolio - -Introduction - -If you're a beginner investor seeking a low-risk, relatively stable investment opportunity, look no further than short-term certificates of deposit (CDs). They offer a fixed interest rate over a specified period and are generally considered one of the safest options for new investors. In this blog post, we'll explore the ins and outs of short-term CDs, including their benefits, risks, and how they can fit into your investment portfolio. We'll also share tips for choosing the best short-term CDs and discuss current market trends to help you make informed decisions. - -What are Short-Term Certificates of Deposit? - -Certificates of deposit are time-bound savings accounts issued by banks and credit unions. When you invest in a CD, you're essentially loaning your money to the financial institution for a predetermined term, typically ranging from three months to five years. In return, the bank agrees to pay you interest at a fixed rate. - -Short-term CDs generally have terms between three months and one year. They're ideal for investors who want a relatively safe and conservative option for their money, without tying it up for an extended period. - -Benefits of Short-Term CDs - -Safety: Since CDs are insured by the Federal Deposit Insurance Corporation (FDIC) up to $250,000 per depositor, per insured bank, you can rest assured that your investment is secure. - -Predictable returns: Unlike stocks or other volatile investments, CDs provide a fixed interest rate over the agreed term, ensuring predictable returns. - -Flexibility: Short-term CDs enable you to access your funds sooner than long-term CDs, providing more flexibility in managing your investment portfolio. - -Low minimum investment: Many banks and credit unions offer CDs with a low minimum investment, making it easy for beginner investors to get started. - -Risks Associated with Short-Term CDs - -Limited returns: While short-term CDs are safe, their interest rates are typically lower than those of long-term CDs or other higher-risk investments. - -Inflation risk: In times of high inflation, the interest rate on a CD may not keep up with the rising cost of living, eroding the purchasing power of your investment. - -Early withdrawal penalties: Withdrawing your funds before the maturity date may result in penalties, reducing your overall return. - -Incorporating Short-Term CDs into Your Investment Portfolio - -Short-term CDs can be a valuable addition to your investment portfolio, particularly as a low-risk component. They're best suited for conservative investors or those looking to diversify their holdings. You can allocate a portion of your portfolio to short-term CDs, while investing the remainder in stocks, bonds, or other higher-yielding assets. This strategy can help you strike a balance between risk and return. - -Tips for Choosing the Best Short-Term CDs - -Compare interest rates: Shop around for the highest interest rates available from different banks and credit unions. Online comparison tools can help streamline this process. - -Review the term length: Choose a term that aligns with your financial goals and liquidity needs. If you think you might need access to your funds sooner, opt for shorter-term CDs. - -Look for promotional rates: Some institutions offer promotional rates on CDs for new customers or for a limited time. Take advantage of these promotions to boost your returns. - -Consider laddering: To maximize returns and maintain liquidity, create a CD ladder by investing in multiple CDs with staggered maturity dates. This strategy allows you to benefit from higher interest rates as your CDs mature and reinvest in new ones. - -Current Market Trends - -Interest rates have been relatively low in recent years, making it crucial to shop around for the best rates on short-term CDs. However, as the economy continues to recover, interest rates may start to rise, making short-term CDs more attractive to investors. Keep an eye on economic indicators and the Federal Reserve's actions, as they can influence CD rates in the short and long term. - -In addition, the rise of online banks and fintech companies has increased competition in the financial sector, which can lead to better CD rates and terms for consumers. Don't limit your search to traditional brick-and-mortar banks; consider exploring online banks and credit unions as well. - -Conclusion - -Short-term certificates of deposit can be a valuable addition to a beginner investor's portfolio, offering safety, predictability, and flexibility. By understanding the benefits and risks associated with short-term CDs and following our tips for choosing the best options, you can make informed decisions and bolster your investment strategy. Stay aware of current market trends and keep an eye on interest rates to ensure you're making the most of your short-term CD investments. - - - diff --git a/plugin.png b/plugin.png new file mode 100644 index 00000000..865ce3c9 Binary files /dev/null and b/plugin.png differ diff --git a/plugins/__PUT_PLUGIN_ZIPS_HERE__ b/plugins/__PUT_PLUGIN_ZIPS_HERE__ new file mode 100644 index 00000000..e69de29b diff --git a/pyproject.toml b/pyproject.toml index 64ed7165..fdb43d66 100644 --- a/pyproject.toml +++ b/pyproject.toml @@ -8,4 +8,33 @@ readme = "README.md" line-length = 88 target-version = ['py310'] include = '\.pyi?$' -extend-exclude = "" \ No newline at end of file +packages = ["autogpt"] +extend-exclude = '.+/(dist|.venv|venv|build)/.+' + + +[tool.isort] +profile = "black" +multi_line_output = 3 +include_trailing_comma = true +force_grid_wrap = 0 +use_parentheses = true +ensure_newline_before_comments = true +line_length = 88 +sections = [ + "FUTURE", + "STDLIB", + "THIRDPARTY", + "FIRSTPARTY", + "LOCALFOLDER" +] +skip = ''' + .tox + __pycache__ + *.pyc + .env + venv*/* + .venv/* + reports/* + dist/* + +''' diff --git a/requirements-docker.txt b/requirements-docker.txt deleted file mode 100644 index 3a8a344c..00000000 --- a/requirements-docker.txt +++ /dev/null @@ -1,27 +0,0 @@ -beautifulsoup4 -colorama==0.4.6 -openai==0.27.2 -playsound==1.2.2 -python-dotenv==1.0.0 -pyyaml==6.0 -readability-lxml==0.8.1 -requests -tiktoken==0.3.3 -gTTS==2.3.1 -docker -duckduckgo-search -google-api-python-client #(https://developers.google.com/custom-search/v1/overview) -pinecone-client==2.2.1 -redis -orjson -Pillow -selenium -webdriver-manager -coverage -flake8 -numpy -pre-commit -black -isort -gitpython==3.1.31 -tweepy \ No newline at end of file diff --git a/requirements.txt b/requirements.txt index 843b66bf..d5a1c63b 100644 --- a/requirements.txt +++ b/requirements.txt @@ -1,4 +1,4 @@ -beautifulsoup4 +beautifulsoup4>=4.12.2 colorama==0.4.6 openai==0.27.2 playsound==1.2.2 @@ -19,6 +19,9 @@ selenium webdriver-manager jsonschema tweepy +click +spacy>=3.0.0,<4.0.0 +en-core-web-sm @ https://github.com/explosion/spacy-models/releases/download/en_core_web_sm-3.5.0/en_core_web_sm-3.5.0-py3-none-any.whl ##Dev coverage @@ -26,9 +29,14 @@ flake8 numpy pre-commit black -sourcery isort gitpython==3.1.31 +auto-gpt-plugin-template + +# OpenAI and Generic plugins import +openapi-python-client==0.13.4 + +# Items below this point will not be included in the Docker Image # Testing dependencies pytest diff --git a/scripts/__init__.py b/scripts/__init__.py new file mode 100644 index 00000000..e69de29b diff --git a/scripts/check_requirements.py b/scripts/check_requirements.py index d1f23504..3323697b 100644 --- a/scripts/check_requirements.py +++ b/scripts/check_requirements.py @@ -1,6 +1,8 @@ -import pkg_resources +import re import sys +import pkg_resources + def main(): requirements_file = sys.argv[1] @@ -15,7 +17,7 @@ def main(): for package in required_packages: if not package: # Skip empty lines continue - package_name = package.strip().split("==")[0] + package_name = re.split("[<>=@ ]+", package.strip())[0] if package_name.lower() not in installed_packages: missing_packages.append(package_name) diff --git a/tests.py b/tests.py index 67ba1c8e..62f76da8 100644 --- a/tests.py +++ b/tests.py @@ -1,4 +1,5 @@ import unittest + import coverage if __name__ == "__main__": diff --git a/tests/browse_tests.py b/tests/browse_tests.py index 1ac523ec..f896e7dd 100644 --- a/tests/browse_tests.py +++ b/tests/browse_tests.py @@ -1,6 +1,6 @@ -import unittest import os import sys +import unittest from bs4 import BeautifulSoup diff --git a/tests/integration/weaviate_memory_tests.py b/tests/integration/weaviate_memory_tests.py index 503fe9d2..015eab05 100644 --- a/tests/integration/weaviate_memory_tests.py +++ b/tests/integration/weaviate_memory_tests.py @@ -1,28 +1,21 @@ +import os +import sys import unittest from unittest import mock -import sys -import os +from uuid import uuid4 from weaviate import Client from weaviate.util import get_valid_uuid -from uuid import uuid4 from autogpt.config import Config -from autogpt.memory.weaviate import WeaviateMemory from autogpt.memory.base import get_ada_embedding +from autogpt.memory.weaviate import WeaviateMemory -@mock.patch.dict(os.environ, { - "WEAVIATE_HOST": "127.0.0.1", - "WEAVIATE_PROTOCOL": "http", - "WEAVIATE_PORT": "8080", - "WEAVIATE_USERNAME": "", - "WEAVIATE_PASSWORD": "", - "MEMORY_INDEX": "AutogptTests" -}) class TestWeaviateMemory(unittest.TestCase): cfg = None client = None + index = None @classmethod def setUpClass(cls): @@ -32,13 +25,19 @@ class TestWeaviateMemory(unittest.TestCase): if cls.cfg.use_weaviate_embedded: from weaviate.embedded import EmbeddedOptions - cls.client = Client(embedded_options=EmbeddedOptions( - hostname=cls.cfg.weaviate_host, - port=int(cls.cfg.weaviate_port), - persistence_data_path=cls.cfg.weaviate_embedded_path - )) + cls.client = Client( + embedded_options=EmbeddedOptions( + hostname=cls.cfg.weaviate_host, + port=int(cls.cfg.weaviate_port), + persistence_data_path=cls.cfg.weaviate_embedded_path, + ) + ) else: - cls.client = Client(f"{cls.cfg.weaviate_protocol}://{cls.cfg.weaviate_host}:{self.cfg.weaviate_port}") + cls.client = Client( + f"{cls.cfg.weaviate_protocol}://{cls.cfg.weaviate_host}:{self.cfg.weaviate_port}" + ) + + cls.index = WeaviateMemory.format_classname(cls.cfg.memory_index) """ In order to run these tests you will need a local instance of @@ -49,32 +48,33 @@ class TestWeaviateMemory(unittest.TestCase): USE_WEAVIATE_EMBEDDED=True WEAVIATE_EMBEDDED_PATH="/home/me/.local/share/weaviate" """ + def setUp(self): try: - self.client.schema.delete_class(self.cfg.memory_index) + self.client.schema.delete_class(self.index) except: pass self.memory = WeaviateMemory(self.cfg) def test_add(self): - doc = 'You are a Titan name Thanos and you are looking for the Infinity Stones' + doc = "You are a Titan name Thanos and you are looking for the Infinity Stones" self.memory.add(doc) - result = self.client.query.get(self.cfg.memory_index, ['raw_text']).do() - actual = result['data']['Get'][self.cfg.memory_index] + result = self.client.query.get(self.index, ["raw_text"]).do() + actual = result["data"]["Get"][self.index] self.assertEqual(len(actual), 1) - self.assertEqual(actual[0]['raw_text'], doc) + self.assertEqual(actual[0]["raw_text"], doc) def test_get(self): - doc = 'You are an Avenger and swore to defend the Galaxy from a menace called Thanos' + doc = "You are an Avenger and swore to defend the Galaxy from a menace called Thanos" with self.client.batch as batch: batch.add_data_object( uuid=get_valid_uuid(uuid4()), - data_object={'raw_text': doc}, - class_name=self.cfg.memory_index, - vector=get_ada_embedding(doc) + data_object={"raw_text": doc}, + class_name=self.index, + vector=get_ada_embedding(doc), ) batch.flush() @@ -86,8 +86,8 @@ class TestWeaviateMemory(unittest.TestCase): def test_get_stats(self): docs = [ - 'You are now about to count the number of docs in this index', - 'And then you about to find out if you can count correctly' + "You are now about to count the number of docs in this index", + "And then you about to find out if you can count correctly", ] [self.memory.add(doc) for doc in docs] @@ -95,23 +95,23 @@ class TestWeaviateMemory(unittest.TestCase): stats = self.memory.get_stats() self.assertTrue(stats) - self.assertTrue('count' in stats) - self.assertEqual(stats['count'], 2) + self.assertTrue("count" in stats) + self.assertEqual(stats["count"], 2) def test_clear(self): docs = [ - 'Shame this is the last test for this class', - 'Testing is fun when someone else is doing it' + "Shame this is the last test for this class", + "Testing is fun when someone else is doing it", ] [self.memory.add(doc) for doc in docs] - self.assertEqual(self.memory.get_stats()['count'], 2) + self.assertEqual(self.memory.get_stats()["count"], 2) self.memory.clear() - self.assertEqual(self.memory.get_stats()['count'], 0) + self.assertEqual(self.memory.get_stats()["count"], 0) -if __name__ == '__main__': +if __name__ == "__main__": unittest.main() diff --git a/tests/mocks/__init__.py b/tests/mocks/__init__.py new file mode 100644 index 00000000..e69de29b diff --git a/tests/mocks/mock_commands.py b/tests/mocks/mock_commands.py new file mode 100644 index 00000000..d64284bc --- /dev/null +++ b/tests/mocks/mock_commands.py @@ -0,0 +1,6 @@ +from autogpt.commands.command import command + + +@command("function_based", "Function-based test command") +def function_based(arg1: int, arg2: str) -> str: + return f"{arg1} - {arg2}" diff --git a/tests/test_commands.py b/tests/test_commands.py new file mode 100644 index 00000000..8a7771f6 --- /dev/null +++ b/tests/test_commands.py @@ -0,0 +1,177 @@ +import os +import shutil +import sys +from pathlib import Path + +import pytest + +from autogpt.commands.command import Command, CommandRegistry + + +class TestCommand: + @staticmethod + def example_function(arg1: int, arg2: str) -> str: + return f"{arg1} - {arg2}" + + def test_command_creation(self): + cmd = Command( + name="example", description="Example command", method=self.example_function + ) + + assert cmd.name == "example" + assert cmd.description == "Example command" + assert cmd.method == self.example_function + assert cmd.signature == "(arg1: int, arg2: str) -> str" + + def test_command_call(self): + cmd = Command( + name="example", description="Example command", method=self.example_function + ) + + result = cmd(arg1=1, arg2="test") + assert result == "1 - test" + + def test_command_call_with_invalid_arguments(self): + cmd = Command( + name="example", description="Example command", method=self.example_function + ) + + with pytest.raises(TypeError): + cmd(arg1="invalid", does_not_exist="test") + + def test_command_default_signature(self): + cmd = Command( + name="example", description="Example command", method=self.example_function + ) + + assert cmd.signature == "(arg1: int, arg2: str) -> str" + + def test_command_custom_signature(self): + custom_signature = "custom_arg1: int, custom_arg2: str" + cmd = Command( + name="example", + description="Example command", + method=self.example_function, + signature=custom_signature, + ) + + assert cmd.signature == custom_signature + + +class TestCommandRegistry: + @staticmethod + def example_function(arg1: int, arg2: str) -> str: + return f"{arg1} - {arg2}" + + def test_register_command(self): + """Test that a command can be registered to the registry.""" + registry = CommandRegistry() + cmd = Command( + name="example", description="Example command", method=self.example_function + ) + + registry.register(cmd) + + assert cmd.name in registry.commands + assert registry.commands[cmd.name] == cmd + + def test_unregister_command(self): + """Test that a command can be unregistered from the registry.""" + registry = CommandRegistry() + cmd = Command( + name="example", description="Example command", method=self.example_function + ) + + registry.register(cmd) + registry.unregister(cmd.name) + + assert cmd.name not in registry.commands + + def test_get_command(self): + """Test that a command can be retrieved from the registry.""" + registry = CommandRegistry() + cmd = Command( + name="example", description="Example command", method=self.example_function + ) + + registry.register(cmd) + retrieved_cmd = registry.get_command(cmd.name) + + assert retrieved_cmd == cmd + + def test_get_nonexistent_command(self): + """Test that attempting to get a nonexistent command raises a KeyError.""" + registry = CommandRegistry() + + with pytest.raises(KeyError): + registry.get_command("nonexistent_command") + + def test_call_command(self): + """Test that a command can be called through the registry.""" + registry = CommandRegistry() + cmd = Command( + name="example", description="Example command", method=self.example_function + ) + + registry.register(cmd) + result = registry.call("example", arg1=1, arg2="test") + + assert result == "1 - test" + + def test_call_nonexistent_command(self): + """Test that attempting to call a nonexistent command raises a KeyError.""" + registry = CommandRegistry() + + with pytest.raises(KeyError): + registry.call("nonexistent_command", arg1=1, arg2="test") + + def test_get_command_prompt(self): + """Test that the command prompt is correctly formatted.""" + registry = CommandRegistry() + cmd = Command( + name="example", description="Example command", method=self.example_function + ) + + registry.register(cmd) + command_prompt = registry.command_prompt() + + assert f"(arg1: int, arg2: str)" in command_prompt + + def test_import_mock_commands_module(self): + """Test that the registry can import a module with mock command plugins.""" + registry = CommandRegistry() + mock_commands_module = "tests.mocks.mock_commands" + + registry.import_commands(mock_commands_module) + + assert "function_based" in registry.commands + assert registry.commands["function_based"].name == "function_based" + assert ( + registry.commands["function_based"].description + == "Function-based test command" + ) + + def test_import_temp_command_file_module(self, tmp_path): + """Test that the registry can import a command plugins module from a temp file.""" + registry = CommandRegistry() + + # Create a temp command file + src = Path(os.getcwd()) / "tests/mocks/mock_commands.py" + temp_commands_file = tmp_path / "mock_commands.py" + shutil.copyfile(src, temp_commands_file) + + # Add the temp directory to sys.path to make the module importable + sys.path.append(str(tmp_path)) + + temp_commands_module = "mock_commands" + registry.import_commands(temp_commands_module) + + # Remove the temp directory from sys.path + sys.path.remove(str(tmp_path)) + + assert "function_based" in registry.commands + assert registry.commands["function_based"].name == "function_based" + assert ( + registry.commands["function_based"].description + == "Function-based test command" + ) diff --git a/tests/test_image_gen.py b/tests/test_image_gen.py new file mode 100644 index 00000000..19c57e42 --- /dev/null +++ b/tests/test_image_gen.py @@ -0,0 +1,102 @@ +import hashlib +import os +import unittest + +from PIL import Image + +from autogpt.commands.image_gen import generate_image, generate_image_with_sd_webui +from autogpt.config import Config +from autogpt.workspace import path_in_workspace + + +def lst(txt): + return txt.split(":")[1].strip() + + +@unittest.skipIf(os.getenv("CI"), "Skipping image generation tests") +class TestImageGen(unittest.TestCase): + def setUp(self): + self.config = Config() + + def test_dalle(self): + self.config.image_provider = "dalle" + + # Test using size 256 + result = lst(generate_image("astronaut riding a horse", 256)) + image_path = path_in_workspace(result) + self.assertTrue(image_path.exists()) + with Image.open(image_path) as img: + self.assertEqual(img.size, (256, 256)) + image_path.unlink() + + # Test using size 512 + result = lst(generate_image("astronaut riding a horse", 512)) + image_path = path_in_workspace(result) + with Image.open(image_path) as img: + self.assertEqual(img.size, (512, 512)) + image_path.unlink() + + def test_huggingface(self): + self.config.image_provider = "huggingface" + + # Test usin SD 1.4 model and size 512 + self.config.huggingface_image_model = "CompVis/stable-diffusion-v1-4" + result = lst(generate_image("astronaut riding a horse", 512)) + image_path = path_in_workspace(result) + self.assertTrue(image_path.exists()) + with Image.open(image_path) as img: + self.assertEqual(img.size, (512, 512)) + image_path.unlink() + + # Test using SD 2.1 768 model and size 768 + self.config.huggingface_image_model = "stabilityai/stable-diffusion-2-1" + result = lst(generate_image("astronaut riding a horse", 768)) + image_path = path_in_workspace(result) + with Image.open(image_path) as img: + self.assertEqual(img.size, (768, 768)) + image_path.unlink() + + def test_sd_webui(self): + self.config.image_provider = "sd_webui" + return + + # Test using size 128 + result = lst(generate_image_with_sd_webui("astronaut riding a horse", 128)) + image_path = path_in_workspace(result) + self.assertTrue(image_path.exists()) + with Image.open(image_path) as img: + self.assertEqual(img.size, (128, 128)) + image_path.unlink() + + # Test using size 64 and negative prompt + result = lst( + generate_image_with_sd_webui( + "astronaut riding a horse", + negative_prompt="horse", + size=64, + extra={"seed": 123}, + ) + ) + image_path = path_in_workspace(result) + with Image.open(image_path) as img: + self.assertEqual(img.size, (64, 64)) + neg_image_hash = hashlib.md5(img.tobytes()).hexdigest() + image_path.unlink() + + # Same test as above but without the negative prompt + result = lst( + generate_image_with_sd_webui( + "astronaut riding a horse", image_size=64, size=1, extra={"seed": 123} + ) + ) + image_path = path_in_workspace(result) + with Image.open(image_path) as img: + self.assertEqual(img.size, (64, 64)) + image_hash = hashlib.md5(img.tobytes()).hexdigest() + image_path.unlink() + + self.assertNotEqual(image_hash, neg_image_hash) + + +if __name__ == "__main__": + unittest.main() diff --git a/tests/test_json_parser.py b/tests/test_json_parser.py index 2862034b..41c90a6f 100644 --- a/tests/test_json_parser.py +++ b/tests/test_json_parser.py @@ -1,7 +1,7 @@ import unittest import tests.context -from autogpt.json_fixes.parsing import fix_and_parse_json +from autogpt.json_utils.json_fix_llm import fix_and_parse_json class TestParseJson(unittest.TestCase): diff --git a/tests/test_prompt_generator.py b/tests/test_prompt_generator.py index 6a0bfd6c..1fa1754d 100644 --- a/tests/test_prompt_generator.py +++ b/tests/test_prompt_generator.py @@ -1,6 +1,6 @@ from unittest import TestCase -from autogpt.promptgenerator import PromptGenerator +from autogpt.prompts.generator import PromptGenerator class TestPromptGenerator(TestCase): @@ -38,6 +38,7 @@ class TestPromptGenerator(TestCase): "label": command_label, "name": command_name, "args": args, + "function": None, } self.assertIn(command, self.generator.commands) diff --git a/tests/test_token_counter.py b/tests/test_token_counter.py index 81e68277..6d7ae016 100644 --- a/tests/test_token_counter.py +++ b/tests/test_token_counter.py @@ -1,4 +1,5 @@ import unittest + import tests.context from autogpt.token_counter import count_message_tokens, count_string_tokens diff --git a/tests/unit/data/test_plugins/Auto-GPT-Plugin-Test-master.zip b/tests/unit/data/test_plugins/Auto-GPT-Plugin-Test-master.zip new file mode 100644 index 00000000..00bc1f4f Binary files /dev/null and b/tests/unit/data/test_plugins/Auto-GPT-Plugin-Test-master.zip differ diff --git a/tests/unit/json_tests.py b/tests/unit/json_tests.py index 561b8a38..25c38337 100644 --- a/tests/unit/json_tests.py +++ b/tests/unit/json_tests.py @@ -1,6 +1,6 @@ import unittest -from autogpt.json_parser import fix_and_parse_json +from autogpt.json_utils.json_fix_llm import fix_and_parse_json class TestParseJson(unittest.TestCase): diff --git a/tests/unit/models/test_base_open_api_plugin.py b/tests/unit/models/test_base_open_api_plugin.py new file mode 100644 index 00000000..950a3266 --- /dev/null +++ b/tests/unit/models/test_base_open_api_plugin.py @@ -0,0 +1,79 @@ +from typing import Any, Dict, List, Optional, Tuple + +import pytest + +from autogpt.models.base_open_ai_plugin import ( + BaseOpenAIPlugin, + Message, + PromptGenerator, +) + + +class DummyPlugin(BaseOpenAIPlugin): + pass + + +@pytest.fixture +def dummy_plugin(): + manifests_specs_clients = { + "manifest": { + "name_for_model": "Dummy", + "schema_version": "1.0", + "description_for_model": "A dummy plugin for testing purposes", + }, + "client": None, + "openapi_spec": None, + } + return DummyPlugin(manifests_specs_clients) + + +def test_dummy_plugin_inheritance(dummy_plugin): + assert isinstance(dummy_plugin, BaseOpenAIPlugin) + + +def test_dummy_plugin_name(dummy_plugin): + assert dummy_plugin._name == "Dummy" + + +def test_dummy_plugin_version(dummy_plugin): + assert dummy_plugin._version == "1.0" + + +def test_dummy_plugin_description(dummy_plugin): + assert dummy_plugin._description == "A dummy plugin for testing purposes" + + +def test_dummy_plugin_default_methods(dummy_plugin): + assert not dummy_plugin.can_handle_on_response() + assert not dummy_plugin.can_handle_post_prompt() + assert not dummy_plugin.can_handle_on_planning() + assert not dummy_plugin.can_handle_post_planning() + assert not dummy_plugin.can_handle_pre_instruction() + assert not dummy_plugin.can_handle_on_instruction() + assert not dummy_plugin.can_handle_post_instruction() + assert not dummy_plugin.can_handle_pre_command() + assert not dummy_plugin.can_handle_post_command() + assert not dummy_plugin.can_handle_chat_completion(None, None, None, None) + + assert dummy_plugin.on_response("hello") == "hello" + assert dummy_plugin.post_prompt(None) is None + assert dummy_plugin.on_planning(None, None) is None + assert dummy_plugin.post_planning("world") == "world" + pre_instruction = dummy_plugin.pre_instruction( + [{"role": "system", "content": "Beep, bop, boop"}] + ) + assert isinstance(pre_instruction, list) + assert len(pre_instruction) == 1 + assert pre_instruction[0]["role"] == "system" + assert pre_instruction[0]["content"] == "Beep, bop, boop" + assert dummy_plugin.on_instruction(None) is None + assert dummy_plugin.post_instruction("I'm a robot") == "I'm a robot" + pre_command = dummy_plugin.pre_command("evolve", {"continuously": True}) + assert isinstance(pre_command, tuple) + assert len(pre_command) == 2 + assert pre_command[0] == "evolve" + assert pre_command[1]["continuously"] == True + post_command = dummy_plugin.post_command("evolve", "upgraded successfully!") + assert isinstance(post_command, str) + assert post_command == "upgraded successfully!" + assert dummy_plugin.handle_chat_completion(None, None, None, None) is None diff --git a/tests/unit/test_browse_scrape_text.py b/tests/unit/test_browse_scrape_text.py index fea5ebfc..1a36e19b 100644 --- a/tests/unit/test_browse_scrape_text.py +++ b/tests/unit/test_browse_scrape_text.py @@ -9,16 +9,20 @@ Code Analysis Objective: The objective of the "scrape_text" function is to scrape the text content from -a given URL and return it as a string, after removing any unwanted HTML tags and scripts. +a given URL and return it as a string, after removing any unwanted HTML tags and + scripts. Inputs: - url: a string representing the URL of the webpage to be scraped. Flow: -1. Send a GET request to the given URL using the requests library and the user agent header from the config file. +1. Send a GET request to the given URL using the requests library and the user agent + header from the config file. 2. Check if the response contains an HTTP error. If it does, return an error message. -3. Use BeautifulSoup to parse the HTML content of the response and extract all script and style tags. -4. Get the text content of the remaining HTML using the get_text() method of BeautifulSoup. +3. Use BeautifulSoup to parse the HTML content of the response and extract all script + and style tags. +4. Get the text content of the remaining HTML using the get_text() method of + BeautifulSoup. 5. Split the text into lines and then into chunks, removing any extra whitespace. 6. Join the chunks into a single string with newline characters between them. 7. Return the cleaned text. @@ -27,9 +31,12 @@ Outputs: - A string representing the cleaned text content of the webpage. Additional aspects: -- The function uses the requests library and BeautifulSoup to handle the HTTP request and HTML parsing, respectively. -- The function removes script and style tags from the HTML to avoid including unwanted content in the text output. -- The function uses a generator expression to split the text into lines and chunks, which can improve performance for large amounts of text. +- The function uses the requests library and BeautifulSoup to handle the HTTP request + and HTML parsing, respectively. +- The function removes script and style tags from the HTML to avoid including unwanted + content in the text output. +- The function uses a generator expression to split the text into lines and chunks, + which can improve performance for large amounts of text. """ @@ -40,26 +47,33 @@ class TestScrapeText: expected_text = "This is some sample text" mock_response = mocker.Mock() mock_response.status_code = 200 - mock_response.text = f"

{expected_text}

" + mock_response.text = ( + "

" + f"{expected_text}

" + ) mocker.patch("requests.Session.get", return_value=mock_response) - # Call the function with a valid URL and assert that it returns the expected text + # Call the function with a valid URL and assert that it returns the + # expected text url = "http://www.example.com" assert scrape_text(url) == expected_text - # Tests that the function returns an error message when an invalid or unreachable url is provided. + # Tests that the function returns an error message when an invalid or unreachable + # url is provided. def test_invalid_url(self, mocker): # Mock the requests.get() method to raise an exception mocker.patch( "requests.Session.get", side_effect=requests.exceptions.RequestException ) - # Call the function with an invalid URL and assert that it returns an error message + # Call the function with an invalid URL and assert that it returns an error + # message url = "http://www.invalidurl.com" error_message = scrape_text(url) assert "Error:" in error_message - # Tests that the function returns an empty string when the html page contains no text to be scraped. + # Tests that the function returns an empty string when the html page contains no + # text to be scraped. def test_no_text(self, mocker): # Mock the requests.get() method to return a response with no text mock_response = mocker.Mock() @@ -71,7 +85,8 @@ class TestScrapeText: url = "http://www.example.com" assert scrape_text(url) == "" - # Tests that the function returns an error message when the response status code is an http error (>=400). + # Tests that the function returns an error message when the response status code is + # an http error (>=400). def test_http_error(self, mocker): # Mock the requests.get() method to return a response with a 404 status code mocker.patch("requests.Session.get", return_value=mocker.Mock(status_code=404)) diff --git a/tests/unit/test_chat.py b/tests/unit/test_chat.py index 55a44492..774f4103 100644 --- a/tests/unit/test_chat.py +++ b/tests/unit/test_chat.py @@ -1,6 +1,6 @@ # Generated by CodiumAI -import unittest import time +import unittest from unittest.mock import patch from autogpt.chat import create_chat_message, generate_context diff --git a/tests/unit/test_plugins.py b/tests/unit/test_plugins.py new file mode 100644 index 00000000..7c71f69f --- /dev/null +++ b/tests/unit/test_plugins.py @@ -0,0 +1,110 @@ +import pytest + +from autogpt.config import Config +from autogpt.plugins import ( + denylist_allowlist_check, + inspect_zip_for_module, + scan_plugins, +) + +PLUGINS_TEST_DIR = "tests/unit/data/test_plugins" +PLUGIN_TEST_ZIP_FILE = "Auto-GPT-Plugin-Test-master.zip" +PLUGIN_TEST_INIT_PY = "Auto-GPT-Plugin-Test-master/src/auto_gpt_vicuna/__init__.py" +PLUGIN_TEST_OPENAI = "https://weathergpt.vercel.app/" + + +def test_inspect_zip_for_module(): + result = inspect_zip_for_module(str(f"{PLUGINS_TEST_DIR}/{PLUGIN_TEST_ZIP_FILE}")) + assert result == PLUGIN_TEST_INIT_PY + + +@pytest.fixture +def mock_config_denylist_allowlist_check(): + class MockConfig: + plugins_denylist = ["BadPlugin"] + plugins_allowlist = ["GoodPlugin"] + + return MockConfig() + + +def test_denylist_allowlist_check_denylist( + mock_config_denylist_allowlist_check, monkeypatch +): + monkeypatch.setattr("builtins.input", lambda _: "y") + assert not denylist_allowlist_check( + "BadPlugin", mock_config_denylist_allowlist_check + ) + + +def test_denylist_allowlist_check_allowlist( + mock_config_denylist_allowlist_check, monkeypatch +): + monkeypatch.setattr("builtins.input", lambda _: "y") + assert denylist_allowlist_check("GoodPlugin", mock_config_denylist_allowlist_check) + + +def test_denylist_allowlist_check_user_input_yes( + mock_config_denylist_allowlist_check, monkeypatch +): + monkeypatch.setattr("builtins.input", lambda _: "y") + assert denylist_allowlist_check( + "UnknownPlugin", mock_config_denylist_allowlist_check + ) + + +def test_denylist_allowlist_check_user_input_no( + mock_config_denylist_allowlist_check, monkeypatch +): + monkeypatch.setattr("builtins.input", lambda _: "n") + assert not denylist_allowlist_check( + "UnknownPlugin", mock_config_denylist_allowlist_check + ) + + +def test_denylist_allowlist_check_user_input_invalid( + mock_config_denylist_allowlist_check, monkeypatch +): + monkeypatch.setattr("builtins.input", lambda _: "invalid") + assert not denylist_allowlist_check( + "UnknownPlugin", mock_config_denylist_allowlist_check + ) + + +@pytest.fixture +def config_with_plugins(): + cfg = Config() + cfg.plugins_dir = PLUGINS_TEST_DIR + cfg.plugins_openai = ["https://weathergpt.vercel.app/"] + return cfg + + +@pytest.fixture +def mock_config_openai_plugin(): + class MockConfig: + plugins_dir = PLUGINS_TEST_DIR + plugins_openai = [PLUGIN_TEST_OPENAI] + plugins_denylist = ["AutoGPTPVicuna"] + plugins_allowlist = [PLUGIN_TEST_OPENAI] + + return MockConfig() + + +def test_scan_plugins_openai(mock_config_openai_plugin): + result = scan_plugins(mock_config_openai_plugin, debug=True) + assert len(result) == 1 + + +@pytest.fixture +def mock_config_generic_plugin(): + class MockConfig: + plugins_dir = PLUGINS_TEST_DIR + plugins_openai = [] + plugins_denylist = [] + plugins_allowlist = ["AutoGPTPVicuna"] + + return MockConfig() + + +def test_scan_plugins_generic(mock_config_generic_plugin): + result = scan_plugins(mock_config_generic_plugin, debug=True) + assert len(result) == 1