Merge remote-tracking branch 'origin/master' into support-headless-chrome-mode

.devcontainer/Dockerfile

@@ -1,6 +1,6 @@
 # [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
 ARG VARIANT=3-bullseye
-FROM python:3.8
+FROM --platform=linux/amd64 python:3.8
 
 RUN apt-get update && export DEBIAN_FRONTEND=noninteractive \
     # Remove imagemagick due to https://security-tracker.debian.org/tracker/CVE-2019-10131
@@ -10,6 +10,11 @@ RUN apt-get update && export DEBIAN_FRONTEND=noninteractive \
 # They are installed by the base image (python) which does not have the patch.
 RUN python3 -m pip install --upgrade setuptools
 
+# Install Chrome for web browsing
+RUN apt-get update && export DEBIAN_FRONTEND=noninteractive \
+    && curl -sSL https://dl.google.com/linux/direct/google-chrome-stable_current_$(dpkg --print-architecture).deb -o /tmp/chrome.deb \
+    && apt-get -y install /tmp/chrome.deb
+
 # [Optional] If your pip requirements rarely change, uncomment this section to add them to the image.
 # COPY requirements.txt /tmp/pip-tmp/
 # RUN pip3 --disable-pip-version-check --no-cache-dir install -r /tmp/pip-tmp/requirements.txt \

.devcontainer/devcontainer.json

@@ -11,6 +11,7 @@
       "userGid": "1000",
       "upgradePackages": "true"
     },
+    "ghcr.io/devcontainers/features/desktop-lite:1": {},
     "ghcr.io/devcontainers/features/python:1": "none",
     "ghcr.io/devcontainers/features/node:1": "none",
     "ghcr.io/devcontainers/features/git:1": {

.env.template

@@ -5,12 +5,13 @@
 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)
 # 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
 
 ################################################################################
 ### LLM PROVIDER
@@ -18,23 +19,14 @@ AI_SETTINGS_FILE=ai_settings.yaml
 
 ### OPENAI
 # OPENAI_API_KEY - OpenAI API Key (Example: my-openai-api-key)
-# TEMPERATURE - Sets temperature in OpenAI (Default: 1)
+# TEMPERATURE - Sets temperature in OpenAI (Default: 0)
 # USE_AZURE - Use Azure OpenAI or not (Default: False)
 OPENAI_API_KEY=your-openai-api-key
-TEMPERATURE=1
+TEMPERATURE=0
 USE_AZURE=False
 
 ### AZURE
-# OPENAI_AZURE_API_BASE - OpenAI API base URL for Azure (Example: https://my-azure-openai-url.com)
+# cleanup azure env as already moved to `azure.yaml.template`
-# OPENAI_AZURE_API_VERSION - OpenAI API version for Azure (Example: v1)
-# OPENAI_AZURE_DEPLOYMENT_ID - OpenAI deployment ID for Azure (Example: my-deployment-id)
-# OPENAI_AZURE_CHAT_DEPLOYMENT_ID - OpenAI deployment ID for Azure Chat (Example: my-deployment-id-for-azure-chat)
-# OPENAI_AZURE_EMBEDDINGS_DEPLOYMENT_ID - OpenAI deployment ID for Embedding (Example: my-deployment-id-for-azure-embeddigs)
-OPENAI_AZURE_API_BASE=your-base-url-for-azure
-OPENAI_AZURE_API_VERSION=api-version-for-azure
-OPENAI_AZURE_DEPLOYMENT_ID=deployment-id-for-azure
-OPENAI_AZURE_CHAT_DEPLOYMENT_ID=deployment-id-for-azure-chat
-OPENAI_AZURE_EMBEDDINGS_DEPLOYMENT_ID=deployment-id-for-azure-embeddigs
 
 ################################################################################
 ### LLM MODELS
@@ -48,7 +40,7 @@ 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 --gpt3onlythis needs to be set to 4000.
+# When using --gpt3only this needs to be set to 4000.
 FAST_TOKEN_LIMIT=4000
 SMART_TOKEN_LIMIT=8000
 
@@ -56,7 +48,11 @@ SMART_TOKEN_LIMIT=8000
 ### MEMORY
 ################################################################################
 
-# MEMORY_BACKEND - Memory backend type (Default: local)
+### MEMORY_BACKEND - Memory backend type
+# local - Default
+# pinecone - Pinecone (if configured)
+# redis - Redis (if configured)
+# milvus - Milvus (if configured)
 MEMORY_BACKEND=local
 
 ### PINECONE
@@ -66,7 +62,7 @@ PINECONE_API_KEY=your-pinecone-api-key
 PINECONE_ENV=your-pinecone-region
 
 ### REDIS
-# REDIS_HOST - Redis host (Default: localhost)
+# 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: False)
@@ -77,6 +73,34 @@ REDIS_PASSWORD=
 WIPE_REDIS_ON_START=False
 MEMORY_INDEX=auto-gpt
 
+### 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
+
+### 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
+
 ################################################################################
 ### IMAGE GENERATION PROVIDER
 ################################################################################
@@ -93,9 +117,30 @@ IMAGE_PROVIDER=dalle
 HUGGINGFACE_API_TOKEN=your-huggingface-api-token
 
 ################################################################################
-### SEARCH PROVIDER
+### AUDIO TO TEXT PROVIDER
 ################################################################################
 
+### HUGGINGFACE
+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
+
+################################################################################
+### WEB BROWSING
+################################################################################
+
+### BROWSER
+# HEADLESS_BROWSER - Whether to run the browser in headless mode
+HEADLESS_BROWSER=True
+
 ### 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)
@@ -122,5 +167,11 @@ ELEVENLABS_API_KEY=your-elevenlabs-api-key
 ELEVENLABS_VOICE_1_ID=your-voice-id-1
 ELEVENLABS_VOICE_2_ID=your-voice-id-2
 
-# Chrome Headless Mode
+################################################################################
-HEADLESS_BROWSER=True
+### TWITTER API 
+################################################################################
+
+TW_CONSUMER_KEY=
+TW_CONSUMER_SECRET=
+TW_ACCESS_TOKEN=
+TW_ACCESS_TOKEN_SECRET=

.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

.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*/*,
-    .venv/*
+    .venv/*,
-    reports/*
+    reports/*,
-    dist/*
+    dist/*,

.github/ISSUE_TEMPLATE/1.bug.yml

@@ -2,6 +2,29 @@ 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 ⚠️
+      description: >
+        Please [search the history](https://github.com/Torantulino/Auto-GPT/issues)
+        to see if an issue already exists for the same problem.
+      options:
+        - label: I have searched the existing issues, and there is no existing issue for my problem
+          required: true
   - type: markdown
     attributes:
       value: |
@@ -19,14 +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: dropdown
-  - type: checkboxes
     attributes:
-      label: Duplicates
+      label: Which Operating System are you using?
-      description: Please [search the history](https://github.com/Torantulino/Auto-GPT/issues) to see if an issue already exists for the same problem.
+      description: >
+        Please select the operating system you were using to run Auto-GPT when this problem occurred.
       options:
-        - label: I have searched the existing issues
+        - Windows
-          required: true
+        - 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](https://github.com/Significant-Gravitas/Auto-GPT/issues?q=is%3Aissue+label%3A%22AI+model+limitation%22) of GPT-3.5.
+      options:
+        - GPT-3.5
+        - GPT-4
+    validations:
+      required: true
   - type: textarea
     attributes:
       label: Steps to reproduce 🕹
@@ -43,9 +84,34 @@ body:
   - type: textarea
     attributes:
       label: Your prompt 📝
-      description: |
+      description: >
-        If applicable please provide the prompt you are using. You can find your last-used prompt in last_run_ai_settings.yaml.
+        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!
+        
+        <details>
+        <summary><i>Example</i></summary>
+        ```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.
+        ```
+        </details>
+      value: |
+        ```log
+        <insert your logs here>
+        ```

.github/PULL_REQUEST_TEMPLATE.md

@@ -1,3 +1,10 @@
+<!-- ⚠️ At the moment any non-essential commands are not being merged.
+If you want to add non-essential commands to Auto-GPT, please create a plugin instead.
+We are expecting to ship plugin support within the week (PR #757).
+Resources:
+* https://github.com/Significant-Gravitas/Auto-GPT-Plugin-Template
+-->
+
 <!-- 📢 Announcement
 We've recently noticed an increase in pull requests focusing on combining multiple changes. While the intentions behind these PRs are appreciated, it's essential to maintain a clean and manageable git history. To ensure the quality of our repository, we kindly ask you to adhere to the following guidelines when submitting PRs:
 
@@ -30,4 +37,4 @@ By following these guidelines, your PRs are more likely to be merged quickly aft
 
 <!-- If you haven't added tests, please explain why. If you have, check the appropriate box. If you've ensured your PR is atomic and well-documented, check the corresponding boxes. -->
 
-<!-- By submitting this, I agree that my pull request should be closed if I do not fill this out or follow the guide lines. -->
+<!-- By submitting this, I agree that my pull request should be closed if I do not fill this out or follow the guidelines. -->

.github/workflows/benchmark.yml

@@ -0,0 +1,31 @@
+name: benchmark
+
+on:
+  workflow_dispatch:
+
+jobs:
+  build:
+    runs-on: ubuntu-latest
+    environment: benchmark
+    strategy:
+      matrix:
+        python-version: [3.8]
+
+    steps:
+    - name: Check out repository
+      uses: actions/checkout@v2
+
+    - name: Set up Python ${{ matrix.python-version }}
+      uses: actions/setup-python@v2
+      with:
+        python-version: ${{ matrix.python-version }}
+
+    - name: Install dependencies
+      run: |
+        python -m pip install --upgrade pip
+        pip install -r requirements.txt
+    - name: benchmark
+      run: |
+         python benchmark/benchmark_entrepeneur_gpt_with_undecisive_user.py
+      env:
+        OPENAI_API_KEY: ${{ secrets.OPENAI_API_KEY }}

.github/workflows/ci.yml

@@ -6,7 +6,10 @@ on:
       - master
   pull_request:
     branches:
-      - master
+      - '**'
+  pull_request_target:
+    branches:
+      - '**'
 
 jobs:
   build:
@@ -32,11 +35,19 @@ jobs:
 
     - name: Lint with flake8
       continue-on-error: false
-      run: flake8 autogpt/ tests/ --select E303,W293,W291,W292,E305,E231,E302
+      run: flake8
+
+    - name: Check black formatting
+      continue-on-error: false
+      run: black . --check
+
+    - name: Check isort formatting
+      continue-on-error: false
+      run: isort . --check
 
     - name: Run unittest tests with coverage
       run: |
-        coverage run --source=autogpt -m unittest discover tests
+        pytest --cov=autogpt --without-integration --without-slow-integration
 
     - name: Generate coverage report
       run: |

.github/workflows/docker-image.yml

@@ -0,0 +1,18 @@
+name: Docker Image CI
+
+on:
+  push:
+    branches: [ "master" ]
+  pull_request:
+    branches: [ "master" ]
+
+jobs:
+
+  build:
+
+    runs-on: ubuntu-latest
+
+    steps:
+    - uses: actions/checkout@v3
+    - name: Build the Docker image
+      run: docker build . --file Dockerfile --tag autogpt:$(date +%s)

.github/workflows/dockerhub-imagepush.yml

@@ -0,0 +1,24 @@
+name: Push Docker Image on Release
+
+on:
+  push:
+    branches: [ "stable" ]
+
+jobs:
+
+  build:
+
+    runs-on: ubuntu-latest
+
+    steps:
+    - uses: actions/checkout@v3
+    - name: Log in to Docker hub
+      env:
+        DOCKER_USER: ${{secrets.DOCKER_USER}}
+        DOCKER_PASSWORD: ${{secrets.DOCKER_PASSWORD}}
+      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`)
+    - name: Docker Push
+      run: docker push ${{secrets.DOCKER_USER}}/auto-gpt

.github/workflows/pr-label.yml

@@ -0,0 +1,28 @@
+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."

.gitignore

@@ -3,13 +3,13 @@ autogpt/keys.py
 autogpt/*json
 autogpt/node_modules/
 autogpt/__pycache__/keys.cpython-310.pyc
+autogpt/auto_gpt_workspace
 package-lock.json
 *.pyc
 auto_gpt_workspace/*
 *.mpeg
 .env
 azure.yaml
-*venv/*
 outputs/*
 ai_settings.yaml
 last_run_ai_settings.yaml
@@ -19,6 +19,8 @@ auto-gpt.json
 log.txt
 log-ingestion.txt
 logs
+*.log
+*.mp3
 
 # Byte-compiled / optimized / DLL files
 __pycache__/
@@ -125,13 +127,13 @@ celerybeat.pid
 *.sage.py
 
 # Environments
+.direnv/
 .env
 .venv
 env/
-venv/
+venv*/
 ENV/
 env.bak/
-venv.bak/
 
 # Spyder project settings
 .spyderproject
@@ -151,4 +153,7 @@ dmypy.json
 # Pyre type checker
 .pyre/
 llama-*
-vicuna-*
+vicuna-*
+
+# mac
+.DS_Store

.isort.cfg

@@ -1,10 +0,0 @@
-[settings]
-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
-skip = venv,env,node_modules,.env,.venv,dist
-sections = FUTURE,STDLIB,THIRDPARTY,FIRSTPARTY,LOCALFOLDER

.pre-commit-config.yaml

@@ -1,33 +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
+        language_version: python3.10
-        entry: isort
+
-        language: python
+  - repo: https://github.com/psf/black
-        types: [ python ]
+    rev: 23.3.0
-        exclude: .+/(dist|.venv|venv|build)/.+
+    hooks:
-        pass_filenames: true
       - id: black
-        name: black-local
+        language_version: python3.10
-        entry: black
+
-        language: python
+  - repo: local
-        types: [ python ]
+    hooks:
-        exclude: .+/(dist|.venv|venv|build)/.+
+      - id: pytest-check
-        pass_filenames: true
+        name: pytest-check
+        entry: pytest --cov=autogpt --without-integration --without-slow-integration
+        language: system
+        pass_filenames: false
+        always_run: true

CODE_OF_CONDUCT.md

@@ -0,0 +1,40 @@
+# Code of Conduct for auto-gpt
+
+## 1. Purpose
+
+The purpose of this Code of Conduct is to provide guidelines for contributors to the auto-gpt project on GitHub. We aim to create a positive and inclusive environment where all participants can contribute and collaborate effectively. By participating in this project, you agree to abide by this Code of Conduct.
+
+## 2. Scope
+
+This Code of Conduct applies to all contributors, maintainers, and users of the auto-gpt project. It extends to all project spaces, including but not limited to issues, pull requests, code reviews, comments, and other forms of communication within the project.
+
+## 3. Our Standards
+
+We encourage the following behavior:
+
+* Being respectful and considerate to others
+* Actively seeking diverse perspectives
+* Providing constructive feedback and assistance
+* Demonstrating empathy and understanding
+
+We discourage the following behavior:
+
+* Harassment or discrimination of any kind
+* Disrespectful, offensive, or inappropriate language or content
+* Personal attacks or insults
+* Unwarranted criticism or negativity
+
+## 4. Reporting and Enforcement
+
+If you witness or experience any violations of this Code of Conduct, please report them to the project maintainers by email or other appropriate means. The maintainers will investigate and take appropriate action, which may include warnings, temporary or permanent bans, or other measures as necessary.
+
+Maintainers are responsible for ensuring compliance with this Code of Conduct and may take action to address any violations.
+
+## 5. Acknowledgements
+
+This Code of Conduct is adapted from the [Contributor Covenant](https://www.contributor-covenant.org/version/2/0/code_of_conduct.html).
+
+## 6. Contact
+
+If you have any questions or concerns, please contact the project maintainers.
+

CONTRIBUTING.md

@@ -1,64 +1,105 @@
+# Contributing to ProjectName
 
-To contribute to this GitHub project, you can follow these steps:
+First of all, thank you for considering contributing to our project! We appreciate your time and effort, and we value any contribution, whether it's reporting a bug, suggesting a new feature, or submitting a pull request.
 
-1. Fork the repository you want to contribute to by clicking the "Fork" button on the project page.
+This document provides guidelines and best practices to help you contribute effectively.
 
-2. Clone the repository to your local machine using the following command:
+## Table of Contents
 
+- [Code of Conduct](#code-of-conduct)
+- [Getting Started](#getting-started)
+- [How to Contribute](#how-to-contribute)
+  - [Reporting Bugs](#reporting-bugs)
+  - [Suggesting Enhancements](#suggesting-enhancements)
+  - [Submitting Pull Requests](#submitting-pull-requests)
+- [Style Guidelines](#style-guidelines)
+  - [Code Formatting](#code-formatting)
+  - [Pre-Commit Hooks](#pre-commit-hooks)
+
+## Code of Conduct
+
+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:
+
+1. Fork the repository and clone your fork.
+2. Create a new branch for your changes (use a descriptive name, such as `fix-bug-123` or `add-new-feature`).
+3. Make your changes in the new branch.
+4. Test your changes thoroughly.
+5. Commit and push your changes to your fork.
+6. Create a pull request following the guidelines in the [Submitting Pull Requests](#submitting-pull-requests) section.
+
+## How to Contribute
+
+### Reporting Bugs
+
+If you find a bug in the project, please create an issue on GitHub with the following information:
+
+- A clear, descriptive title for the issue.
+- A description of the problem, including steps to reproduce the issue.
+- Any relevant logs, screenshots, or other supporting information.
+
+### Suggesting Enhancements
+
+If you have an idea for a new feature or improvement, please create an issue on GitHub with the following information:
+
+- A clear, descriptive title for the issue.
+- A detailed description of the proposed enhancement, including any benefits and potential drawbacks.
+- Any relevant examples, mockups, or supporting information.
+
+### Submitting Pull Requests
+
+When submitting a pull request, please ensure that your changes meet the following criteria:
+
+- Your pull request should be atomic and focus on a single change.
+- Your pull request should include tests for your change.
+- You should have thoroughly tested your changes with multiple different prompts.
+- You should have considered potential risks and mitigations for your changes.
+- You should have documented your changes clearly and comprehensively.
+- You should not include any unrelated or "extra" small tweaks or changes.
+
+## Style Guidelines
+
+### Code Formatting
+
+We use the `black` code formatter to maintain a consistent coding style across the project. Please ensure that your code is formatted using `black` before submitting a pull request. You can install `black` using `pip`:
+
+```bash
+pip install black
 ```
-git clone https://github.com/<YOUR-GITHUB-USERNAME>/Auto-GPT
+
+To format your code, run the following command in the project's root directory:
+
+```bash
+black .
 ```
-3. Install the project requirements
+### Pre-Commit Hooks
-```
+We use pre-commit hooks to ensure that code formatting and other checks are performed automatically before each commit. To set up pre-commit hooks for this project, follow these steps:
-pip install -r requirements.txt
+
-```
+Install the pre-commit package using pip:
-4. Install pre-commit hooks
+```bash
+pip install pre-commit
 ```
+
+Run the following command in the project's root directory to install the pre-commit hooks:
+```bash
 pre-commit install
 ```
-5. Create a new branch for your changes using the following command:
 
-```
+Now, the pre-commit hooks will run automatically before each commit, checking your code formatting and other requirements.
-git checkout -b "branch-name"
-```
-6. Make your changes to the code or documentation.
-- Example: Improve User Interface or Add Documentation.
 
+If you encounter any issues or have questions, feel free to reach out to the maintainers or open a new issue on GitHub. We're here to help and appreciate your efforts to contribute to the project.
 
-7. Add the changes to the staging area using the following command:
+Happy coding, and once again, thank you for your contributions!
-```
-git add .
-```
 
-8. Commit the changes with a meaningful commit message using the following command:
+Maintainers will look at PR that have no merge conflicts when deciding what to add to the project. Make sure your PR shows up here:
-```
-git commit -m "your commit message"
-```
-9. Push the changes to your forked repository using the following command:
-```
-git push origin branch-name
-```
-10. Go to the GitHub website and navigate to your forked repository.
 
-11. Click the "New pull request" button.
+https://github.com/Torantulino/Auto-GPT/pulls?q=is%3Apr+is%3Aopen+-is%3Aconflict+
-
-12. Select the branch you just pushed to and the branch you want to merge into on the original repository.
-
-13. Add a description of your changes and click the "Create pull request" button.
-
-14. Wait for the project maintainer to review your changes and provide feedback.
-
-15. Make any necessary changes based on feedback and repeat steps 5-12 until your changes are accepted and merged into the main project.
-
-16. Once your changes are merged, you can update your forked repository and local copy of the repository with the following commands:
-
-```
-git fetch upstream
-git checkout master
-git merge upstream/master
-```
-Finally, delete the branch you created with the following command:
-```
-git branch -d branch-name
-```
-That's it you made it 🐣⭐⭐

Dockerfile

@@ -1,6 +1,20 @@
 # Use an official Python base image from the Docker Hub
 FROM python:3.11-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 \
@@ -14,10 +28,11 @@ USER appuser
 
 # Copy the requirements.txt file and install the requirements
 COPY --chown=appuser:appuser requirements.txt .
-RUN pip install --no-cache-dir --user -r 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/ .
+COPY --chown=appuser:appuser autogpt/ ./autogpt
 
 # Set the entrypoint
 ENTRYPOINT ["python", "-m", "autogpt"]

autogpt/__main__.py

@@ -1,572 +1,5 @@
-import argparse
+"""Auto-GPT: A GPT powered AI Assistant"""
-import json
+import autogpt.cli
-import logging
-import traceback
-
-from colorama import Fore, Style
-
-from autogpt import chat
-from autogpt import commands as cmd
-from autogpt import speak, utils
-from autogpt.ai_config import AIConfig
-from autogpt.config import Config
-from autogpt.json_parser import fix_and_parse_json
-from autogpt.logger import logger
-from autogpt.memory import get_memory, get_supported_memory_backends
-from autogpt.spinner import Spinner
-
-cfg = Config()
-config = None
-
-
-def check_openai_api_key():
-    """Check if the OpenAI API key is set in config.py or as an environment variable."""
-    if not cfg.openai_api_key:
-        print(
-            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")
-        exit(1)
-
-
-def attempt_to_fix_json_by_finding_outermost_brackets(json_string):
-    if cfg.speak_mode and cfg.debug_mode:
-        speak.say_text(
-            "I have received an invalid JSON response from the OpenAI API. "
-            "Trying to fix it now."
-        )
-    logger.typewriter_log("Attempting to fix JSON by finding outermost brackets\n")
-
-    try:
-        # Use regex to search for JSON objects
-        import regex
-
-        json_pattern = regex.compile(r"\{(?:[^{}]|(?R))*\}")
-        json_match = json_pattern.search(json_string)
-
-        if json_match:
-            # Extract the valid JSON object from the string
-            json_string = json_match.group(0)
-            logger.typewriter_log(
-                title="Apparently json was fixed.", title_color=Fore.GREEN
-            )
-            if cfg.speak_mode and cfg.debug_mode:
-                speak.say_text("Apparently json was fixed.")
-        else:
-            raise ValueError("No valid JSON object found")
-
-    except (json.JSONDecodeError, ValueError) as e:
-        if cfg.debug_mode:
-            logger.error("Error: Invalid JSON: %s\n", json_string)
-        if cfg.speak_mode:
-            speak.say_text("Didn't work. I will have to ignore this response then.")
-        logger.error("Error: Invalid JSON, setting it to empty JSON now.\n")
-        json_string = {}
-
-    return json_string
-
-
-def print_assistant_thoughts(assistant_reply):
-    """Prints the assistant's thoughts to the console"""
-    global ai_name
-    global cfg
-    try:
-        try:
-            # Parse and print Assistant response
-            assistant_reply_json = fix_and_parse_json(assistant_reply)
-        except json.JSONDecodeError as e:
-            logger.error("Error: Invalid JSON in assistant thoughts\n", assistant_reply)
-            assistant_reply_json = attempt_to_fix_json_by_finding_outermost_brackets(
-                assistant_reply
-            )
-            assistant_reply_json = fix_and_parse_json(assistant_reply_json)
-
-        # Check if assistant_reply_json is a string and attempt to parse it into a
-        #  JSON object
-        if isinstance(assistant_reply_json, str):
-            try:
-                assistant_reply_json = json.loads(assistant_reply_json)
-            except json.JSONDecodeError as e:
-                logger.error("Error: Invalid JSON\n", assistant_reply)
-                assistant_reply_json = (
-                    attempt_to_fix_json_by_finding_outermost_brackets(
-                        assistant_reply_json
-                    )
-                )
-
-        assistant_thoughts_reasoning = None
-        assistant_thoughts_plan = None
-        assistant_thoughts_speak = None
-        assistant_thoughts_criticism = None
-        assistant_thoughts = assistant_reply_json.get("thoughts", {})
-        assistant_thoughts_text = assistant_thoughts.get("text")
-
-        if assistant_thoughts:
-            assistant_thoughts_reasoning = assistant_thoughts.get("reasoning")
-            assistant_thoughts_plan = assistant_thoughts.get("plan")
-            assistant_thoughts_criticism = assistant_thoughts.get("criticism")
-            assistant_thoughts_speak = assistant_thoughts.get("speak")
-
-        logger.typewriter_log(
-            f"{ai_name.upper()} THOUGHTS:", Fore.YELLOW, f"{assistant_thoughts_text}"
-        )
-        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
-            if isinstance(assistant_thoughts_plan, list):
-                assistant_thoughts_plan = "\n".join(assistant_thoughts_plan)
-            elif isinstance(assistant_thoughts_plan, dict):
-                assistant_thoughts_plan = str(assistant_thoughts_plan)
-
-            # Split the input_string using the newline character and dashes
-            lines = assistant_thoughts_plan.split("\n")
-            for line in lines:
-                line = line.lstrip("- ")
-                logger.typewriter_log("- ", Fore.GREEN, line.strip())
-
-        logger.typewriter_log(
-            "CRITICISM:", Fore.YELLOW, f"{assistant_thoughts_criticism}"
-        )
-        # Speak the assistant's thoughts
-        if cfg.speak_mode and assistant_thoughts_speak:
-            speak.say_text(assistant_thoughts_speak)
-
-        return assistant_reply_json
-    except json.decoder.JSONDecodeError:
-        call_stack = traceback.format_exc()
-        logger.error("Error: Invalid JSON\n", assistant_reply)
-        logger.error("Traceback: \n", call_stack)
-        if cfg.speak_mode:
-            speak.say_text(
-                "I have received an invalid JSON response from the OpenAI API."
-                " I cannot ignore this response."
-            )
-
-    # All other errors, return "Error: + error message"
-    except Exception:
-        call_stack = traceback.format_exc()
-        logger.error("Error: \n", call_stack)
-
-
-def construct_prompt():
-    """Construct the prompt for the AI to respond to"""
-    config: AIConfig = AIConfig.load(cfg.ai_settings_file)
-    if cfg.skip_reprompt and config.ai_name:
-        logger.typewriter_log("Name :", Fore.GREEN, config.ai_name)
-        logger.typewriter_log("Role :", Fore.GREEN, config.ai_role)
-        logger.typewriter_log("Goals:", Fore.GREEN, f"{config.ai_goals}")
-    elif config.ai_name:
-        logger.typewriter_log(
-            "Welcome back! ",
-            Fore.GREEN,
-            f"Would you like me to return to being {config.ai_name}?",
-            speak_text=True,
-        )
-        should_continue = utils.clean_input(
-            f"""Continue with the last settings?
-Name:  {config.ai_name}
-Role:  {config.ai_role}
-Goals: {config.ai_goals}
-Continue (y/n): """
-        )
-        if should_continue.lower() == "n":
-            config = AIConfig()
-
-    if not config.ai_name:
-        config = prompt_user()
-        config.save()
-
-    # Get rid of this global:
-    global ai_name
-    ai_name = config.ai_name
-
-    return config.construct_full_prompt()
-
-
-def prompt_user():
-    """Prompt the user for input"""
-    ai_name = ""
-    # Construct the prompt
-    logger.typewriter_log(
-        "Welcome to Auto-GPT! ",
-        Fore.GREEN,
-        "Enter the name of your AI and its role below. Entering nothing will load"
-        " defaults.",
-        speak_text=True,
-    )
-
-    # Get AI Name from User
-    logger.typewriter_log(
-        "Name your AI: ", Fore.GREEN, "For example, 'Entrepreneur-GPT'"
-    )
-    ai_name = utils.clean_input("AI Name: ")
-    if ai_name == "":
-        ai_name = "Entrepreneur-GPT"
-
-    logger.typewriter_log(
-        f"{ai_name} here!", Fore.LIGHTBLUE_EX, "I am at your service.", speak_text=True
-    )
-
-    # Get AI Role from User
-    logger.typewriter_log(
-        "Describe your AI's role: ",
-        Fore.GREEN,
-        "For example, 'an AI designed to autonomously develop and run businesses with"
-        " the sole goal of increasing your net worth.'",
-    )
-    ai_role = utils.clean_input(f"{ai_name} is: ")
-    if ai_role == "":
-        ai_role = "an AI designed to autonomously develop and run businesses with the"
-        " sole goal of increasing your net worth."
-
-    # Enter up to 5 goals for the AI
-    logger.typewriter_log(
-        "Enter up to 5 goals for your AI: ",
-        Fore.GREEN,
-        "For example: \nIncrease net worth, Grow Twitter Account, Develop and manage"
-        " multiple businesses autonomously'",
-    )
-    print("Enter nothing to load defaults, enter nothing when finished.", flush=True)
-    ai_goals = []
-    for i in range(5):
-        ai_goal = utils.clean_input(f"{Fore.LIGHTBLUE_EX}Goal{Style.RESET_ALL} {i+1}: ")
-        if ai_goal == "":
-            break
-        ai_goals.append(ai_goal)
-    if len(ai_goals) == 0:
-        ai_goals = [
-            "Increase net worth",
-            "Grow Twitter Account",
-            "Develop and manage multiple businesses autonomously",
-        ]
-
-    config = AIConfig(ai_name, ai_role, ai_goals)
-    return config
-
-
-def parse_arguments():
-    """Parses the arguments passed to the script"""
-    global cfg
-    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(
-        "--ai-settings",
-        "-C",
-        dest="ai_settings_file",
-        help="Specifies which ai_settings.yaml file to use, will also automatically"
-        " skip the re-prompt.",
-    )
-    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 not chosen 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
-
-
-def main():
-    global ai_name, memory
-    # 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 = ""
-    prompt = construct_prompt()
-    # print(prompt)
-    # Initialize variables
-    full_message_history = []
-    next_action_count = 0
-    # Make a constant:
-    user_input = (
-        "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)
-    print(f"Using memory of type: {memory.__class__.__name__}")
-    agent = Agent(
-        ai_name=ai_name,
-        memory=memory,
-        full_message_history=full_message_history,
-        next_action_count=next_action_count,
-        prompt=prompt,
-        user_input=user_input,
-    )
-    agent.start_interaction_loop()
-
-
-class Agent:
-    """Agent class for interacting with Auto-GPT.
-
-    Attributes:
-        ai_name: The name of the agent.
-        memory: The memory object to use.
-        full_message_history: The full message history.
-        next_action_count: The number of actions to execute.
-        prompt: The prompt to use.
-        user_input: The user input.
-
-    """
-
-    def __init__(
-        self,
-        ai_name,
-        memory,
-        full_message_history,
-        next_action_count,
-        prompt,
-        user_input,
-    ):
-        self.ai_name = ai_name
-        self.memory = memory
-        self.full_message_history = full_message_history
-        self.next_action_count = next_action_count
-        self.prompt = prompt
-        self.user_input = user_input
-
-    def start_interaction_loop(self):
-        # Interaction Loop
-        loop_count = 0
-        command_name = None
-        arguments = None
-        while True:
-            # Discontinue if continuous limit is reached
-            loop_count += 1
-            if (
-                cfg.continuous_mode
-                and cfg.continuous_limit > 0
-                and loop_count > cfg.continuous_limit
-            ):
-                logger.typewriter_log(
-                    "Continuous Limit Reached: ", Fore.YELLOW, f"{cfg.continuous_limit}"
-                )
-                break
-
-            # Send message to AI, get response
-            with Spinner("Thinking... "):
-                assistant_reply = chat.chat_with_ai(
-                    self.prompt,
-                    self.user_input,
-                    self.full_message_history,
-                    self.memory,
-                    cfg.fast_token_limit,
-                )  # TODO: This hardcodes the model to use GPT3.5. Make this an argument
-
-            # Print Assistant thoughts
-            print_assistant_thoughts(assistant_reply)
-
-            # Get command name and arguments
-            try:
-                command_name, arguments = cmd.get_command(
-                    attempt_to_fix_json_by_finding_outermost_brackets(assistant_reply)
-                )
-                if cfg.speak_mode:
-                    speak.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 key press: Prompt the user to press enter to continue or escape
-                # to exit
-                self.user_input = ""
-                logger.typewriter_log(
-                    "NEXT ACTION: ",
-                    Fore.CYAN,
-                    f"COMMAND = {Fore.CYAN}{command_name}{Style.RESET_ALL}"
-                    f"  ARGUMENTS = {Fore.CYAN}{arguments}{Style.RESET_ALL}",
-                )
-                print(
-                    "Enter 'y' to authorise command, 'y -N' to run N continuous"
-                    " commands, 'n' to exit program, or enter feedback for"
-                    f" {self.ai_name}...",
-                    flush=True,
-                )
-                while True:
-                    console_input = utils.clean_input(
-                        Fore.MAGENTA + "Input:" + Style.RESET_ALL
-                    )
-                    if console_input.lower().rstrip() == "y":
-                        self.user_input = "GENERATE NEXT COMMAND JSON"
-                        break
-                    elif console_input.lower().startswith("y -"):
-                        try:
-                            self.next_action_count = abs(
-                                int(console_input.split(" ")[1])
-                            )
-                            self.user_input = "GENERATE NEXT COMMAND JSON"
-                        except ValueError:
-                            print(
-                                "Invalid input format. Please enter 'y -n' where n"
-                                " is the number of continuous tasks."
-                            )
-                            continue
-                        break
-                    elif console_input.lower() == "n":
-                        self.user_input = "EXIT"
-                        break
-                    else:
-                        self.user_input = console_input
-                        command_name = "human_feedback"
-                        break
-
-                if self.user_input == "GENERATE NEXT COMMAND JSON":
-                    logger.typewriter_log(
-                        "-=-=-=-=-=-=-= COMMAND AUTHORISED BY USER -=-=-=-=-=-=-=",
-                        Fore.MAGENTA,
-                        "",
-                    )
-                elif self.user_input == "EXIT":
-                    print("Exiting...", flush=True)
-                    break
-            else:
-                # Print command
-                logger.typewriter_log(
-                    "NEXT ACTION: ",
-                    Fore.CYAN,
-                    f"COMMAND = {Fore.CYAN}{command_name}{Style.RESET_ALL}"
-                    f"  ARGUMENTS = {Fore.CYAN}{arguments}{Style.RESET_ALL}",
-                )
-
-            # Execute command
-            if command_name is not None and command_name.lower().startswith("error"):
-                result = (
-                    f"Command {command_name} threw the following error: {arguments}"
-                )
-            elif command_name == "human_feedback":
-                result = f"Human feedback: {self.user_input}"
-            else:
-                result = (
-                    f"Command {command_name} "
-                    f"returned: {cmd.execute_command(command_name, arguments)}"
-                )
-                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: {self.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(
-                    chat.create_chat_message("system", result)
-                )
-                logger.typewriter_log("SYSTEM: ", Fore.YELLOW, result)
-            else:
-                self.full_message_history.append(
-                    chat.create_chat_message("system", "Unable to execute command")
-                )
-                logger.typewriter_log(
-                    "SYSTEM: ", Fore.YELLOW, "Unable to execute command"
-                )
-
 
 if __name__ == "__main__":
-    main()
+    autogpt.cli.main()

autogpt/agent.py

@@ -1,304 +0,0 @@
-import json
-import regex
-import traceback
-
-from colorama import Fore, Style
-
-from autogpt.chat import chat_with_ai, create_chat_message
-import autogpt.commands as cmd
-from autogpt.config import Config
-from autogpt.json_parser import fix_and_parse_json
-from autogpt.logger import logger
-from autogpt.speak import say_text
-from autogpt.spinner import Spinner
-from autogpt.utils import clean_input
-
-
-class Agent:
-    """Agent class for interacting with Auto-GPT.
-
-    Attributes:
-        ai_name: The name of the agent.
-        memory: The memory object to use.
-        full_message_history: The full message history.
-        next_action_count: The number of actions to execute.
-        prompt: The prompt to use.
-        user_input: The user input.
-
-    """
-
-    def __init__(
-        self,
-        ai_name,
-        memory,
-        full_message_history,
-        next_action_count,
-        prompt,
-        user_input,
-    ):
-        self.ai_name = ai_name
-        self.memory = memory
-        self.full_message_history = full_message_history
-        self.next_action_count = next_action_count
-        self.prompt = prompt
-        self.user_input = user_input
-
-    def start_interaction_loop(self):
-        # Interaction Loop
-        cfg = Config()
-        loop_count = 0
-        command_name = None
-        arguments = None
-        while True:
-            # Discontinue if continuous limit is reached
-            loop_count += 1
-            if (
-                cfg.continuous_mode
-                and cfg.continuous_limit > 0
-                and loop_count > cfg.continuous_limit
-            ):
-                logger.typewriter_log(
-                    "Continuous Limit Reached: ", Fore.YELLOW, f"{cfg.continuous_limit}"
-                )
-                break
-
-            # Send message to AI, get response
-            with Spinner("Thinking... "):
-                assistant_reply = chat_with_ai(
-                    self.prompt,
-                    self.user_input,
-                    self.full_message_history,
-                    self.memory,
-                    cfg.fast_token_limit,
-                )  # TODO: This hardcodes the model to use GPT3.5. Make this an argument
-
-            # Print Assistant thoughts
-            print_assistant_thoughts(self.ai_name, assistant_reply)
-
-            # Get command name and arguments
-            try:
-                command_name, arguments = cmd.get_command(
-                    attempt_to_fix_json_by_finding_outermost_brackets(assistant_reply)
-                )
-                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 key press: Prompt the user to press enter to continue or escape
-                # to exit
-                self.user_input = ""
-                logger.typewriter_log(
-                    "NEXT ACTION: ",
-                    Fore.CYAN,
-                    f"COMMAND = {Fore.CYAN}{command_name}{Style.RESET_ALL}  "
-                    f"ARGUMENTS = {Fore.CYAN}{arguments}{Style.RESET_ALL}",
-                )
-                print(
-                    "Enter 'y' to authorise command, 'y -N' to run N continuous "
-                    "commands, 'n' to exit program, or enter feedback for "
-                    f"{self.ai_name}...",
-                    flush=True,
-                )
-                while True:
-                    console_input = clean_input(
-                        Fore.MAGENTA + "Input:" + Style.RESET_ALL
-                    )
-                    if console_input.lower().rstrip() == "y":
-                        self.user_input = "GENERATE NEXT COMMAND JSON"
-                        break
-                    elif console_input.lower().startswith("y -"):
-                        try:
-                            self.next_action_count = abs(
-                                int(console_input.split(" ")[1])
-                            )
-                            self.user_input = "GENERATE NEXT COMMAND JSON"
-                        except ValueError:
-                            print(
-                                "Invalid input format. Please enter 'y -n' where n is"
-                                " the number of continuous tasks."
-                            )
-                            continue
-                        break
-                    elif console_input.lower() == "n":
-                        self.user_input = "EXIT"
-                        break
-                    else:
-                        self.user_input = console_input
-                        command_name = "human_feedback"
-                        break
-
-                if self.user_input == "GENERATE NEXT COMMAND JSON":
-                    logger.typewriter_log(
-                        "-=-=-=-=-=-=-= COMMAND AUTHORISED BY USER -=-=-=-=-=-=-=",
-                        Fore.MAGENTA,
-                        "",
-                    )
-                elif self.user_input == "EXIT":
-                    print("Exiting...", flush=True)
-                    break
-            else:
-                # Print command
-                logger.typewriter_log(
-                    "NEXT ACTION: ",
-                    Fore.CYAN,
-                    f"COMMAND = {Fore.CYAN}{command_name}{Style.RESET_ALL}"
-                    f"  ARGUMENTS = {Fore.CYAN}{arguments}{Style.RESET_ALL}",
-                )
-
-            # Execute command
-            if command_name is not None and command_name.lower().startswith("error"):
-                result = (
-                    f"Command {command_name} threw the following error: {arguments}"
-                )
-            elif command_name == "human_feedback":
-                result = f"Human feedback: {self.user_input}"
-            else:
-                result = (
-                    f"Command {command_name} returned: "
-                    f"{cmd.execute_command(command_name, arguments)}"
-                )
-                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: {self.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"
-                )
-
-
-def attempt_to_fix_json_by_finding_outermost_brackets(json_string):
-    cfg = Config()
-    if cfg.speak_mode and cfg.debug_mode:
-        say_text(
-            "I have received an invalid JSON response from the OpenAI API. "
-            "Trying to fix it now."
-        )
-    logger.typewriter_log("Attempting to fix JSON by finding outermost brackets\n")
-
-    try:
-        json_pattern = regex.compile(r"\{(?:[^{}]|(?R))*\}")
-        json_match = json_pattern.search(json_string)
-
-        if json_match:
-            # Extract the valid JSON object from the string
-            json_string = json_match.group(0)
-            logger.typewriter_log(
-                title="Apparently json was fixed.", title_color=Fore.GREEN
-            )
-            if cfg.speak_mode and cfg.debug_mode:
-                say_text("Apparently json was fixed.")
-        else:
-            raise ValueError("No valid JSON object found")
-
-    except (json.JSONDecodeError, ValueError):
-        if cfg.speak_mode:
-            say_text("Didn't work. I will have to ignore this response then.")
-        logger.error("Error: Invalid JSON, setting it to empty JSON now.\n")
-        json_string = {}
-
-    return json_string
-
-
-def print_assistant_thoughts(ai_name, assistant_reply):
-    """Prints the assistant's thoughts to the console"""
-    cfg = Config()
-    try:
-        try:
-            # Parse and print Assistant response
-            assistant_reply_json = fix_and_parse_json(assistant_reply)
-        except json.JSONDecodeError:
-            logger.error("Error: Invalid JSON in assistant thoughts\n", assistant_reply)
-            assistant_reply_json = attempt_to_fix_json_by_finding_outermost_brackets(
-                assistant_reply
-            )
-            if isinstance(assistant_reply_json, str):
-                assistant_reply_json = fix_and_parse_json(assistant_reply_json)
-
-        # Check if assistant_reply_json is a string and attempt to parse
-        # it into a JSON object
-        if isinstance(assistant_reply_json, str):
-            try:
-                assistant_reply_json = json.loads(assistant_reply_json)
-            except json.JSONDecodeError:
-                logger.error("Error: Invalid JSON\n", assistant_reply)
-                assistant_reply_json = (
-                    attempt_to_fix_json_by_finding_outermost_brackets(
-                        assistant_reply_json
-                    )
-                )
-
-        assistant_thoughts_reasoning = None
-        assistant_thoughts_plan = None
-        assistant_thoughts_speak = None
-        assistant_thoughts_criticism = None
-        if not isinstance(assistant_reply_json, dict):
-            assistant_reply_json = {}
-        assistant_thoughts = assistant_reply_json.get("thoughts", {})
-        assistant_thoughts_text = assistant_thoughts.get("text")
-
-        if assistant_thoughts:
-            assistant_thoughts_reasoning = assistant_thoughts.get("reasoning")
-            assistant_thoughts_plan = assistant_thoughts.get("plan")
-            assistant_thoughts_criticism = assistant_thoughts.get("criticism")
-            assistant_thoughts_speak = assistant_thoughts.get("speak")
-
-        logger.typewriter_log(
-            f"{ai_name.upper()} THOUGHTS:", Fore.YELLOW, f"{assistant_thoughts_text}"
-        )
-        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
-            if isinstance(assistant_thoughts_plan, list):
-                assistant_thoughts_plan = "\n".join(assistant_thoughts_plan)
-            elif isinstance(assistant_thoughts_plan, dict):
-                assistant_thoughts_plan = str(assistant_thoughts_plan)
-
-            # Split the input_string using the newline character and dashes
-            lines = assistant_thoughts_plan.split("\n")
-            for line in lines:
-                line = line.lstrip("- ")
-                logger.typewriter_log("- ", Fore.GREEN, line.strip())
-
-        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)
-
-        return assistant_reply_json
-    except json.decoder.JSONDecodeError:
-        logger.error("Error: Invalid JSON\n", assistant_reply)
-        if cfg.speak_mode:
-            say_text(
-                "I have received an invalid JSON response from the OpenAI API."
-                " I cannot ignore this response."
-            )
-
-    # All other errors, return "Error: + error message"
-    except Exception:
-        call_stack = traceback.format_exc()
-        logger.error("Error: \n", call_stack)

autogpt/agent/__init__.py

@@ -0,0 +1,4 @@
+from autogpt.agent.agent import Agent
+from autogpt.agent.agent_manager import AgentManager
+
+__all__ = ["Agent", "AgentManager"]

autogpt/agent/agent.py

@@ -0,0 +1,197 @@
+from colorama import Fore, Style
+
+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.logs import logger, print_assistant_thoughts
+from autogpt.speech import say_text
+from autogpt.spinner import Spinner
+from autogpt.utils import clean_input
+
+
+class Agent:
+    """Agent class for interacting with Auto-GPT.
+
+    Attributes:
+        ai_name: The name of the 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.
+
+        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)
+    """
+
+    def __init__(
+        self,
+        ai_name,
+        memory,
+        full_message_history,
+        next_action_count,
+        system_prompt,
+        triggering_prompt,
+    ):
+        self.ai_name = ai_name
+        self.memory = memory
+        self.full_message_history = full_message_history
+        self.next_action_count = next_action_count
+        self.system_prompt = system_prompt
+        self.triggering_prompt = triggering_prompt
+
+    def start_interaction_loop(self):
+        # Interaction Loop
+        cfg = Config()
+        loop_count = 0
+        command_name = None
+        arguments = None
+        user_input = ""
+
+        while True:
+            # Discontinue if continuous limit is reached
+            loop_count += 1
+            if (
+                cfg.continuous_mode
+                and cfg.continuous_limit > 0
+                and loop_count > cfg.continuous_limit
+            ):
+                logger.typewriter_log(
+                    "Continuous Limit Reached: ", Fore.YELLOW, f"{cfg.continuous_limit}"
+                )
+                break
+
+            # Send message to AI, get response
+            with Spinner("Thinking... "):
+                assistant_reply = chat_with_ai(
+                    self.system_prompt,
+                    self.triggering_prompt,
+                    self.full_message_history,
+                    self.memory,
+                    cfg.fast_token_limit,
+                )  # TODO: This hardcodes the model to use GPT3.5. Make this an argument
+
+            assistant_reply_json = fix_json_using_multiple_techniques(assistant_reply)
+
+            # Print Assistant thoughts
+            if assistant_reply_json != {}:
+                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 key press: Prompt the user to press enter to continue or escape
+                # to exit
+                logger.typewriter_log(
+                    "NEXT ACTION: ",
+                    Fore.CYAN,
+                    f"COMMAND = {Fore.CYAN}{command_name}{Style.RESET_ALL}  "
+                    f"ARGUMENTS = {Fore.CYAN}{arguments}{Style.RESET_ALL}",
+                )
+                print(
+                    "Enter 'y' to authorise command, 'y -N' to run N continuous "
+                    "commands, 'n' to exit program, or enter feedback for "
+                    f"{self.ai_name}...",
+                    flush=True,
+                )
+                while True:
+                    console_input = clean_input(
+                        Fore.MAGENTA + "Input:" + Style.RESET_ALL
+                    )
+                    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(
+                                int(console_input.split(" ")[1])
+                            )
+                            user_input = "GENERATE NEXT COMMAND JSON"
+                        except ValueError:
+                            print(
+                                "Invalid input format. Please enter 'y -n' where n is"
+                                " the number of continuous tasks."
+                            )
+                            continue
+                        break
+                    elif console_input.lower() == "n":
+                        user_input = "EXIT"
+                        break
+                    else:
+                        user_input = console_input
+                        command_name = "human_feedback"
+                        break
+
+                if user_input == "GENERATE NEXT COMMAND JSON":
+                    logger.typewriter_log(
+                        "-=-=-=-=-=-=-= COMMAND AUTHORISED BY USER -=-=-=-=-=-=-=",
+                        Fore.MAGENTA,
+                        "",
+                    )
+                elif user_input == "EXIT":
+                    print("Exiting...", flush=True)
+                    break
+            else:
+                # Print command
+                logger.typewriter_log(
+                    "NEXT ACTION: ",
+                    Fore.CYAN,
+                    f"COMMAND = {Fore.CYAN}{command_name}{Style.RESET_ALL}"
+                    f"  ARGUMENTS = {Fore.CYAN}{arguments}{Style.RESET_ALL}",
+                )
+
+            # Execute command
+            if command_name is not None and command_name.lower().startswith("error"):
+                result = (
+                    f"Command {command_name} threw the following error: {arguments}"
+                )
+            elif command_name == "human_feedback":
+                result = f"Human feedback: {user_input}"
+            else:
+                result = (
+                    f"Command {command_name} returned: "
+                    f"{execute_command(command_name, arguments)}"
+                )
+                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"
+                )

autogpt/agent/agent_manager.py

@@ -0,0 +1,103 @@
+"""Agent manager for managing GPT agents"""
+from __future__ import annotations
+
+from typing import Union
+
+from autogpt.config.config import Singleton
+from autogpt.llm_utils import create_chat_completion
+
+
+class AgentManager(metaclass=Singleton):
+    """Agent manager for managing GPT agents"""
+
+    def __init__(self):
+        self.next_key = 0
+        self.agents = {}  # key, (task, full_message_history, model)
+
+    # Create new GPT agent
+    # TODO: Centralise use of create_chat_completion() to globally enforce token limit
+
+    def create_agent(self, task: str, prompt: str, model: str) -> tuple[int, str]:
+        """Create a new agent and return its key
+
+        Args:
+            task: The task to perform
+            prompt: The prompt to use
+            model: The model to use
+
+        Returns:
+            The key of the new agent
+        """
+        messages = [
+            {"role": "user", "content": prompt},
+        ]
+
+        # Start GPT instance
+        agent_reply = create_chat_completion(
+            model=model,
+            messages=messages,
+        )
+
+        # Update full message history
+        messages.append({"role": "assistant", "content": agent_reply})
+
+        key = self.next_key
+        # This is done instead of len(agents) to make keys unique even if agents
+        # are deleted
+        self.next_key += 1
+
+        self.agents[key] = (task, messages, model)
+
+        return key, agent_reply
+
+    def message_agent(self, key: str | int, message: str) -> str:
+        """Send a message to an agent and return its response
+
+        Args:
+            key: The key of the agent to message
+            message: The message to send to the agent
+
+        Returns:
+            The agent's response
+        """
+        task, messages, model = self.agents[int(key)]
+
+        # Add user message to message history before sending to agent
+        messages.append({"role": "user", "content": message})
+
+        # Start GPT instance
+        agent_reply = create_chat_completion(
+            model=model,
+            messages=messages,
+        )
+
+        # Update full message history
+        messages.append({"role": "assistant", "content": agent_reply})
+
+        return agent_reply
+
+    def list_agents(self) -> list[tuple[str | int, str]]:
+        """Return a list of all agents
+
+        Returns:
+            A list of tuples of the form (key, task)
+        """
+
+        # 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:
+        """Delete an agent from the agent manager
+
+        Args:
+            key: The key of the agent to delete
+
+        Returns:
+            True if successful, False otherwise
+        """
+
+        try:
+            del self.agents[int(key)]
+            return True
+        except KeyError:
+            return False

autogpt/agent_manager.py

@@ -1,75 +0,0 @@
-from autogpt.llm_utils import create_chat_completion
-
-next_key = 0
-agents = {}  # key, (task, full_message_history, model)
-
-# Create new GPT agent
-# TODO: Centralise use of create_chat_completion() to globally enforce token limit
-
-
-def create_agent(task, prompt, model):
-    """Create a new agent and return its key"""
-    global next_key
-    global agents
-
-    messages = [
-        {"role": "user", "content": prompt},
-    ]
-
-    # Start GPT instance
-    agent_reply = create_chat_completion(
-        model=model,
-        messages=messages,
-    )
-
-    # Update full message history
-    messages.append({"role": "assistant", "content": agent_reply})
-
-    key = next_key
-    # This is done instead of len(agents) to make keys unique even if agents
-    # are deleted
-    next_key += 1
-
-    agents[key] = (task, messages, model)
-
-    return key, agent_reply
-
-
-def message_agent(key, message):
-    """Send a message to an agent and return its response"""
-    global agents
-
-    task, messages, model = agents[int(key)]
-
-    # Add user message to message history before sending to agent
-    messages.append({"role": "user", "content": message})
-
-    # Start GPT instance
-    agent_reply = create_chat_completion(
-        model=model,
-        messages=messages,
-    )
-
-    # Update full message history
-    messages.append({"role": "assistant", "content": agent_reply})
-
-    return agent_reply
-
-
-def list_agents():
-    """Return a list of all agents"""
-    global agents
-
-    # Return a list of agent keys and their tasks
-    return [(key, task) for key, (task, _, _) in agents.items()]
-
-
-def delete_agent(key):
-    """Delete an agent and return True if successful, False otherwise"""
-    global agents
-
-    try:
-        del agents[int(key)]
-        return True
-    except KeyError:
-        return False

autogpt/ai_functions.py

@@ -1,77 +0,0 @@
-import json
-from typing import List
-
-from autogpt.call_ai_function import call_ai_function
-from autogpt.config import Config
-
-cfg = Config()
-
-
-def evaluate_code(code: str) -> List[str]:
-    """
-    A function that takes in a string and returns a response from create chat
-      completion api call.
-
-    Parameters:
-        code (str): Code to be evaluated.
-    Returns:
-        A result string from create chat completion. A list of suggestions to
-            improve the code.
-    """
-
-    function_string = "def analyze_code(code: str) -> List[str]:"
-    args = [code]
-    description_string = (
-        "Analyzes the given code and returns a list of suggestions" " for improvements."
-    )
-
-    return call_ai_function(function_string, args, description_string)
-
-
-def improve_code(suggestions: List[str], code: str) -> str:
-    """
-    A function that takes in code and suggestions and returns a response from create
-      chat completion api call.
-
-    Parameters:
-        suggestions (List): A list of suggestions around what needs to be improved.
-        code (str): Code to be improved.
-    Returns:
-        A result string from create chat completion. Improved code in response.
-    """
-
-    function_string = (
-        "def generate_improved_code(suggestions: List[str], code: str) -> str:"
-    )
-    args = [json.dumps(suggestions), code]
-    description_string = (
-        "Improves the provided code based on the suggestions"
-        " provided, making no other changes."
-    )
-
-    return call_ai_function(function_string, args, description_string)
-
-
-def write_tests(code: str, focus: List[str]) -> str:
-    """
-    A function that takes in code and focus topics and returns a response from create
-      chat completion api call.
-
-    Parameters:
-        focus (List): A list of suggestions around what needs to be improved.
-        code (str): Code for test cases to be generated against.
-    Returns:
-        A result string from create chat completion. Test cases for the submitted code
-          in response.
-    """
-
-    function_string = (
-        "def create_test_cases(code: str, focus: Optional[str] = None) -> str:"
-    )
-    args = [code, json.dumps(focus)]
-    description_string = (
-        "Generates test cases for the existing code, focusing on"
-        " specific areas if required."
-    )
-
-    return call_ai_function(function_string, args, description_string)

autogpt/app.py

@@ -0,0 +1,330 @@
+""" Command and Control """
+import json
+from typing import Dict, List, NoReturn, Union
+
+from autogpt.agent.agent_manager import AgentManager
+from autogpt.commands.audio_text import read_audio_from_file
+from autogpt.commands.evaluate_code import evaluate_code
+from autogpt.commands.execute_code import (
+    execute_python_file,
+    execute_shell,
+    execute_shell_popen,
+)
+from autogpt.commands.file_operations import (
+    append_to_file,
+    delete_file,
+    download_file,
+    read_file,
+    search_files,
+    write_to_file,
+)
+from autogpt.commands.git_operations import clone_repository
+from autogpt.commands.google_search import google_official_search, google_search
+from autogpt.commands.image_gen import generate_image
+from autogpt.commands.improve_code import improve_code
+from autogpt.commands.twitter import send_tweet
+from autogpt.commands.web_requests import scrape_links, scrape_text
+from autogpt.commands.web_selenium import browse_website
+from autogpt.commands.write_tests import write_tests
+from autogpt.config import Config
+from autogpt.json_fixes.parsing import fix_and_parse_json
+from autogpt.memory import get_memory
+from autogpt.processing.text import summarize_text
+from autogpt.speech import say_text
+
+CFG = Config()
+AGENT_MANAGER = AgentManager()
+
+
+def is_valid_int(value: str) -> bool:
+    """Check if the value is a valid integer
+
+    Args:
+        value (str): The value to check
+
+    Returns:
+        bool: True if the value is a valid integer, False otherwise
+    """
+    try:
+        int(value)
+        return True
+    except ValueError:
+        return False
+
+
+def get_command(response_json: Dict):
+    """Parse the response and return the command name and arguments
+
+    Args:
+        response_json (json): The response from the AI
+
+    Returns:
+        tuple: The command name and arguments
+
+    Raises:
+        json.decoder.JSONDecodeError: If the response is not valid JSON
+
+        Exception: If any other error occurs
+    """
+    try:
+        if "command" not in response_json:
+            return "Error:", "Missing 'command' object in JSON"
+
+        if not isinstance(response_json, dict):
+            return "Error:", f"'response_json' object is not dictionary {response_json}"
+
+        command = response_json["command"]
+        if not isinstance(command, dict):
+            return "Error:", "'command' object is not a dictionary"
+
+        if "name" not in command:
+            return "Error:", "Missing 'name' field in 'command' object"
+
+        command_name = command["name"]
+
+        # Use an empty dictionary if 'args' field is not present in 'command' object
+        arguments = command.get("args", {})
+
+        return command_name, arguments
+    except json.decoder.JSONDecodeError:
+        return "Error:", "Invalid JSON"
+    # All other errors, return "Error: + error message"
+    except Exception as e:
+        return "Error:", str(e)
+
+
+def map_command_synonyms(command_name: str):
+    """Takes the original command name given by the AI, and checks if the
+    string matches a list of common/known hallucinations
+    """
+    synonyms = [
+        ("write_file", "write_to_file"),
+        ("create_file", "write_to_file"),
+        ("search", "google"),
+    ]
+    for seen_command, actual_command_name in synonyms:
+        if command_name == seen_command:
+            return actual_command_name
+    return command_name
+
+
+def execute_command(command_name: str, arguments):
+    """Execute the command and return the result
+
+    Args:
+        command_name (str): The name of the command to execute
+        arguments (dict): The arguments for the command
+
+    Returns:
+        str: The result of the command
+    """
+    try:
+        command_name = map_command_synonyms(command_name.lower())
+        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"])
+
+            # 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")
+
+            return safe_message.decode("utf-8")
+        elif command_name == "memory_add":
+            memory = get_memory(CFG)
+            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 == "execute_shell_popen":
+            if CFG.execute_local_commands:
+                return execute_shell_popen(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"])
+        elif command_name == "do_nothing":
+            return "No action performed."
+        elif command_name == "task_complete":
+            shutdown()
+        else:
+            return (
+                f"Unknown command '{command_name}'. Please refer to the 'COMMANDS'"
+                " list for available commands and only respond in the specified JSON"
+                " format."
+            )
+    except Exception as e:
+        return f"Error: {str(e)}"
+
+
+def get_text_summary(url: str, question: str) -> str:
+    """Return the results of a Google search
+
+    Args:
+        url (str): The url to scrape
+        question (str): The question to summarize the text for
+
+    Returns:
+        str: The summary of the text
+    """
+    text = scrape_text(url)
+    summary = summarize_text(url, text, question)
+    return f""" "Result" : {summary}"""
+
+
+def get_hyperlinks(url: str) -> Union[str, List[str]]:
+    """Return the results of a Google search
+
+    Args:
+        url (str): The url to scrape
+
+    Returns:
+        str or list: The hyperlinks on the page
+    """
+    return scrape_links(url)
+
+
+def shutdown() -> NoReturn:
+    """Shut down the program"""
+    print("Shutting down...")
+    quit()
+
+
+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
+
+    Args:
+        name (str): The name of the agent
+        task (str): The task of the agent
+        prompt (str): The prompt for the agent
+        model (str): The model to use for the agent
+
+    Returns:
+        str: The response of the agent
+    """
+    # Remove underscores from name
+    voice_name = name.replace("_", " ")
+
+    first_message = f"""You are {name}.  Respond with: "Acknowledged"."""
+    agent_intro = f"{voice_name} here, Reporting for duty!"
+
+    # Create agent
+    if CFG.speak_mode:
+        say_text(agent_intro, 1)
+    key, ack = AGENT_MANAGER.create_agent(task, first_message, model)
+
+    if CFG.speak_mode:
+        say_text(f"Hello {voice_name}. Your task is as follows. {task}.")
+
+    # Assign task (prompt), get response
+    agent_response = AGENT_MANAGER.message_agent(key, prompt)
+
+    return f"Agent {name} created with key {key}. First response: {agent_response}"
+
+
+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
+    if is_valid_int(key):
+        agent_response = AGENT_MANAGER.message_agent(int(key), message)
+    else:
+        return "Invalid key, must be an integer."
+
+    # Speak response
+    if CFG.speak_mode:
+        say_text(agent_response, 1)
+    return agent_response
+
+
+def list_agents():
+    """List all agents
+
+    Returns:
+        str: A list of all agents
+    """
+    return "List of agents:\n" + "\n".join(
+        [str(x[0]) + ": " + x[1] for x in AGENT_MANAGER.list_agents()]
+    )
+
+
+def delete_agent(key: str) -> str:
+    """Delete an agent with a given key
+
+    Args:
+        key (str): The key of the agent to delete
+
+    Returns:
+        str: A message indicating whether the agent was deleted or not
+    """
+    result = AGENT_MANAGER.delete_agent(key)
+    return f"Agent {key} deleted." if result else f"Agent {key} does not exist."

autogpt/browse.py

@@ -1,198 +0,0 @@
-from urllib.parse import urljoin, urlparse
-
-import requests
-from bs4 import BeautifulSoup
-
-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)
-
-session = requests.Session()
-session.headers.update({"User-Agent": cfg.user_agent})
-
-
-# Function to check if the URL is valid
-def is_valid_url(url):
-    try:
-        result = urlparse(url)
-        return all([result.scheme, result.netloc])
-    except ValueError:
-        return False
-
-
-# Function to sanitize the URL
-def sanitize_url(url):
-    return urljoin(url, urlparse(url).path)
-
-
-# Define and check for local file address prefixes
-def check_local_file_access(url):
-    local_prefixes = [
-        "file:///",
-        "file://localhost",
-        "http://localhost",
-        "https://localhost",
-    ]
-    return any(url.startswith(prefix) for prefix in local_prefixes)
-
-
-def get_response(url, timeout=10):
-    try:
-        # Restrict access to local files
-        if check_local_file_access(url):
-            raise ValueError("Access to local files is restricted")
-
-        # Most basic check if the URL is valid:
-        if not url.startswith("http://") and not url.startswith("https://"):
-            raise ValueError("Invalid URL format")
-
-        sanitized_url = sanitize_url(url)
-
-        response = session.get(sanitized_url, timeout=timeout)
-
-        # Check if the response contains an HTTP error
-        if response.status_code >= 400:
-            return None, "Error: HTTP " + str(response.status_code) + " error"
-
-        return response, None
-    except ValueError as ve:
-        # Handle invalid URL format
-        return None, "Error: " + str(ve)
-
-    except requests.exceptions.RequestException as re:
-        # Handle exceptions related to the HTTP request
-        #  (e.g., connection errors, timeouts, etc.)
-        return None, "Error: " + str(re)
-
-
-def scrape_text(url):
-    """Scrape text from a webpage"""
-    response, error_message = get_response(url)
-    if error_message:
-        return error_message
-    if not response:
-        return "Error: Could not get response"
-
-    soup = BeautifulSoup(response.text, "html.parser")
-
-    for script in soup(["script", "style"]):
-        script.extract()
-
-    text = soup.get_text()
-    lines = (line.strip() for line in text.splitlines())
-    chunks = (phrase.strip() for line in lines for phrase in line.split("  "))
-    text = "\n".join(chunk for chunk in chunks if chunk)
-
-    return text
-
-
-def extract_hyperlinks(soup):
-    """Extract hyperlinks from a BeautifulSoup object"""
-    hyperlinks = []
-    for link in soup.find_all("a", href=True):
-        hyperlinks.append((link.text, link["href"]))
-    return hyperlinks
-
-
-def format_hyperlinks(hyperlinks):
-    """Format hyperlinks into a list of strings"""
-    formatted_links = []
-    for link_text, link_url in hyperlinks:
-        formatted_links.append(f"{link_text} ({link_url})")
-    return formatted_links
-
-
-def scrape_links(url):
-    """Scrape links from a webpage"""
-    response, error_message = get_response(url)
-    if error_message:
-        return error_message
-    if not response:
-        return "Error: Could not get response"
-    soup = BeautifulSoup(response.text, "html.parser")
-
-    for script in soup(["script", "style"]):
-        script.extract()
-
-    hyperlinks = extract_hyperlinks(soup)
-
-    return format_hyperlinks(hyperlinks)
-
-
-def split_text(text, max_length=cfg.browse_chunk_max_length):
-    """Split text into chunks of a maximum length"""
-    paragraphs = text.split("\n")
-    current_length = 0
-    current_chunk = []
-
-    for paragraph in paragraphs:
-        if current_length + len(paragraph) + 1 <= max_length:
-            current_chunk.append(paragraph)
-            current_length += len(paragraph) + 1
-        else:
-            yield "\n".join(current_chunk)
-            current_chunk = [paragraph]
-            current_length = len(paragraph) + 1
-
-    if current_chunk:
-        yield "\n".join(current_chunk)
-
-
-def create_message(chunk, question):
-    """Create a message for the user to summarize a chunk of text"""
-    return {
-        "role": "user",
-        "content": f'"""{chunk}""" Using the above text, please answer the following'
-        f' question: "{question}" -- if the question cannot be answered using the'
-        " text, please summarize the text.",
-    }
-
-
-def summarize_text(url, text, question):
-    """Summarize text using the LLM model"""
-    if not text:
-        return "Error: No text to summarize"
-
-    text_length = len(text)
-    print(f"Text length: {text_length} characters")
-
-    summaries = []
-    chunks = list(split_text(text))
-
-    for i, chunk in enumerate(chunks):
-        print(f"Adding chunk {i + 1} / {len(chunks)} to memory")
-
-        memory_to_add = f"Source: {url}\n" f"Raw content part#{i + 1}: {chunk}"
-
-        memory.add(memory_to_add)
-
-        print(f"Summarizing chunk {i + 1} / {len(chunks)}")
-        messages = [create_message(chunk, question)]
-
-        summary = create_chat_completion(
-            model=cfg.fast_llm_model,
-            messages=messages,
-            max_tokens=cfg.browse_summary_max_token,
-        )
-        summaries.append(summary)
-        print(f"Added chunk {i + 1} summary to memory")
-
-        memory_to_add = f"Source: {url}\n" f"Content summary part#{i + 1}: {summary}"
-
-        memory.add(memory_to_add)
-
-    print(f"Summarized {len(chunks)} chunks.")
-
-    combined_summary = "\n".join(summaries)
-    messages = [create_message(combined_summary, question)]
-
-    final_summary = create_chat_completion(
-        model=cfg.fast_llm_model,
-        messages=messages,
-        max_tokens=cfg.browse_summary_max_token,
-    )
-
-    return final_summary

autogpt/call_ai_function.py

@@ -1,26 +0,0 @@
-from autogpt.config import Config
-from autogpt.llm_utils import create_chat_completion
-
-cfg = Config()
-
-
-# This is a magic function that can do anything with no-code. See
-# https://github.com/Torantulino/AI-Functions for more info.
-def call_ai_function(function, args, description, model=None) -> str:
-    """Call an AI function"""
-    if model is None:
-        model = cfg.smart_llm_model
-    # 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 = [
-        {
-            "role": "system",
-            "content": f"You are now the following python function: ```# {description}"
-            f"\n{function}```\n\nOnly respond with your `return` value.",
-        },
-        {"role": "user", "content": args},
-    ]
-
-    return create_chat_completion(model=model, messages=messages, temperature=0)

autogpt/chat.py

@@ -5,7 +5,7 @@ from openai.error import RateLimitError
 from autogpt import token_counter
 from autogpt.config import Config
 from autogpt.llm_utils import create_chat_completion
-from autogpt.logger import logger
+from autogpt.logs import logger
 
 cfg = Config()
 
@@ -96,7 +96,7 @@ def chat_with_ai(
 
             while current_tokens_used > 2500:
                 # remove memories until we are under 2500 tokens
-                relevant_memory = relevant_memory[1:]
+                relevant_memory = relevant_memory[:-1]
                 (
                     next_message_to_add_index,
                     current_tokens_used,

autogpt/cli.py

@@ -0,0 +1,125 @@
+"""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.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,
+) -> 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
+
+    from colorama import Fore
+
+    from autogpt.agent.agent import Agent
+    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.prompt import construct_prompt
+
+    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,
+        )
+        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(
+            "Using memory of type:", Fore.GREEN, f"{memory.__class__.__name__}"
+        )
+        logger.typewriter_log("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()
+
+
+if __name__ == "__main__":
+    main()

autogpt/commands.py

@@ -1,274 +0,0 @@
-import json
-import datetime
-import autogpt.agent_manager as agents
-from autogpt.config import Config
-from autogpt.json_parser import fix_and_parse_json
-from autogpt.image_gen import generate_image
-from duckduckgo_search import ddg
-from autogpt.ai_functions import evaluate_code, improve_code, write_tests
-from autogpt.browse import scrape_links, scrape_text, summarize_text
-from autogpt.execute_code import execute_python_file, execute_shell
-from autogpt.file_operations import (
-    append_to_file,
-    delete_file,
-    read_file,
-    search_files,
-    write_to_file,
-)
-from autogpt.memory import get_memory
-from autogpt.speak import say_text
-from autogpt.web import browse_website
-
-
-cfg = Config()
-
-
-def is_valid_int(value) -> bool:
-    try:
-        int(value)
-        return True
-    except ValueError:
-        return False
-
-
-def get_command(response):
-    """Parse the response and return the command name and arguments"""
-    try:
-        response_json = fix_and_parse_json(response)
-
-        if "command" not in response_json:
-            return "Error:", "Missing 'command' object in JSON"
-
-        if not isinstance(response_json, dict):
-            return "Error:", f"'response_json' object is not dictionary {response_json}"
-
-        command = response_json["command"]
-        if not isinstance(command, dict):
-            return "Error:", "'command' object is not a dictionary"
-
-        if "name" not in command:
-            return "Error:", "Missing 'name' field in 'command' object"
-
-        command_name = command["name"]
-
-        # Use an empty dictionary if 'args' field is not present in 'command' object
-        arguments = command.get("args", {})
-
-        return command_name, arguments
-    except json.decoder.JSONDecodeError:
-        return "Error:", "Invalid JSON"
-    # All other errors, return "Error: + error message"
-    except Exception as e:
-        return "Error:", str(e)
-
-
-def execute_command(command_name, arguments):
-    """Execute the command and return the result"""
-    memory = get_memory(cfg)
-
-    try:
-        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":
-                return google_official_search(arguments["input"])
-            else:
-                return google_search(arguments["input"])
-        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 == "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 == "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 == "generate_image":
-            return generate_image(arguments["prompt"])
-        elif command_name == "do_nothing":
-            return "No action performed."
-        elif command_name == "task_complete":
-            shutdown()
-        else:
-            return (
-                f"Unknown command '{command_name}'. Please refer to the 'COMMANDS'"
-                " list for available commands and only respond in the specified JSON"
-                " format."
-            )
-    # All errors, return "Error: + error message"
-    except Exception as e:
-        return "Error: " + str(e)
-
-
-def get_datetime():
-    """Return the current date and time"""
-    return "Current date and time: " + datetime.datetime.now().strftime(
-        "%Y-%m-%d %H:%M:%S"
-    )
-
-
-def google_search(query, num_results=8):
-    """Return the results of a google search"""
-    search_results = []
-    if not query:
-        return json.dumps(search_results)
-
-    for j in ddg(query, max_results=num_results):
-        search_results.append(j)
-
-    return json.dumps(search_results, ensure_ascii=False, indent=4)
-
-
-def google_official_search(query, num_results=8):
-    """Return the results of a google search using the official Google API"""
-    import json
-
-    from googleapiclient.discovery import build
-    from googleapiclient.errors import HttpError
-
-    try:
-        # Get the Google API key and Custom Search Engine ID from the config file
-        api_key = cfg.google_api_key
-        custom_search_engine_id = cfg.custom_search_engine_id
-
-        # Initialize the Custom Search API service
-        service = build("customsearch", "v1", developerKey=api_key)
-
-        # Send the search query and retrieve the results
-        result = (
-            service.cse()
-            .list(q=query, cx=custom_search_engine_id, num=num_results)
-            .execute()
-        )
-
-        # Extract the search result items from the response
-        search_results = result.get("items", [])
-
-        # Create a list of only the URLs from the search results
-        search_results_links = [item["link"] for item in search_results]
-
-    except HttpError as e:
-        # Handle errors in the API call
-        error_details = json.loads(e.content.decode())
-
-        # Check if the error is related to an invalid or missing API key
-        if error_details.get("error", {}).get(
-            "code"
-        ) == 403 and "invalid API key" in error_details.get("error", {}).get(
-            "message", ""
-        ):
-            return "Error: The provided Google API key is invalid or missing."
-        else:
-            return f"Error: {e}"
-
-    # Return the list of search result URLs
-    return search_results_links
-
-
-def get_text_summary(url, question):
-    """Return the results of a google search"""
-    text = scrape_text(url)
-    summary = summarize_text(url, text, question)
-    return """ "Result" : """ + summary
-
-
-def get_hyperlinks(url):
-    """Return the results of a google search"""
-    return scrape_links(url)
-
-
-def shutdown():
-    """Shut down the program"""
-    print("Shutting down...")
-    quit()
-
-
-def start_agent(name, task, prompt, model=cfg.fast_llm_model):
-    """Start an agent with a given name, task, and prompt"""
-    # Remove underscores from name
-    voice_name = name.replace("_", " ")
-
-    first_message = f"""You are {name}.  Respond with: "Acknowledged"."""
-    agent_intro = f"{voice_name} here, Reporting for duty!"
-
-    # Create agent
-    if cfg.speak_mode:
-        say_text(agent_intro, 1)
-    key, ack = agents.create_agent(task, first_message, model)
-
-    if cfg.speak_mode:
-        say_text(f"Hello {voice_name}. Your task is as follows. {task}.")
-
-    # Assign task (prompt), get response
-    agent_response = agents.message_agent(key, prompt)
-
-    return f"Agent {name} created with key {key}. First response: {agent_response}"
-
-
-def message_agent(key, message):
-    """Message an agent with a given key and message"""
-    # Check if the key is a valid integer
-    if is_valid_int(key):
-        agent_response = agents.message_agent(int(key), message)
-    # Check if the key is a valid string
-    elif isinstance(key, str):
-        agent_response = agents.message_agent(key, message)
-    else:
-        return "Invalid key, must be an integer or a string."
-
-    # Speak response
-    if cfg.speak_mode:
-        say_text(agent_response, 1)
-    return agent_response
-
-
-def list_agents():
-    """List all agents"""
-    return list_agents()
-
-
-def delete_agent(key):
-    """Delete an agent with a given key"""
-    result = agents.delete_agent(key)
-    return f"Agent {key} deleted." if result else f"Agent {key} does not exist."

autogpt/commands/audio_text.py

@@ -0,0 +1,36 @@
+import json
+
+import requests
+
+from autogpt.config import Config
+from autogpt.workspace import path_in_workspace
+
+cfg = Config()
+
+
+def read_audio_from_file(audio_path):
+    audio_path = path_in_workspace(audio_path)
+    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
+    api_url = f"https://api-inference.huggingface.co/models/{model}"
+    api_token = cfg.huggingface_api_token
+    headers = {"Authorization": f"Bearer {api_token}"}
+
+    if api_token is None:
+        raise ValueError(
+            "You need to set your Hugging Face API token in the config file."
+        )
+
+    response = requests.post(
+        api_url,
+        headers=headers,
+        data=audio,
+    )
+
+    text = json.loads(response.content.decode("utf-8"))["text"]
+    return "The audio says: " + text

autogpt/commands/evaluate_code.py

@@ -0,0 +1,25 @@
+"""Code evaluation module."""
+from __future__ import annotations
+
+from autogpt.llm_utils import call_ai_function
+
+
+def evaluate_code(code: str) -> list[str]:
+    """
+    A function that takes in a string and returns a response from create chat
+      completion api call.
+
+    Parameters:
+        code (str): Code to be evaluated.
+    Returns:
+        A result string from create chat completion. A list of suggestions to
+            improve the code.
+    """
+
+    function_string = "def analyze_code(code: str) -> List[str]:"
+    args = [code]
+    description_string = (
+        "Analyzes the given code and returns a list of suggestions" " for improvements."
+    )
+
+    return call_ai_function(function_string, args, description_string)

autogpt/commands/execute_code.py

@@ -0,0 +1,153 @@
+"""Execute code in a Docker container"""
+import os
+import subprocess
+
+import docker
+from docker.errors import ImageNotFound
+
+from autogpt.workspace import WORKSPACE_PATH, path_in_workspace
+
+
+def execute_python_file(file: str) -> str:
+    """Execute a Python file in a Docker container and return the output
+
+    Args:
+        file (str): The name of the file to execute
+
+    Returns:
+        str: The output of the file
+    """
+
+    print(f"Executing file '{file}' in workspace '{WORKSPACE_PATH}'")
+
+    if not file.endswith(".py"):
+        return "Error: Invalid file type. Only .py files are allowed."
+
+    file_path = path_in_workspace(file)
+
+    if not os.path.isfile(file_path):
+        return f"Error: File '{file}' does not exist."
+
+    if we_are_running_in_a_docker_container():
+        result = subprocess.run(
+            f"python {file_path}", capture_output=True, encoding="utf8", shell=True
+        )
+        if result.returncode == 0:
+            return result.stdout
+        else:
+            return f"Error: {result.stderr}"
+
+    try:
+        client = docker.from_env()
+
+        # 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-alpine"
+        try:
+            client.images.get(image_name)
+            print(f"Image '{image_name}' found locally")
+        except ImageNotFound:
+            print(f"Image '{image_name}' not found locally, pulling from Docker Hub")
+            # Use the low-level API to stream the pull response
+            low_level_client = docker.APIClient()
+            for line in low_level_client.pull(image_name, stream=True, decode=True):
+                # Print the status and progress, if available
+                status = line.get("status")
+                progress = line.get("progress")
+                if status and progress:
+                    print(f"{status}: {progress}")
+                elif status:
+                    print(status)
+
+        container = client.containers.run(
+            image_name,
+            f"python {file}",
+            volumes={
+                os.path.abspath(WORKSPACE_PATH): {
+                    "bind": "/workspace",
+                    "mode": "ro",
+                }
+            },
+            working_dir="/workspace",
+            stderr=True,
+            stdout=True,
+            detach=True,
+        )
+
+        container.wait()
+        logs = container.logs().decode("utf-8")
+        container.remove()
+
+        # print(f"Execution complete. Output: {output}")
+        # print(f"Logs: {logs}")
+
+        return logs
+
+    except Exception as e:
+        return f"Error: {str(e)}"
+
+
+def execute_shell(command_line: str) -> str:
+    """Execute a shell command and return the output
+
+    Args:
+        command_line (str): The command line to execute
+
+    Returns:
+        str: The output of the command
+    """
+    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()}'")
+
+    result = subprocess.run(command_line, capture_output=True, shell=True)
+    output = f"STDOUT:\n{result.stdout}\nSTDERR:\n{result.stderr}"
+
+    # Change back to whatever the prior working dir was
+
+    os.chdir(current_dir)
+
+    return output
+
+
+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()
+
+    if WORKING_DIRECTORY not in current_dir:  # Change dir into workspace if necessary
+        work_dir = os.path.join(os.getcwd(), WORKING_DIRECTORY)
+        os.chdir(work_dir)
+
+    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:
+    """Check if we are running in a Docker container
+
+    Returns:
+        bool: True if we are running in a Docker container, False otherwise
+    """
+    return os.path.exists("/.dockerenv")

autogpt/commands/file_operations.py

@@ -0,0 +1,268 @@
+"""File operations for AutoGPT"""
+from __future__ import annotations
+
+import os
+import os.path
+from pathlib import Path
+from typing import Generator, List
+
+import requests
+from colorama import Back, Fore
+from requests.adapters import HTTPAdapter, Retry
+
+from autogpt.spinner import Spinner
+from autogpt.utils import readable_file_size
+from autogpt.workspace import WORKSPACE_PATH, path_in_workspace
+
+LOG_FILE = "file_logger.txt"
+LOG_FILE_PATH = WORKSPACE_PATH / LOG_FILE
+
+
+def check_duplicate_operation(operation: str, filename: str) -> bool:
+    """Check if the operation has already been performed on the given file
+
+    Args:
+        operation (str): The operation to check for
+        filename (str): The name of the file to check for
+
+    Returns:
+        bool: True if the operation has already been performed on the file
+    """
+    log_content = read_file(LOG_FILE)
+    log_entry = f"{operation}: {filename}\n"
+    return log_entry in log_content
+
+
+def log_operation(operation: str, filename: str) -> None:
+    """Log the file operation to the file_logger.txt
+
+    Args:
+        operation (str): The operation to log
+        filename (str): The name of the file the operation was performed on
+    """
+    log_entry = f"{operation}: {filename}\n"
+
+    # Create the log file if it doesn't exist
+    if not os.path.exists(LOG_FILE_PATH):
+        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)
+
+
+def split_file(
+    content: str, max_length: int = 4000, overlap: int = 0
+) -> Generator[str, None, None]:
+    """
+    Split text into chunks of a specified maximum length with a specified overlap
+    between chunks.
+
+    :param content: The input text to be split into chunks
+    :param max_length: The maximum length of each chunk,
+        default is 4000 (about 1k token)
+    :param overlap: The number of overlapping characters between chunks,
+        default is no overlap
+    :return: A generator yielding chunks of text
+    """
+    start = 0
+    content_length = len(content)
+
+    while start < content_length:
+        end = start + max_length
+        if end + overlap < content_length:
+            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
+
+
+def read_file(filename: str) -> str:
+    """Read a file and return the contents
+
+    Args:
+        filename (str): The name of the file to read
+
+    Returns:
+        str: The contents of the file
+    """
+    try:
+        filepath = path_in_workspace(filename)
+        with open(filepath, "r", encoding="utf-8") as f:
+            content = f.read()
+        return content
+    except Exception as e:
+        return f"Error: {str(e)}"
+
+
+def ingest_file(
+    filename: str, memory, max_length: int = 4000, overlap: int = 200
+) -> None:
+    """
+    Ingest a file by reading its content, splitting it into chunks with a specified
+    maximum length and overlap, and adding the chunks to the memory storage.
+
+    :param filename: The name of the file to ingest
+    :param memory: An object with an add() method to store the chunks in memory
+    :param max_length: The maximum length of each chunk, default is 4000
+    :param overlap: The number of overlapping characters between chunks, default is 200
+    """
+    try:
+        print(f"Working with file {filename}")
+        content = read_file(filename)
+        content_length = len(content)
+        print(f"File length: {content_length} characters")
+
+        chunks = list(split_file(content, max_length=max_length, overlap=overlap))
+
+        num_chunks = len(chunks)
+        for i, chunk in enumerate(chunks):
+            print(f"Ingesting chunk {i + 1} / {num_chunks} into memory")
+            memory_to_add = (
+                f"Filename: {filename}\n" f"Content part#{i + 1}/{num_chunks}: {chunk}"
+            )
+
+            memory.add(memory_to_add)
+
+        print(f"Done ingesting {num_chunks} chunks from {filename}.")
+    except Exception as e:
+        print(f"Error while ingesting file '{filename}': {str(e)}")
+
+
+def write_to_file(filename: str, text: str) -> str:
+    """Write text to a file
+
+    Args:
+        filename (str): The name of the file to write to
+        text (str): The text to write to the file
+
+    Returns:
+        str: A message indicating success or failure
+    """
+    if check_duplicate_operation("write", filename):
+        return "Error: File has already been updated."
+    try:
+        filepath = path_in_workspace(filename)
+        directory = os.path.dirname(filepath)
+        if not os.path.exists(directory):
+            os.makedirs(directory)
+        with open(filepath, "w", encoding="utf-8") as f:
+            f.write(text)
+        log_operation("write", filename)
+        return "File written to successfully."
+    except Exception as e:
+        return f"Error: {str(e)}"
+
+
+def append_to_file(filename: str, text: str, shouldLog: bool = True) -> str:
+    """Append text to a file
+
+    Args:
+        filename (str): The name of the file to append to
+        text (str): The text to append to the file
+
+    Returns:
+        str: A message indicating success or failure
+    """
+    try:
+        filepath = path_in_workspace(filename)
+        with open(filepath, "a") as f:
+            f.write(text)
+
+        if shouldLog:
+            log_operation("append", filename)
+
+        return "Text appended successfully."
+    except Exception as e:
+        return f"Error: {str(e)}"
+
+
+def delete_file(filename: str) -> str:
+    """Delete a file
+
+    Args:
+        filename (str): The name of the file to delete
+
+    Returns:
+        str: A message indicating success or failure
+    """
+    if check_duplicate_operation("delete", filename):
+        return "Error: File has already been deleted."
+    try:
+        filepath = path_in_workspace(filename)
+        os.remove(filepath)
+        log_operation("delete", filename)
+        return "File deleted successfully."
+    except Exception as e:
+        return f"Error: {str(e)}"
+
+
+def search_files(directory: str) -> list[str]:
+    """Search for files in a directory
+
+    Args:
+        directory (str): The directory to search in
+
+    Returns:
+        list[str]: A list of files found in the directory
+    """
+    found_files = []
+
+    if directory in {"", "/"}:
+        search_directory = WORKSPACE_PATH
+    else:
+        search_directory = path_in_workspace(directory)
+
+    for root, _, files in os.walk(search_directory):
+        for file in files:
+            if file.startswith("."):
+                continue
+            relative_path = os.path.relpath(os.path.join(root, file), WORKSPACE_PATH)
+            found_files.append(relative_path)
+
+    return found_files
+
+
+def download_file(url, filename):
+    """Downloads a file
+    Args:
+        url (str): URL of the file to download
+        filename (str): Filename to save the file as
+    """
+    safe_filename = path_in_workspace(filename)
+    try:
+        message = f"{Fore.YELLOW}Downloading file from {Back.LIGHTBLUE_EX}{url}{Back.RESET}{Fore.RESET}"
+        with Spinner(message) as spinner:
+            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)
+
+            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))
+                downloaded_size = 0
+
+                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
+                        progress = f"{readable_file_size(downloaded_size)} / {readable_file_size(total_size)}"
+                        spinner.update_message(f"{message} {progress}")
+
+            return f'Successfully downloaded and locally stored file: "{filename}"! (Size: {readable_file_size(total_size)})'
+    except requests.HTTPError as e:
+        return f"Got an HTTP Error whilst trying to download file: {e}"
+    except Exception as e:
+        return "Error: " + str(e)

autogpt/commands/git_operations.py

@@ -0,0 +1,26 @@
+"""Git operations for autogpt"""
+import git
+
+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
+
+    Args:
+        repo_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("//")
+    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}"""
+    except Exception as e:
+        return f"Error: {str(e)}"

autogpt/commands/google_search.py

@@ -0,0 +1,87 @@
+"""Google search command for Autogpt."""
+from __future__ import annotations
+
+import json
+
+from duckduckgo_search import ddg
+
+from autogpt.config import Config
+
+CFG = Config()
+
+
+def google_search(query: str, num_results: int = 8) -> str:
+    """Return the results of a Google search
+
+    Args:
+        query (str): The search query.
+        num_results (int): The number of results to return.
+
+    Returns:
+        str: The results of the search.
+    """
+    search_results = []
+    if not query:
+        return json.dumps(search_results)
+
+    results = ddg(query, max_results=num_results)
+    if not results:
+        return json.dumps(search_results)
+
+    for j in results:
+        search_results.append(j)
+
+    return json.dumps(search_results, ensure_ascii=False, indent=4)
+
+
+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
+
+    Args:
+        query (str): The search query.
+        num_results (int): The number of results to return.
+
+    Returns:
+        str: The results of the search.
+    """
+
+    from googleapiclient.discovery import build
+    from googleapiclient.errors import HttpError
+
+    try:
+        # Get the Google API key and Custom Search Engine ID from the config file
+        api_key = CFG.google_api_key
+        custom_search_engine_id = CFG.custom_search_engine_id
+
+        # Initialize the Custom Search API service
+        service = build("customsearch", "v1", developerKey=api_key)
+
+        # Send the search query and retrieve the results
+        result = (
+            service.cse()
+            .list(q=query, cx=custom_search_engine_id, num=num_results)
+            .execute()
+        )
+
+        # Extract the search result items from the response
+        search_results = result.get("items", [])
+
+        # Create a list of only the URLs from the search results
+        search_results_links = [item["link"] for item in search_results]
+
+    except HttpError as e:
+        # Handle errors in the API call
+        error_details = json.loads(e.content.decode())
+
+        # Check if the error is related to an invalid or missing API key
+        if error_details.get("error", {}).get(
+            "code"
+        ) == 403 and "invalid API key" in error_details.get("error", {}).get(
+            "message", ""
+        ):
+            return "Error: The provided Google API key is invalid or missing."
+        else:
+            return f"Error: {e}"
+
+    # Return the list of search result URLs
+    return search_results_links

autogpt/commands/image_gen.py

@@ -0,0 +1,98 @@
+""" 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.config import Config
+from autogpt.workspace import path_in_workspace
+
+CFG = Config()
+
+
+def generate_image(prompt: str) -> str:
+    """Generate an image from a prompt.
+
+    Args:
+        prompt (str): The prompt to use
+
+    Returns:
+        str: The filename of the image
+    """
+    filename = f"{str(uuid.uuid4())}.jpg"
+
+    # DALL-E
+    if CFG.image_provider == "dalle":
+        return generate_image_with_dalle(prompt, filename)
+    elif CFG.image_provider == "sd":
+        return generate_image_with_hf(prompt, filename)
+    else:
+        return "No Image Provider Set"
+
+
+def generate_image_with_hf(prompt: str, filename: str) -> str:
+    """Generate an image with HuggingFace's API.
+
+    Args:
+        prompt (str): The prompt to use
+        filename (str): The filename to save the image to
+
+    Returns:
+        str: The filename of the image
+    """
+    API_URL = (
+        "https://api-inference.huggingface.co/models/CompVis/stable-diffusion-v1-4"
+    )
+    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}"}
+
+    response = requests.post(
+        API_URL,
+        headers=headers,
+        json={
+            "inputs": prompt,
+        },
+    )
+
+    image = Image.open(io.BytesIO(response.content))
+    print(f"Image Generated for prompt:{prompt}")
+
+    image.save(path_in_workspace(filename))
+
+    return f"Saved to disk:{filename}"
+
+
+def generate_image_with_dalle(prompt: str, filename: str) -> str:
+    """Generate an image with DALL-E.
+
+    Args:
+        prompt (str): The prompt to use
+        filename (str): The filename to save the image to
+
+    Returns:
+        str: The filename of the image
+    """
+    openai.api_key = CFG.openai_api_key
+
+    response = openai.Image.create(
+        prompt=prompt,
+        n=1,
+        size="256x256",
+        response_format="b64_json",
+    )
+
+    print(f"Image Generated for prompt:{prompt}")
+
+    image_data = b64decode(response["data"][0]["b64_json"])
+
+    with open(path_in_workspace(filename), mode="wb") as png:
+        png.write(image_data)
+
+    return f"Saved to disk:{filename}"

autogpt/commands/improve_code.py

@@ -0,0 +1,29 @@
+from __future__ import annotations
+
+import json
+
+from autogpt.llm_utils import call_ai_function
+
+
+def improve_code(suggestions: list[str], code: str) -> str:
+    """
+    A function that takes in code and suggestions and returns a response from create
+      chat completion api call.
+
+    Parameters:
+        suggestions (List): A list of suggestions around what needs to be improved.
+        code (str): Code to be improved.
+    Returns:
+        A result string from create chat completion. Improved code in response.
+    """
+
+    function_string = (
+        "def generate_improved_code(suggestions: List[str], code: str) -> str:"
+    )
+    args = [json.dumps(suggestions), code]
+    description_string = (
+        "Improves the provided code based on the suggestions"
+        " provided, making no other changes."
+    )
+
+    return call_ai_function(function_string, args, description_string)

autogpt/commands/times.py

@@ -0,0 +1,10 @@
+from datetime import datetime
+
+
+def get_datetime() -> str:
+    """Return the current date and time
+
+    Returns:
+        str: The current date and time
+    """
+    return "Current date and time: " + datetime.now().strftime("%Y-%m-%d %H:%M:%S")

autogpt/commands/twitter.py

@@ -0,0 +1,26 @@
+import os
+
+import tweepy
+from dotenv import load_dotenv
+
+load_dotenv()
+
+
+def send_tweet(tweet_text):
+    consumer_key = os.environ.get("TW_CONSUMER_KEY")
+    consumer_secret = os.environ.get("TW_CONSUMER_SECRET")
+    access_token = os.environ.get("TW_ACCESS_TOKEN")
+    access_token_secret = os.environ.get("TW_ACCESS_TOKEN_SECRET")
+    # Authenticate to Twitter
+    auth = tweepy.OAuthHandler(consumer_key, consumer_secret)
+    auth.set_access_token(access_token, access_token_secret)
+
+    # Create API object
+    api = tweepy.API(auth)
+
+    # Send tweet
+    try:
+        api.update_status(tweet_text)
+        print("Tweet sent successfully!")
+    except tweepy.TweepyException as e:
+        print("Error sending tweet: {}".format(e.reason))

autogpt/commands/web_playwright.py

@@ -0,0 +1,80 @@
+"""Web scraping commands using Playwright"""
+from __future__ import annotations
+
+try:
+    from playwright.sync_api import sync_playwright
+except ImportError:
+    print(
+        "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
+
+
+def scrape_text(url: str) -> str:
+    """Scrape text from a webpage
+
+    Args:
+        url (str): The URL to scrape text from
+
+    Returns:
+        str: The scraped text
+    """
+    with sync_playwright() as p:
+        browser = p.chromium.launch()
+        page = browser.new_page()
+
+        try:
+            page.goto(url)
+            html_content = page.content()
+            soup = BeautifulSoup(html_content, "html.parser")
+
+            for script in soup(["script", "style"]):
+                script.extract()
+
+            text = soup.get_text()
+            lines = (line.strip() for line in text.splitlines())
+            chunks = (phrase.strip() for line in lines for phrase in line.split("  "))
+            text = "\n".join(chunk for chunk in chunks if chunk)
+
+        except Exception as e:
+            text = f"Error: {str(e)}"
+
+        finally:
+            browser.close()
+
+    return text
+
+
+def scrape_links(url: str) -> str | list[str]:
+    """Scrape links from a webpage
+
+    Args:
+        url (str): The URL to scrape links from
+
+    Returns:
+        Union[str, List[str]]: The scraped links
+    """
+    with sync_playwright() as p:
+        browser = p.chromium.launch()
+        page = browser.new_page()
+
+        try:
+            page.goto(url)
+            html_content = page.content()
+            soup = BeautifulSoup(html_content, "html.parser")
+
+            for script in soup(["script", "style"]):
+                script.extract()
+
+            hyperlinks = extract_hyperlinks(soup, url)
+            formatted_links = format_hyperlinks(hyperlinks)
+
+        except Exception as e:
+            formatted_links = f"Error: {str(e)}"
+
+        finally:
+            browser.close()
+
+    return formatted_links

autogpt/commands/web_requests.py

@@ -0,0 +1,190 @@
+"""Browse a webpage and summarize it using the LLM model"""
+from __future__ import annotations
+
+from urllib.parse import urljoin, urlparse
+
+import requests
+from bs4 import BeautifulSoup
+from requests import Response
+from requests.compat import urljoin
+
+from autogpt.config import Config
+from autogpt.memory import get_memory
+from autogpt.processing.html import extract_hyperlinks, format_hyperlinks
+
+CFG = Config()
+memory = get_memory(CFG)
+
+session = requests.Session()
+session.headers.update({"User-Agent": CFG.user_agent})
+
+
+def is_valid_url(url: str) -> bool:
+    """Check if the URL is valid
+
+    Args:
+        url (str): The URL to check
+
+    Returns:
+        bool: True if the URL is valid, False otherwise
+    """
+    try:
+        result = urlparse(url)
+        return all([result.scheme, result.netloc])
+    except ValueError:
+        return False
+
+
+def sanitize_url(url: str) -> str:
+    """Sanitize the URL
+
+    Args:
+        url (str): The URL to sanitize
+
+    Returns:
+        str: The sanitized URL
+    """
+    return urljoin(url, urlparse(url).path)
+
+
+def check_local_file_access(url: str) -> bool:
+    """Check if the URL is a local file
+
+    Args:
+        url (str): The URL to check
+
+    Returns:
+        bool: True if the URL is a local file, False otherwise
+    """
+    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)
+
+
+def get_response(
+    url: str, timeout: int = 10
+) -> tuple[None, str] | tuple[Response, None]:
+    """Get the response from a URL
+
+    Args:
+        url (str): The URL to get the response from
+        timeout (int): The timeout for the HTTP request
+
+    Returns:
+        tuple[None, str] | tuple[Response, None]: The response and error message
+
+    Raises:
+        ValueError: If the URL is invalid
+        requests.exceptions.RequestException: If the HTTP request fails
+    """
+    try:
+        # Restrict access to local files
+        if check_local_file_access(url):
+            raise ValueError("Access to local files is restricted")
+
+        # Most basic check if the URL is valid:
+        if not url.startswith("http://") and not url.startswith("https://"):
+            raise ValueError("Invalid URL format")
+
+        sanitized_url = sanitize_url(url)
+
+        response = session.get(sanitized_url, timeout=timeout)
+
+        # Check if the response contains an HTTP error
+        if response.status_code >= 400:
+            return None, f"Error: HTTP {str(response.status_code)} error"
+
+        return response, None
+    except ValueError as ve:
+        # Handle invalid URL format
+        return None, f"Error: {str(ve)}"
+
+    except requests.exceptions.RequestException as re:
+        # Handle exceptions related to the HTTP request
+        #  (e.g., connection errors, timeouts, etc.)
+        return None, f"Error: {str(re)}"
+
+
+def scrape_text(url: str) -> str:
+    """Scrape text from a webpage
+
+    Args:
+        url (str): The URL to scrape text from
+
+    Returns:
+        str: The scraped text
+    """
+    response, error_message = get_response(url)
+    if error_message:
+        return error_message
+    if not response:
+        return "Error: Could not get response"
+
+    soup = BeautifulSoup(response.text, "html.parser")
+
+    for script in soup(["script", "style"]):
+        script.extract()
+
+    text = soup.get_text()
+    lines = (line.strip() for line in text.splitlines())
+    chunks = (phrase.strip() for line in lines for phrase in line.split("  "))
+    text = "\n".join(chunk for chunk in chunks if chunk)
+
+    return text
+
+
+def scrape_links(url: str) -> str | list[str]:
+    """Scrape links from a webpage
+
+    Args:
+        url (str): The URL to scrape links from
+
+    Returns:
+       str | list[str]: The scraped links
+    """
+    response, error_message = get_response(url)
+    if error_message:
+        return error_message
+    if not response:
+        return "Error: Could not get response"
+    soup = BeautifulSoup(response.text, "html.parser")
+
+    for script in soup(["script", "style"]):
+        script.extract()
+
+    hyperlinks = extract_hyperlinks(soup, url)
+
+    return format_hyperlinks(hyperlinks)
+
+
+def create_message(chunk, question):
+    """Create a message for the user to summarize a chunk of text"""
+    return {
+        "role": "user",
+        "content": f'"""{chunk}""" Using the above text, answer the following'
+        f' question: "{question}" -- if the question cannot be answered using the'
+        " text, summarize the text.",
+    }

autogpt/commands/web_selenium.py

@@ -0,0 +1,154 @@
+"""Selenium web scraping module."""
+from __future__ import annotations
+
+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.config import Config
+from autogpt.processing.html import extract_hyperlinks, format_hyperlinks
+
+FILE_DIR = Path(__file__).parent.parent
+CFG = Config()
+
+
+def browse_website(url: str, question: str) -> tuple[str, WebDriver]:
+    """Browse a website and return the answer and links to the user
+
+    Args:
+        url (str): The url of the website to browse
+        question (str): The question asked by the user
+
+    Returns:
+        Tuple[str, WebDriver]: The answer and links to the user and the webdriver
+    """
+    driver, text = scrape_text_with_selenium(url)
+    add_header(driver)
+    summary_text = summary.summarize_text(url, text, question, driver)
+    links = scrape_links_with_selenium(driver, url)
+
+    # Limit links to 5
+    if len(links) > 5:
+        links = links[:5]
+    close_browser(driver)
+    return f"Answer gathered from website: {summary_text} \n \n Links: {links}", driver
+
+
+def scrape_text_with_selenium(url: str) -> tuple[WebDriver, str]:
+    """Scrape text from a website using selenium
+
+    Args:
+        url (str): The url of the website to scrape
+
+    Returns:
+        Tuple[WebDriver, str]: The webdriver and the text scraped from the website
+    """
+    logging.getLogger("selenium").setLevel(logging.CRITICAL)
+
+    options_available = {
+        "chrome": ChromeOptions,
+        "safari": SafariOptions,
+        "firefox": FirefoxOptions,
+    }
+
+    options = options_available[CFG.selenium_web_browser]()
+    options.add_argument(
+        "user-agent=Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/112.0.5615.49 Safari/537.36"
+    )
+
+    if CFG.selenium_web_browser == "firefox":
+        driver = webdriver.Firefox(
+            executable_path=GeckoDriverManager().install(), options=options
+        )
+    elif CFG.selenium_web_browser == "safari":
+        # Requires a bit more setup on the users end
+        # 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.headless_browser:
+            options.add_argument("--headless")
+            options.add_argument("--disable-gpu")
+
+        driver = webdriver.Chrome(
+            executable_path=ChromeDriverManager().install(), options=options
+        )
+    driver.get(url)
+
+    WebDriverWait(driver, 10).until(
+        EC.presence_of_element_located((By.TAG_NAME, "body"))
+    )
+
+    # Get the HTML content directly from the browser's DOM
+    page_source = driver.execute_script("return document.body.outerHTML;")
+    soup = BeautifulSoup(page_source, "html.parser")
+
+    for script in soup(["script", "style"]):
+        script.extract()
+
+    text = soup.get_text()
+    lines = (line.strip() for line in text.splitlines())
+    chunks = (phrase.strip() for line in lines for phrase in line.split("  "))
+    text = "\n".join(chunk for chunk in chunks if chunk)
+    return driver, text
+
+
+def scrape_links_with_selenium(driver: WebDriver, url: str) -> list[str]:
+    """Scrape links from a website using selenium
+
+    Args:
+        driver (WebDriver): The webdriver to use to scrape the links
+
+    Returns:
+        List[str]: The links scraped from the website
+    """
+    page_source = driver.page_source
+    soup = BeautifulSoup(page_source, "html.parser")
+
+    for script in soup(["script", "style"]):
+        script.extract()
+
+    hyperlinks = extract_hyperlinks(soup, url)
+
+    return format_hyperlinks(hyperlinks)
+
+
+def close_browser(driver: WebDriver) -> None:
+    """Close the browser
+
+    Args:
+        driver (WebDriver): The webdriver to close
+
+    Returns:
+        None
+    """
+    driver.quit()
+
+
+def add_header(driver: WebDriver) -> None:
+    """Add a header to the website
+
+    Args:
+        driver (WebDriver): The webdriver to use to add the header
+
+    Returns:
+        None
+    """
+    driver.execute_script(open(f"{FILE_DIR}/js/overlay.js", "r").read())

autogpt/commands/write_tests.py

@@ -0,0 +1,31 @@
+"""A module that contains a function to generate test cases for the submitted code."""
+from __future__ import annotations
+
+import json
+
+from autogpt.llm_utils import call_ai_function
+
+
+def write_tests(code: str, focus: list[str]) -> str:
+    """
+    A function that takes in code and focus topics and returns a response from create
+      chat completion api call.
+
+    Parameters:
+        focus (list): A list of suggestions around what needs to be improved.
+        code (str): Code for test cases to be generated against.
+    Returns:
+        A result string from create chat completion. Test cases for the submitted code
+          in response.
+    """
+
+    function_string = (
+        "def create_test_cases(code: str, focus: Optional[str] = None) -> str:"
+    )
+    args = [code, json.dumps(focus)]
+    description_string = (
+        "Generates test cases for the existing code, focusing on"
+        " specific areas if required."
+    )
+
+    return call_ai_function(function_string, args, description_string)

autogpt/config/__init__.py

@@ -0,0 +1,14 @@
+"""
+This module contains the configuration classes for AutoGPT.
+"""
+from autogpt.config.ai_config import AIConfig
+from autogpt.config.config import Config, check_openai_api_key
+from autogpt.config.singleton import AbstractSingleton, Singleton
+
+__all__ = [
+    "check_openai_api_key",
+    "AbstractSingleton",
+    "AIConfig",
+    "Config",
+    "Singleton",
+]

autogpt/config/ai_config.py

@@ -1,8 +1,13 @@
+# sourcery skip: do-not-use-staticmethod
+"""
+A module that contains the AIConfig class object that contains the configuration
+"""
+from __future__ import annotations
+
 import os
 from typing import Type
-import yaml
 
-from autogpt.prompt import get_prompt
+import yaml
 
 
 class AIConfig:
@@ -16,7 +21,7 @@ class AIConfig:
     """
 
     def __init__(
-        self, ai_name: str = "", ai_role: str = "", ai_goals: list = []
+        self, ai_name: str = "", ai_role: str = "", ai_goals: list | None = None
     ) -> None:
         """
         Initialize a class instance
@@ -28,7 +33,8 @@ class AIConfig:
         Returns:
             None
         """
-
+        if ai_goals is None:
+            ai_goals = []
         self.ai_name = ai_name
         self.ai_role = ai_role
         self.ai_goals = ai_goals
@@ -36,15 +42,14 @@ class AIConfig:
     # 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")
 
-    @classmethod
+    @staticmethod
-    def load(cls: "Type[AIConfig]", config_file: str = SAVE_FILE) -> "Type[AIConfig]":
+    def load(config_file: str = SAVE_FILE) -> "AIConfig":
         """
         Returns class object with parameters (ai_name, ai_role, ai_goals) loaded from
           yaml file if yaml file exists,
         else returns class with no parameters.
 
         Parameters:
-           cls (class object): An AIConfig Class object.
            config_file (int): The path to the config yaml file.
              DEFAULT: "../ai_settings.yaml"
 
@@ -62,7 +67,7 @@ class AIConfig:
         ai_role = config_params.get("ai_role", "")
         ai_goals = config_params.get("ai_goals", [])
         # type: Type[AIConfig]
-        return cls(ai_name, ai_role, ai_goals)
+        return AIConfig(ai_name, ai_role, ai_goals)
 
     def save(self, config_file: str = SAVE_FILE) -> None:
         """
@@ -98,11 +103,13 @@ class AIConfig:
 
         prompt_start = (
             "Your decisions must always be made independently without"
-            "seeking user assistance. Play to your strengths as an LLM and pursue"
+            " seeking user assistance. Play to your strengths as an LLM and pursue"
             " simple strategies with no legal complications."
             ""
         )
 
+        from autogpt.prompt import get_prompt
+
         # Construct full prompt
         full_prompt = (
             f"You are {self.ai_name}, {self.ai_role}\n{prompt_start}\n\nGOALS:\n\n"

autogpt/config/config.py

@@ -1,30 +1,14 @@
-import abc
+"""Configuration class to store the state of bools for different scripts access."""
 import os
 
 import openai
 import yaml
+from colorama import Fore
 from dotenv import load_dotenv
 
-# Load environment variables from .env file
+from autogpt.config.singleton import Singleton
-load_dotenv()
 
-
+load_dotenv(verbose=True)
-class Singleton(abc.ABCMeta, type):
-    """
-    Singleton metaclass for ensuring only one instance of a class.
-    """
-
-    _instances = {}
-
-    def __call__(cls, *args, **kwargs):
-        """Call method for the singleton metaclass."""
-        if cls not in cls._instances:
-            cls._instances[cls] = super(Singleton, cls).__call__(*args, **kwargs)
-        return cls._instances[cls]
-
-
-class AbstractSingleton(abc.ABC, metaclass=Singleton):
-    pass
 
 
 class Config(metaclass=Singleton):
@@ -32,21 +16,22 @@ class Config(metaclass=Singleton):
     Configuration class to store the state of bools for different scripts access.
     """
 
-    def __init__(self):
+    def __init__(self) -> None:
         """Initialize the Config class"""
         self.debug_mode = False
         self.continuous_mode = False
         self.continuous_limit = 0
         self.speak_mode = False
         self.skip_reprompt = False
+        self.allow_downloads = 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.openai_api_key = os.getenv("OPENAI_API_KEY")
         self.temperature = float(os.getenv("TEMPERATURE", "1"))
@@ -71,20 +56,44 @@ class Config(metaclass=Singleton):
         self.use_brian_tts = False
         self.use_brian_tts = os.getenv("USE_BRIAN_TTS")
 
+        self.github_api_key = os.getenv("GITHUB_API_KEY")
+        self.github_username = os.getenv("GITHUB_USERNAME")
+
         self.google_api_key = os.getenv("GOOGLE_API_KEY")
         self.custom_search_engine_id = os.getenv("CUSTOM_SEARCH_ENGINE_ID")
 
         self.pinecone_api_key = os.getenv("PINECONE_API_KEY")
         self.pinecone_region = os.getenv("PINECONE_ENV")
 
+        self.weaviate_host = os.getenv("WEAVIATE_HOST")
+        self.weaviate_port = os.getenv("WEAVIATE_PORT")
+        self.weaviate_protocol = os.getenv("WEAVIATE_PROTOCOL", "http")
+        self.weaviate_username = os.getenv("WEAVIATE_USERNAME", None)
+        self.weaviate_password = os.getenv("WEAVIATE_PASSWORD", None)
+        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"
+        )
+
+        # 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.huggingface_api_token = os.getenv("HUGGINGFACE_API_TOKEN")
+        self.huggingface_audio_to_text_model = os.getenv(
+            "HUGGINGFACE_AUDIO_TO_TEXT_MODEL"
+        )
 
         # User agent headers to use when browsing web
-        # Some websites might just completely deny request with an error code if no user agent was found.
+        # Some websites might just completely deny request with an error code if
+        # no user agent was found.
         self.user_agent = os.getenv(
             "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",
+            "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.headless_browser = os.getenv('HEADLESS_BROWSER',"True") == "True"
         self.redis_host = os.getenv("REDIS_HOST", "localhost")
@@ -109,15 +118,17 @@ class Config(metaclass=Singleton):
             The matching deployment id if found, otherwise an empty string.
         """
         if model == self.fast_llm_model:
-            return self.azure_model_to_deployment_id_map["fast_llm_model_deployment_id"]
+            return self.azure_model_to_deployment_id_map[
+                "fast_llm_model_deployment_id"
+            ]  # type: ignore
         elif model == self.smart_llm_model:
             return self.azure_model_to_deployment_id_map[
                 "smart_llm_model_deployment_id"
-            ]
+            ]  # type: ignore
         elif model == "text-embedding-ada-002":
             return self.azure_model_to_deployment_id_map[
                 "embedding_model_deployment_id"
-            ]
+            ]  # type: ignore
         else:
             return ""
 
@@ -125,7 +136,8 @@ class Config(metaclass=Singleton):
 
     def load_azure_config(self, config_file: str = AZURE_CONFIG_FILE) -> None:
         """
-        Loads the configuration parameters for Azure hosting from the specified file path as a yaml file.
+        Loads the configuration parameters for Azure hosting from the specified file
+          path as a yaml file.
 
         Parameters:
             config_file(str): The path to the config yaml file. DEFAULT: "../azure.yaml"
@@ -138,85 +150,89 @@ class Config(metaclass=Singleton):
                 config_params = yaml.load(file, Loader=yaml.FullLoader)
         except FileNotFoundError:
             config_params = {}
-        self.openai_api_type = os.getenv(
+        self.openai_api_type = config_params.get("azure_api_type") or "azure"
-            "OPENAI_API_TYPE", config_params.get("azure_api_type", "azure")
+        self.openai_api_base = config_params.get("azure_api_base") or ""
-        )
+        self.openai_api_version = (
-        self.openai_api_base = os.getenv(
+            config_params.get("azure_api_version") or "2023-03-15-preview"
-            "OPENAI_AZURE_API_BASE", config_params.get("azure_api_base", "")
-        )
-        self.openai_api_version = os.getenv(
-            "OPENAI_AZURE_API_VERSION", config_params.get("azure_api_version", "")
         )
         self.azure_model_to_deployment_id_map = config_params.get("azure_model_map", [])
 
-    def set_continuous_mode(self, value: bool):
+    def set_continuous_mode(self, value: bool) -> None:
         """Set the continuous mode value."""
         self.continuous_mode = value
 
-    def set_continuous_limit(self, value: int):
+    def set_continuous_limit(self, value: int) -> None:
         """Set the continuous limit value."""
         self.continuous_limit = value
 
-    def set_speak_mode(self, value: bool):
+    def set_speak_mode(self, value: bool) -> None:
         """Set the speak mode value."""
         self.speak_mode = value
 
-    def set_fast_llm_model(self, value: str):
+    def set_fast_llm_model(self, value: str) -> None:
         """Set the fast LLM model value."""
         self.fast_llm_model = value
 
-    def set_smart_llm_model(self, value: str):
+    def set_smart_llm_model(self, value: str) -> None:
         """Set the smart LLM model value."""
         self.smart_llm_model = value
 
-    def set_fast_token_limit(self, value: int):
+    def set_fast_token_limit(self, value: int) -> None:
         """Set the fast token limit value."""
         self.fast_token_limit = value
 
-    def set_smart_token_limit(self, value: int):
+    def set_smart_token_limit(self, value: int) -> None:
         """Set the smart token limit value."""
         self.smart_token_limit = value
 
-    def set_browse_chunk_max_length(self, value: int):
+    def set_browse_chunk_max_length(self, value: int) -> None:
         """Set the browse_website command chunk max length value."""
         self.browse_chunk_max_length = value
 
-    def set_browse_summary_max_token(self, value: int):
+    def set_openai_api_key(self, value: str) -> None:
-        """Set the browse_website command summary max token value."""
-        self.browse_summary_max_token = value
-
-    def set_openai_api_key(self, value: str):
         """Set the OpenAI API key value."""
         self.openai_api_key = value
 
-    def set_elevenlabs_api_key(self, value: str):
+    def set_elevenlabs_api_key(self, value: str) -> None:
         """Set the ElevenLabs API key value."""
         self.elevenlabs_api_key = value
 
-    def set_elevenlabs_voice_1_id(self, value: str):
+    def set_elevenlabs_voice_1_id(self, value: str) -> None:
         """Set the ElevenLabs Voice 1 ID value."""
         self.elevenlabs_voice_1_id = value
 
-    def set_elevenlabs_voice_2_id(self, value: str):
+    def set_elevenlabs_voice_2_id(self, value: str) -> None:
         """Set the ElevenLabs Voice 2 ID value."""
         self.elevenlabs_voice_2_id = value
 
-    def set_google_api_key(self, value: str):
+    def set_google_api_key(self, value: str) -> None:
         """Set the Google API key value."""
         self.google_api_key = value
 
-    def set_custom_search_engine_id(self, value: str):
+    def set_custom_search_engine_id(self, value: str) -> None:
         """Set the custom search engine id value."""
         self.custom_search_engine_id = value
 
-    def set_pinecone_api_key(self, value: str):
+    def set_pinecone_api_key(self, value: str) -> None:
         """Set the Pinecone API key value."""
         self.pinecone_api_key = value
 
-    def set_pinecone_region(self, value: str):
+    def set_pinecone_region(self, value: str) -> None:
         """Set the Pinecone region value."""
         self.pinecone_region = value
 
-    def set_debug_mode(self, value: bool):
+    def set_debug_mode(self, value: bool) -> None:
         """Set the debug mode value."""
         self.debug_mode = value
+
+
+def check_openai_api_key() -> None:
+    """Check if the OpenAI API key is set in config.py or as an environment variable."""
+    cfg = Config()
+    if not cfg.openai_api_key:
+        print(
+            Fore.RED
+            + "Please set your OpenAI API key in .env or as an environment variable."
+        )
+        print("You can get your key from https://platform.openai.com/account/api-keys")
+        exit(1)

autogpt/config/singleton.py

@@ -0,0 +1,24 @@
+"""The singleton metaclass for ensuring only one instance of a class."""
+import abc
+
+
+class Singleton(abc.ABCMeta, type):
+    """
+    Singleton metaclass for ensuring only one instance of a class.
+    """
+
+    _instances = {}
+
+    def __call__(cls, *args, **kwargs):
+        """Call method for the singleton metaclass."""
+        if cls not in cls._instances:
+            cls._instances[cls] = super(Singleton, cls).__call__(*args, **kwargs)
+        return cls._instances[cls]
+
+
+class AbstractSingleton(abc.ABC, metaclass=Singleton):
+    """
+    Abstract singleton class for ensuring only one instance of a class.
+    """
+
+    pass

autogpt/configurator.py

@@ -0,0 +1,130 @@
+"""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,
+) -> 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
+
+    """
+    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 browser_name:
+        CFG.selenium_web_browser = browser_name

autogpt/execute_code.py

@@ -1,105 +0,0 @@
-import os
-import subprocess
-
-import docker
-from docker.errors import ImageNotFound
-
-WORKSPACE_FOLDER = "auto_gpt_workspace"
-
-
-def execute_python_file(file):
-    """Execute a Python file in a Docker container and return the output"""
-
-    print(f"Executing file '{file}' in workspace '{WORKSPACE_FOLDER}'")
-
-    if not file.endswith(".py"):
-        return "Error: Invalid file type. Only .py files are allowed."
-
-    file_path = os.path.join(WORKSPACE_FOLDER, file)
-
-    if not os.path.isfile(file_path):
-        return f"Error: File '{file}' does not exist."
-
-    if we_are_running_in_a_docker_container():
-        result = subprocess.run(
-            f"python {file_path}", capture_output=True, encoding="utf8", shell=True
-        )
-        if result.returncode == 0:
-            return result.stdout
-        else:
-            return f"Error: {result.stderr}"
-    else:
-        try:
-            client = docker.from_env()
-
-            image_name = "python:3.10"
-            try:
-                client.images.get(image_name)
-                print(f"Image '{image_name}' found locally")
-            except ImageNotFound:
-                print(
-                    f"Image '{image_name}' not found locally, pulling from Docker Hub"
-                )
-                # Use the low-level API to stream the pull response
-                low_level_client = docker.APIClient()
-                for line in low_level_client.pull(image_name, stream=True, decode=True):
-                    # Print the status and progress, if available
-                    status = line.get("status")
-                    progress = line.get("progress")
-                    if status and progress:
-                        print(f"{status}: {progress}")
-                    elif status:
-                        print(status)
-
-            # You can replace 'python:3.8' with the desired Python image/version
-            # You can find available Python images on Docker Hub:
-            # https://hub.docker.com/_/python
-            container = client.containers.run(
-                image_name,
-                f"python {file}",
-                volumes={
-                    os.path.abspath(WORKSPACE_FOLDER): {
-                        "bind": "/workspace",
-                        "mode": "ro",
-                    }
-                },
-                working_dir="/workspace",
-                stderr=True,
-                stdout=True,
-                detach=True,
-            )
-
-            container.wait()
-            logs = container.logs().decode("utf-8")
-            container.remove()
-
-            # print(f"Execution complete. Output: {output}")
-            # print(f"Logs: {logs}")
-
-            return logs
-
-        except Exception as e:
-            return f"Error: {str(e)}"
-
-
-def execute_shell(command_line):
-    current_dir = os.getcwd()
-
-    if WORKSPACE_FOLDER not in current_dir:  # Change dir into workspace if necessary
-        work_dir = os.path.join(os.getcwd(), WORKSPACE_FOLDER)
-        os.chdir(work_dir)
-
-    print(f"Executing command '{command_line}' in working directory '{os.getcwd()}'")
-
-    result = subprocess.run(command_line, capture_output=True, shell=True)
-    output = f"STDOUT:\n{result.stdout}\nSTDERR:\n{result.stderr}"
-
-    # Change back to whatever the prior working dir was
-
-    os.chdir(current_dir)
-
-    return output
-
-
-def we_are_running_in_a_docker_container():
-    os.path.exists("/.dockerenv")

autogpt/file_operations.py

@@ -1,141 +0,0 @@
-import os
-import os.path
-
-# Set a dedicated folder for file I/O
-working_directory = "auto_gpt_workspace"
-
-# Create the directory if it doesn't exist
-if not os.path.exists(working_directory):
-    os.makedirs(working_directory)
-
-
-def safe_join(base, *paths):
-    """Join one or more path components intelligently."""
-    new_path = os.path.join(base, *paths)
-    norm_new_path = os.path.normpath(new_path)
-
-    if os.path.commonprefix([base, norm_new_path]) != base:
-        raise ValueError("Attempted to access outside of working directory.")
-
-    return norm_new_path
-
-
-def split_file(content, max_length=4000, overlap=0):
-    """
-    Split text into chunks of a specified maximum length with a specified overlap
-    between chunks.
-
-    :param text: The input text to be split into chunks
-    :param max_length: The maximum length of each chunk,
-        default is 4000 (about 1k token)
-    :param overlap: The number of overlapping characters between chunks,
-        default is no overlap
-    :return: A generator yielding chunks of text
-    """
-    start = 0
-    content_length = len(content)
-
-    while start < content_length:
-        end = start + max_length
-        if end + overlap < content_length:
-            chunk = content[start : end + overlap]
-        else:
-            chunk = content[start:content_length]
-        yield chunk
-        start += max_length - overlap
-
-
-def read_file(filename) -> str:
-    """Read a file and return the contents"""
-    try:
-        filepath = safe_join(working_directory, filename)
-        with open(filepath, "r", encoding="utf-8") as f:
-            content = f.read()
-        return content
-    except Exception as e:
-        return f"Error: {str(e)}"
-
-
-def ingest_file(filename, memory, max_length=4000, overlap=200):
-    """
-    Ingest a file by reading its content, splitting it into chunks with a specified
-    maximum length and overlap, and adding the chunks to the memory storage.
-
-    :param filename: The name of the file to ingest
-    :param memory: An object with an add() method to store the chunks in memory
-    :param max_length: The maximum length of each chunk, default is 4000
-    :param overlap: The number of overlapping characters between chunks, default is 200
-    """
-    try:
-        print(f"Working with file {filename}")
-        content = read_file(filename)
-        content_length = len(content)
-        print(f"File length: {content_length} characters")
-
-        chunks = list(split_file(content, max_length=max_length, overlap=overlap))
-
-        num_chunks = len(chunks)
-        for i, chunk in enumerate(chunks):
-            print(f"Ingesting chunk {i + 1} / {num_chunks} into memory")
-            memory_to_add = (
-                f"Filename: {filename}\n" f"Content part#{i + 1}/{num_chunks}: {chunk}"
-            )
-
-            memory.add(memory_to_add)
-
-        print(f"Done ingesting {num_chunks} chunks from {filename}.")
-    except Exception as e:
-        print(f"Error while ingesting file '{filename}': {str(e)}")
-
-
-def write_to_file(filename, text):
-    """Write text to a file"""
-    try:
-        filepath = safe_join(working_directory, filename)
-        directory = os.path.dirname(filepath)
-        if not os.path.exists(directory):
-            os.makedirs(directory)
-        with open(filepath, "w", encoding="utf-8") as f:
-            f.write(text)
-        return "File written to successfully."
-    except Exception as e:
-        return "Error: " + str(e)
-
-
-def append_to_file(filename, text):
-    """Append text to a file"""
-    try:
-        filepath = safe_join(working_directory, filename)
-        with open(filepath, "a") as f:
-            f.write(text)
-        return "Text appended successfully."
-    except Exception as e:
-        return "Error: " + str(e)
-
-
-def delete_file(filename):
-    """Delete a file"""
-    try:
-        filepath = safe_join(working_directory, filename)
-        os.remove(filepath)
-        return "File deleted successfully."
-    except Exception as e:
-        return "Error: " + str(e)
-
-
-def search_files(directory):
-    found_files = []
-
-    if directory == "" or directory == "/":
-        search_directory = working_directory
-    else:
-        search_directory = safe_join(working_directory, directory)
-
-    for root, _, files in os.walk(search_directory):
-        for file in files:
-            if file.startswith("."):
-                continue
-            relative_path = os.path.relpath(os.path.join(root, file), working_directory)
-            found_files.append(relative_path)
-
-    return found_files

autogpt/image_gen.py

@@ -1,67 +0,0 @@
-import io
-import os.path
-import uuid
-from base64 import b64decode
-
-import openai
-import requests
-from PIL import Image
-
-from autogpt.config import Config
-
-cfg = Config()
-
-working_directory = "auto_gpt_workspace"
-
-
-def generate_image(prompt):
-    filename = str(uuid.uuid4()) + ".jpg"
-
-    # DALL-E
-    if cfg.image_provider == "dalle":
-        openai.api_key = cfg.openai_api_key
-
-        response = openai.Image.create(
-            prompt=prompt,
-            n=1,
-            size="256x256",
-            response_format="b64_json",
-        )
-
-        print("Image Generated for prompt:" + prompt)
-
-        image_data = b64decode(response["data"][0]["b64_json"])
-
-        with open(working_directory + "/" + filename, mode="wb") as png:
-            png.write(image_data)
-
-        return "Saved to disk:" + filename
-
-    # STABLE DIFFUSION
-    elif cfg.image_provider == "sd":
-        API_URL = (
-            "https://api-inference.huggingface.co/models/CompVis/stable-diffusion-v1-4"
-        )
-        if cfg.huggingface_api_token is None:
-            raise ValueError(
-                "You need to set your Hugging Face API token in the config file."
-            )
-        headers = {"Authorization": "Bearer " + cfg.huggingface_api_token}
-
-        response = requests.post(
-            API_URL,
-            headers=headers,
-            json={
-                "inputs": prompt,
-            },
-        )
-
-        image = Image.open(io.BytesIO(response.content))
-        print("Image Generated for prompt:" + prompt)
-
-        image.save(os.path.join(working_directory, filename))
-
-        return "Saved to disk:" + filename
-
-    else:
-        return "No Image Provider Set"

autogpt/json_fixes/auto_fix.py

@@ -0,0 +1,53 @@
+"""This module contains the function to fix JSON strings using GPT-3."""
+import json
+
+from autogpt.config import Config
+from autogpt.llm_utils import call_ai_function
+from autogpt.logs import logger
+
+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"

autogpt/json_fixes/bracket_termination.py

@@ -0,0 +1,37 @@
+"""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

autogpt/json_fixes/escaping.py

@@ -0,0 +1,33 @@
+""" 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

autogpt/json_fixes/master_json_fix_method.py

@@ -0,0 +1,33 @@
+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,
+        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 {}

autogpt/json_fixes/missing_quotes.py

@@ -0,0 +1,27 @@
+"""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

autogpt/json_fixes/parsing.py

@@ -0,0 +1,180 @@
+"""Fix and parse JSON strings."""
+from __future__ import annotations
+
+import contextlib
+import json
+from typing import Any, Dict, Union
+
+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.logs import logger
+from autogpt.speech import say_text
+
+CFG = Config()
+
+JSON_SCHEMA = """
+{
+    "command": {
+        "name": "command name",
+        "args": {
+            "arg name": "value"
+        }
+    },
+    "thoughts":
+    {
+        "text": "thought",
+        "reasoning": "reasoning",
+        "plan": "- short bulleted\n- list that conveys\n- long-term plan",
+        "criticism": "constructive self-criticism",
+        "speak": "thoughts summary to say to user"
+    }
+}
+"""
+
+
+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
+
+
+def fix_and_parse_json(
+    json_to_load: str, try_to_fix_with_gpt: bool = True
+) -> Dict[Any, Any]:
+    """Fix and parse JSON string
+
+    Args:
+        json_to_load (str): The JSON string.
+        try_to_fix_with_gpt (bool, optional): Try to fix the JSON with GPT.
+            Defaults to True.
+
+    Returns:
+        str or dict[Any, Any]: The parsed JSON.
+    """
+
+    with contextlib.suppress(json.JSONDecodeError):
+        json_to_load = json_to_load.replace("\t", "")
+        return json.loads(json_to_load)
+
+    with contextlib.suppress(json.JSONDecodeError):
+        json_to_load = correct_json(json_to_load)
+        return json.loads(json_to_load)
+    # Let's do something manually:
+    # sometimes GPT responds with something BEFORE the braces:
+    # "I'm sorry, I don't understand. Please try again."
+    # {"text": "I'm sorry, I don't understand. Please try again.",
+    #  "confidence": 0.0}
+    # So let's try to find the first brace and then parse the rest
+    #  of the string
+    try:
+        brace_index = json_to_load.index("{")
+        maybe_fixed_json = json_to_load[brace_index:]
+        last_brace_index = maybe_fixed_json.rindex("}")
+        maybe_fixed_json = maybe_fixed_json[: last_brace_index + 1]
+        return json.loads(maybe_fixed_json)
+    except (json.JSONDecodeError, ValueError) as e:
+        return try_ai_fix(try_to_fix_with_gpt, e, json_to_load)
+
+
+def try_ai_fix(
+    try_to_fix_with_gpt: bool, exception: Exception, json_to_load: str
+) -> Dict[Any, Any]:
+    """Try to fix the JSON with the AI
+
+    Args:
+        try_to_fix_with_gpt (bool): Whether to try to fix the JSON with the AI.
+        exception (Exception): The exception that was raised.
+        json_to_load (str): The JSON string to load.
+
+    Raises:
+        exception: If try_to_fix_with_gpt is False.
+
+    Returns:
+        str or dict[Any, Any]: The JSON string or dictionary.
+    """
+    if not try_to_fix_with_gpt:
+        raise exception
+    if CFG.debug_mode:
+        logger.warn(
+            "Warning: Failed to parse AI output, attempting to fix."
+            "\n If you see this warning frequently, it's likely that"
+            " your prompt is confusing the AI. Try changing it up"
+            " slightly."
+        )
+    # Now try to fix this up using the ai_functions
+    ai_fixed_json = fix_json(json_to_load, JSON_SCHEMA)
+
+    if ai_fixed_json != "failed":
+        return json.loads(ai_fixed_json)
+    # This allows the AI to react to the error message,
+    #   which usually results in it correcting its ways.
+    # logger.error("Failed to fix AI output, telling the AI.")
+    return {}
+
+
+def attempt_to_fix_json_by_finding_outermost_brackets(json_string: str):
+    if CFG.speak_mode and CFG.debug_mode:
+        say_text(
+            "I have received an invalid JSON response from the OpenAI API. "
+            "Trying to fix it now."
+        )
+        logger.error("Attempting to fix JSON by finding outermost brackets\n")
+
+    try:
+        json_pattern = regex.compile(r"\{(?:[^{}]|(?R))*\}")
+        json_match = json_pattern.search(json_string)
+
+        if json_match:
+            # Extract the valid JSON object from the string
+            json_string = json_match.group(0)
+            logger.typewriter_log(
+                title="Apparently json was fixed.", title_color=Fore.GREEN
+            )
+            if CFG.speak_mode and CFG.debug_mode:
+                say_text("Apparently json was fixed.")
+        else:
+            return {}
+
+    except (json.JSONDecodeError, ValueError):
+        if CFG.debug_mode:
+            logger.error(f"Error: Invalid JSON: {json_string}\n")
+        if CFG.speak_mode:
+            say_text("Didn't work. I will have to ignore this response then.")
+        logger.error("Error: Invalid JSON, setting it to empty JSON now.\n")
+        json_string = {}
+
+    return fix_and_parse_json(json_string)

autogpt/json_fixes/utilities.py

@@ -0,0 +1,20 @@
+"""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.")

autogpt/json_parser.py

@@ -1,113 +0,0 @@
-import json
-from typing import Any, Dict, Union
-
-from autogpt.call_ai_function import call_ai_function
-from autogpt.config import Config
-from autogpt.json_utils import correct_json
-from autogpt.logger import logger
-
-cfg = Config()
-
-JSON_SCHEMA = """
-{
-    "command": {
-        "name": "command name",
-        "args": {
-            "arg name": "value"
-        }
-    },
-    "thoughts":
-    {
-        "text": "thought",
-        "reasoning": "reasoning",
-        "plan": "- short bulleted\n- list that conveys\n- long-term plan",
-        "criticism": "constructive self-criticism",
-        "speak": "thoughts summary to say to user"
-    }
-}
-"""
-
-
-def fix_and_parse_json(
-    json_str: str, try_to_fix_with_gpt: bool = True
-) -> Union[str, Dict[Any, Any]]:
-    """Fix and parse JSON string"""
-    try:
-        json_str = json_str.replace("\t", "")
-        return json.loads(json_str)
-    except json.JSONDecodeError as _:  # noqa: F841
-        try:
-            json_str = correct_json(json_str)
-            return json.loads(json_str)
-        except json.JSONDecodeError as _:  # noqa: F841
-            pass
-    # Let's do something manually:
-    # sometimes GPT responds with something BEFORE the braces:
-    # "I'm sorry, I don't understand. Please try again."
-    # {"text": "I'm sorry, I don't understand. Please try again.",
-    #  "confidence": 0.0}
-    # So let's try to find the first brace and then parse the rest
-    #  of the string
-    try:
-        brace_index = json_str.index("{")
-        json_str = json_str[brace_index:]
-        last_brace_index = json_str.rindex("}")
-        json_str = json_str[: last_brace_index + 1]
-        return json.loads(json_str)
-    # Can throw a ValueError if there is no "{" or "}" in the json_str
-    except (json.JSONDecodeError, ValueError) as e:  # noqa: F841
-        if try_to_fix_with_gpt:
-            logger.warn(
-                "Warning: Failed to parse AI output, attempting to fix."
-                "\n If you see this warning frequently, it's likely that"
-                " your prompt is confusing the AI. Try changing it up"
-                " slightly."
-            )
-            # Now try to fix this up using the ai_functions
-            ai_fixed_json = fix_json(json_str, JSON_SCHEMA)
-
-            if ai_fixed_json != "failed":
-                return json.loads(ai_fixed_json)
-            else:
-                # This allows the AI to react to the error message,
-                #   which usually results in it correcting its ways.
-                logger.error("Failed to fix AI output, telling the AI.")
-                return json_str
-        else:
-            raise e
-
-
-def fix_json(json_str: str, schema: str) -> str:
-    """Fix the given JSON string to make it parseable and fully compliant with the provided schema."""
-    # Try to fix the JSON using GPT:
-    function_string = "def fix_json(json_str: str, schema:str=None) -> str:"
-    args = [f"'''{json_str}'''", f"'''{schema}'''"]
-    description_string = (
-        "Fixes the provided JSON string to make it parseable"
-        " and fully compliant with the provided schema.\n If an object or"
-        " field specified in the schema isn't contained within the correct"
-        " JSON, it is omitted.\n This function is brilliant at guessing"
-        " when the format is incorrect."
-    )
-
-    # If it doesn't already start with a "`", add one:
-    if not json_str.startswith("`"):
-        json_str = "```json\n" + json_str + "\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_str}")
-    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:  # noqa: E722
-        # Get the call stack:
-        # import traceback
-        # call_stack = traceback.format_exc()
-        # print(f"Failed to fix JSON: '{json_str}' "+call_stack)
-        return "failed"

autogpt/json_schemas/llm_response_format_1.json

@@ -0,0 +1,31 @@
+{
+    "$schema": "http://json-schema.org/draft-07/schema#",
+    "type": "object",
+    "properties": {
+        "thoughts": {
+            "type": "object",
+            "properties": {
+                "text": {"type": "string"},
+                "reasoning": {"type": "string"},
+                "plan": {"type": "string"},
+                "criticism": {"type": "string"},
+                "speak": {"type": "string"}
+            },
+            "required": ["text", "reasoning", "plan", "criticism", "speak"],
+            "additionalProperties": false
+        },
+        "command": {
+            "type": "object",
+            "properties": {
+                "name": {"type": "string"},
+                "args": {
+                    "type": "object"
+                }
+            },
+            "required": ["name", "args"],
+            "additionalProperties": false
+        }
+    },
+    "required": ["thoughts", "command"],
+    "additionalProperties": false
+}

autogpt/json_utils.py

@@ -1,128 +0,0 @@
-import json
-import re
-from typing import Optional
-
-from autogpt.config import Config
-
-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.
-    """
-    import re
-
-    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 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):
-        return f'"{match.group(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 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
-
-    try:
-        json.loads(json_string)
-        return json_string
-    except json.JSONDecodeError:
-        pass
-
-
-def fix_invalid_escape(json_str: str, error_message: str) -> str:
-    while error_message.startswith("Invalid \\escape"):
-        bad_escape_location = extract_char_position(error_message)
-        json_str = json_str[:bad_escape_location] + json_str[bad_escape_location + 1 :]
-        try:
-            json.loads(json_str)
-            return json_str
-        except json.JSONDecodeError as e:
-            if cfg.debug_mode:
-                print("json loads error - fix invalid escape", e)
-            error_message = str(e)
-    return json_str
-
-
-def correct_json(json_str: str) -> str:
-    """
-    Correct common JSON errors.
-
-    Args:
-        json_str (str): The JSON string.
-    """
-
-    try:
-        if cfg.debug_mode:
-            print("json", json_str)
-        json.loads(json_str)
-        return json_str
-    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_str = fix_invalid_escape(json_str, error_message)
-        if error_message.startswith(
-            "Expecting property name enclosed in double quotes"
-        ):
-            json_str = add_quotes_to_property_names(json_str)
-            try:
-                json.loads(json_str)
-                return json_str
-            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_str):
-            return balanced_str
-    return json_str

autogpt/json_validation/validate_json.py

@@ -0,0 +1,34 @@
+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

autogpt/llm_utils.py

@@ -1,35 +1,89 @@
+from __future__ import annotations
+
 import time
+from ast import List
 
 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
 
-cfg = Config()
+CFG = Config()
 
-openai.api_key = cfg.openai_api_key
+openai.api_key = CFG.openai_api_key
+
+
+def call_ai_function(
+    function: str, args: list, description: str, model: str | None = None
+) -> str:
+    """Call an AI function
+
+    This is a magic function that can do anything with no-code. See
+    https://github.com/Torantulino/AI-Functions for more info.
+
+    Args:
+        function (str): The function to call
+        args (list): The arguments to pass to the function
+        description (str): The description of the function
+        model (str, optional): The model to use. Defaults to None.
+
+    Returns:
+        str: The response from the function
+    """
+    if model is None:
+        model = CFG.smart_llm_model
+    # 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 = [
+        {
+            "role": "system",
+            "content": f"You are now the following python function: ```# {description}"
+            f"\n{function}```\n\nOnly respond with your `return` value.",
+        },
+        {"role": "user", "content": args},
+    ]
+
+    return create_chat_completion(model=model, messages=messages, temperature=0)
 
 
 # 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, model=None, temperature=cfg.temperature, max_tokens=None
+    messages: list,  # type: ignore
+    model: str | None = None,
+    temperature: float = CFG.temperature,
+    max_tokens: int | None = None,
 ) -> str:
-    """Create a chat completion using the OpenAI API"""
+    """Create a chat completion using the OpenAI API
+
+    Args:
+        messages (list[dict[str, str]]): 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.
+
+    Returns:
+        str: The response from the chat completion
+    """
     response = None
-    num_retries = 5
+    num_retries = 10
-    if cfg.debug_mode:
+    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
         )
     for attempt in range(num_retries):
+        backoff = 2 ** (attempt + 2)
         try:
-            if cfg.use_azure:
+            if CFG.use_azure:
                 response = openai.ChatCompletion.create(
-                    deployment_id=cfg.get_azure_deployment_id_for_model(model),
+                    deployment_id=CFG.get_azure_deployment_id_for_model(model),
                     model=model,
                     messages=messages,
                     temperature=temperature,
@@ -44,26 +98,75 @@ def create_chat_completion(
                 )
             break
         except RateLimitError:
-            if cfg.debug_mode:
+            if CFG.debug_mode:
                 print(
                     Fore.RED + "Error: ",
-                    "API Rate Limit Reached. Waiting 20 seconds..." + Fore.RESET,
+                    f"Reached rate limit, passing..." + Fore.RESET,
                 )
-            time.sleep(20)
+            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:
-                if cfg.debug_mode:
+                pass
-                    print(
-                        Fore.RED + "Error: ",
-                        "API Bad gateway. Waiting 20 seconds..." + Fore.RESET,
-                    )
-                time.sleep(20)
             else:
                 raise
             if attempt == num_retries - 1:
                 raise
-
+        if CFG.debug_mode:
+            print(
+                Fore.RED + "Error: ",
+                f"API Bad gateway. Waiting {backoff} seconds..." + Fore.RESET,
+            )
+        time.sleep(backoff)
     if response is None:
-        raise RuntimeError("Failed to get response after 5 retries")
+        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)
 
     return response.choices[0].message["content"]
+
+
+def create_embedding_with_ada(text) -> list:
+    """Create an embedding with text-ada-002 using the OpenAI SDK"""
+    num_retries = 10
+    for attempt in range(num_retries):
+        backoff = 2 ** (attempt + 2)
+        try:
+            if CFG.use_azure:
+                return openai.Embedding.create(
+                    input=[text],
+                    engine=CFG.get_azure_deployment_id_for_model(
+                        "text-embedding-ada-002"
+                    ),
+                )["data"][0]["embedding"]
+            else:
+                return openai.Embedding.create(
+                    input=[text], model="text-embedding-ada-002"
+                )["data"][0]["embedding"]
+        except RateLimitError:
+            pass
+        except APIError as e:
+            if e.http_status == 502:
+                pass
+            else:
+                raise
+            if attempt == num_retries - 1:
+                raise
+        if CFG.debug_mode:
+            print(
+                Fore.RED + "Error: ",
+                f"API Bad gateway. Waiting {backoff} seconds..." + Fore.RESET,
+            )
+        time.sleep(backoff)

autogpt/logger.py

@@ -1,195 +0,0 @@
-import logging
-import os
-import random
-import re
-import time
-from logging import LogRecord
-
-from colorama import Fore, Style
-
-from autogpt import speak
-from autogpt.config import Config, Singleton
-
-cfg = Config()
-
-"""
-Logger that handle titles in different colors.
-Outputs logs in console, activity.log, and errors.log
-For console handler: simulates typing
-"""
-
-
-class Logger(metaclass=Singleton):
-    def __init__(self):
-        # create log directory if it doesn't exist
-        this_files_dir_path = os.path.dirname(__file__)
-        log_dir = os.path.join(this_files_dir_path, "../logs")
-        if not os.path.exists(log_dir):
-            os.makedirs(log_dir)
-
-        log_file = "activity.log"
-        error_file = "error.log"
-
-        console_formatter = AutoGptFormatter("%(title_color)s %(message)s")
-
-        # Create a handler for console which simulate typing
-        self.typing_console_handler = TypingConsoleHandler()
-        self.typing_console_handler.setLevel(logging.INFO)
-        self.typing_console_handler.setFormatter(console_formatter)
-
-        # Create a handler for console without typing simulation
-        self.console_handler = ConsoleHandler()
-        self.console_handler.setLevel(logging.DEBUG)
-        self.console_handler.setFormatter(console_formatter)
-
-        # Info handler in activity.log
-        self.file_handler = logging.FileHandler(os.path.join(log_dir, log_file))
-        self.file_handler.setLevel(logging.DEBUG)
-        info_formatter = AutoGptFormatter(
-            "%(asctime)s %(levelname)s %(title)s %(message_no_color)s"
-        )
-        self.file_handler.setFormatter(info_formatter)
-
-        # Error handler error.log
-        error_handler = logging.FileHandler(os.path.join(log_dir, error_file))
-        error_handler.setLevel(logging.ERROR)
-        error_formatter = AutoGptFormatter(
-            "%(asctime)s %(levelname)s %(module)s:%(funcName)s:%(lineno)d %(title)s"
-            " %(message_no_color)s"
-        )
-        error_handler.setFormatter(error_formatter)
-
-        self.typing_logger = logging.getLogger("TYPER")
-        self.typing_logger.addHandler(self.typing_console_handler)
-        self.typing_logger.addHandler(self.file_handler)
-        self.typing_logger.addHandler(error_handler)
-        self.typing_logger.setLevel(logging.DEBUG)
-
-        self.logger = logging.getLogger("LOGGER")
-        self.logger.addHandler(self.console_handler)
-        self.logger.addHandler(self.file_handler)
-        self.logger.addHandler(error_handler)
-        self.logger.setLevel(logging.DEBUG)
-
-    def typewriter_log(
-        self, title="", title_color="", content="", speak_text=False, level=logging.INFO
-    ):
-        if speak_text and cfg.speak_mode:
-            speak.say_text(f"{title}. {content}")
-
-        if content:
-            if isinstance(content, list):
-                content = " ".join(content)
-        else:
-            content = ""
-
-        self.typing_logger.log(
-            level, content, extra={"title": title, "color": title_color}
-        )
-
-    def debug(
-        self,
-        message,
-        title="",
-        title_color="",
-    ):
-        self._log(title, title_color, message, logging.DEBUG)
-
-    def warn(
-        self,
-        message,
-        title="",
-        title_color="",
-    ):
-        self._log(title, title_color, message, logging.WARN)
-
-    def error(self, title, message=""):
-        self._log(title, Fore.RED, message, logging.ERROR)
-
-    def _log(self, title="", title_color="", message="", level=logging.INFO):
-        if message:
-            if isinstance(message, list):
-                message = " ".join(message)
-        self.logger.log(level, message, extra={"title": title, "color": title_color})
-
-    def set_level(self, level):
-        self.logger.setLevel(level)
-        self.typing_logger.setLevel(level)
-
-    def double_check(self, additionalText=None):
-        if not additionalText:
-            additionalText = (
-                "Please ensure you've setup and configured everything"
-                " correctly. Read https://github.com/Torantulino/Auto-GPT#readme to "
-                "double check. You can also create a github issue or join the discord"
-                " and ask there!"
-            )
-
-        self.typewriter_log("DOUBLE CHECK CONFIGURATION", Fore.YELLOW, additionalText)
-
-
-"""
-Output stream to console using simulated typing
-"""
-
-
-class TypingConsoleHandler(logging.StreamHandler):
-    def emit(self, record):
-        min_typing_speed = 0.05
-        max_typing_speed = 0.01
-
-        msg = self.format(record)
-        try:
-            words = msg.split()
-            for i, word in enumerate(words):
-                print(word, end="", flush=True)
-                if i < len(words) - 1:
-                    print(" ", end="", flush=True)
-                typing_speed = random.uniform(min_typing_speed, max_typing_speed)
-                time.sleep(typing_speed)
-                # type faster after each word
-                min_typing_speed = min_typing_speed * 0.95
-                max_typing_speed = max_typing_speed * 0.95
-            print()
-        except Exception:
-            self.handleError(record)
-
-
-class ConsoleHandler(logging.StreamHandler):
-    def emit(self, record) -> None:
-        msg = self.format(record)
-        try:
-            print(msg)
-        except Exception:
-            self.handleError(record)
-
-
-class AutoGptFormatter(logging.Formatter):
-    """
-    Allows to handle custom placeholders 'title_color' and 'message_no_color'.
-    To use this formatter, make sure to pass 'color', 'title' as log extras.
-    """
-
-    def format(self, record: LogRecord) -> str:
-        if hasattr(record, "color"):
-            record.title_color = (
-                getattr(record, "color")
-                + getattr(record, "title")
-                + " "
-                + Style.RESET_ALL
-            )
-        else:
-            record.title_color = getattr(record, "title")
-        if hasattr(record, "msg"):
-            record.message_no_color = remove_color_codes(getattr(record, "msg"))
-        else:
-            record.message_no_color = ""
-        return super().format(record)
-
-
-def remove_color_codes(s: str) -> str:
-    ansi_escape = re.compile(r"\x1B(?:[@-Z\\-_]|\[[0-?]*[ -/]*[@-~])")
-    return ansi_escape.sub("", s)
-
-
-logger = Logger()

autogpt/logs.py

@@ -0,0 +1,332 @@
+"""Logging module for Auto-GPT."""
+import json
+import logging
+import os
+import random
+import re
+import time
+import traceback
+from logging import LogRecord
+
+from colorama import Fore, Style
+
+from autogpt.config import Config, Singleton
+from autogpt.speech import say_text
+
+CFG = Config()
+
+
+class Logger(metaclass=Singleton):
+    """
+    Logger that handle titles in different colors.
+    Outputs logs in console, activity.log, and errors.log
+    For console handler: simulates typing
+    """
+
+    def __init__(self):
+        # create log directory if it doesn't exist
+        this_files_dir_path = os.path.dirname(__file__)
+        log_dir = os.path.join(this_files_dir_path, "../logs")
+        if not os.path.exists(log_dir):
+            os.makedirs(log_dir)
+
+        log_file = "activity.log"
+        error_file = "error.log"
+
+        console_formatter = AutoGptFormatter("%(title_color)s %(message)s")
+
+        # Create a handler for console which simulate typing
+        self.typing_console_handler = TypingConsoleHandler()
+        self.typing_console_handler.setLevel(logging.INFO)
+        self.typing_console_handler.setFormatter(console_formatter)
+
+        # Create a handler for console without typing simulation
+        self.console_handler = ConsoleHandler()
+        self.console_handler.setLevel(logging.DEBUG)
+        self.console_handler.setFormatter(console_formatter)
+
+        # Info handler in activity.log
+        self.file_handler = logging.FileHandler(
+            os.path.join(log_dir, log_file), "a", "utf-8"
+        )
+        self.file_handler.setLevel(logging.DEBUG)
+        info_formatter = AutoGptFormatter(
+            "%(asctime)s %(levelname)s %(title)s %(message_no_color)s"
+        )
+        self.file_handler.setFormatter(info_formatter)
+
+        # Error handler error.log
+        error_handler = logging.FileHandler(
+            os.path.join(log_dir, error_file), "a", "utf-8"
+        )
+        error_handler.setLevel(logging.ERROR)
+        error_formatter = AutoGptFormatter(
+            "%(asctime)s %(levelname)s %(module)s:%(funcName)s:%(lineno)d %(title)s"
+            " %(message_no_color)s"
+        )
+        error_handler.setFormatter(error_formatter)
+
+        self.typing_logger = logging.getLogger("TYPER")
+        self.typing_logger.addHandler(self.typing_console_handler)
+        self.typing_logger.addHandler(self.file_handler)
+        self.typing_logger.addHandler(error_handler)
+        self.typing_logger.setLevel(logging.DEBUG)
+
+        self.logger = logging.getLogger("LOGGER")
+        self.logger.addHandler(self.console_handler)
+        self.logger.addHandler(self.file_handler)
+        self.logger.addHandler(error_handler)
+        self.logger.setLevel(logging.DEBUG)
+
+    def typewriter_log(
+        self, title="", title_color="", content="", speak_text=False, level=logging.INFO
+    ):
+        if speak_text and CFG.speak_mode:
+            say_text(f"{title}. {content}")
+
+        if content:
+            if isinstance(content, list):
+                content = " ".join(content)
+        else:
+            content = ""
+
+        self.typing_logger.log(
+            level, content, extra={"title": title, "color": title_color}
+        )
+
+    def debug(
+        self,
+        message,
+        title="",
+        title_color="",
+    ):
+        self._log(title, title_color, message, logging.DEBUG)
+
+    def warn(
+        self,
+        message,
+        title="",
+        title_color="",
+    ):
+        self._log(title, title_color, message, logging.WARN)
+
+    def error(self, title, message=""):
+        self._log(title, Fore.RED, message, logging.ERROR)
+
+    def _log(self, title="", title_color="", message="", level=logging.INFO):
+        if message:
+            if isinstance(message, list):
+                message = " ".join(message)
+        self.logger.log(level, message, extra={"title": title, "color": title_color})
+
+    def set_level(self, level):
+        self.logger.setLevel(level)
+        self.typing_logger.setLevel(level)
+
+    def double_check(self, additionalText=None):
+        if not additionalText:
+            additionalText = (
+                "Please ensure you've setup and configured everything"
+                " correctly. Read https://github.com/Torantulino/Auto-GPT#readme to "
+                "double check. You can also create a github issue or join the discord"
+                " and ask there!"
+            )
+
+        self.typewriter_log("DOUBLE CHECK CONFIGURATION", Fore.YELLOW, additionalText)
+
+
+"""
+Output stream to console using simulated typing
+"""
+
+
+class TypingConsoleHandler(logging.StreamHandler):
+    def emit(self, record):
+        min_typing_speed = 0.05
+        max_typing_speed = 0.01
+
+        msg = self.format(record)
+        try:
+            words = msg.split()
+            for i, word in enumerate(words):
+                print(word, end="", flush=True)
+                if i < len(words) - 1:
+                    print(" ", end="", flush=True)
+                typing_speed = random.uniform(min_typing_speed, max_typing_speed)
+                time.sleep(typing_speed)
+                # type faster after each word
+                min_typing_speed = min_typing_speed * 0.95
+                max_typing_speed = max_typing_speed * 0.95
+            print()
+        except Exception:
+            self.handleError(record)
+
+
+class ConsoleHandler(logging.StreamHandler):
+    def emit(self, record) -> None:
+        msg = self.format(record)
+        try:
+            print(msg)
+        except Exception:
+            self.handleError(record)
+
+
+class AutoGptFormatter(logging.Formatter):
+    """
+    Allows to handle custom placeholders 'title_color' and 'message_no_color'.
+    To use this formatter, make sure to pass 'color', 'title' as log extras.
+    """
+
+    def format(self, record: LogRecord) -> str:
+        if hasattr(record, "color"):
+            record.title_color = (
+                getattr(record, "color")
+                + getattr(record, "title")
+                + " "
+                + Style.RESET_ALL
+            )
+        else:
+            record.title_color = getattr(record, "title")
+        if hasattr(record, "msg"):
+            record.message_no_color = remove_color_codes(getattr(record, "msg"))
+        else:
+            record.message_no_color = ""
+        return super().format(record)
+
+
+def remove_color_codes(s: str) -> str:
+    ansi_escape = re.compile(r"\x1B(?:[@-Z\\-_]|\[[0-?]*[ -/]*[@-~])")
+    return ansi_escape.sub("", s)
+
+
+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 (
+        attempt_to_fix_json_by_finding_outermost_brackets,
+    )
+    from autogpt.json_fixes.parsing import fix_and_parse_json
+
+    try:
+        try:
+            # Parse and print Assistant response
+            assistant_reply_json = fix_and_parse_json(assistant_reply)
+        except json.JSONDecodeError:
+            logger.error("Error: Invalid JSON in assistant thoughts\n", assistant_reply)
+            assistant_reply_json = attempt_to_fix_json_by_finding_outermost_brackets(
+                assistant_reply
+            )
+            if isinstance(assistant_reply_json, str):
+                assistant_reply_json = fix_and_parse_json(assistant_reply_json)
+
+        # Check if assistant_reply_json is a string and attempt to parse
+        # it into a JSON object
+        if isinstance(assistant_reply_json, str):
+            try:
+                assistant_reply_json = json.loads(assistant_reply_json)
+            except json.JSONDecodeError:
+                logger.error("Error: Invalid JSON\n", assistant_reply)
+                assistant_reply_json = (
+                    attempt_to_fix_json_by_finding_outermost_brackets(
+                        assistant_reply_json
+                    )
+                )
+
+        assistant_thoughts_reasoning = None
+        assistant_thoughts_plan = None
+        assistant_thoughts_speak = None
+        assistant_thoughts_criticism = None
+        if not isinstance(assistant_reply_json, dict):
+            assistant_reply_json = {}
+        assistant_thoughts = assistant_reply_json.get("thoughts", {})
+        assistant_thoughts_text = assistant_thoughts.get("text")
+
+        if assistant_thoughts:
+            assistant_thoughts_reasoning = assistant_thoughts.get("reasoning")
+            assistant_thoughts_plan = assistant_thoughts.get("plan")
+            assistant_thoughts_criticism = assistant_thoughts.get("criticism")
+            assistant_thoughts_speak = assistant_thoughts.get("speak")
+
+        logger.typewriter_log(
+            f"{ai_name.upper()} THOUGHTS:", Fore.YELLOW, f"{assistant_thoughts_text}"
+        )
+        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
+            if isinstance(assistant_thoughts_plan, list):
+                assistant_thoughts_plan = "\n".join(assistant_thoughts_plan)
+            elif isinstance(assistant_thoughts_plan, dict):
+                assistant_thoughts_plan = str(assistant_thoughts_plan)
+
+            # Split the input_string using the newline character and dashes
+            lines = assistant_thoughts_plan.split("\n")
+            for line in lines:
+                line = line.lstrip("- ")
+                logger.typewriter_log("- ", Fore.GREEN, line.strip())
+
+        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)
+        else:
+            logger.typewriter_log("SPEAK:", Fore.YELLOW, f"{assistant_thoughts_speak}")
+
+        return assistant_reply_json
+    except json.decoder.JSONDecodeError:
+        logger.error("Error: Invalid JSON\n", assistant_reply)
+        if CFG.speak_mode:
+            say_text(
+                "I have received an invalid JSON response from the OpenAI API."
+                " I cannot ignore this response."
+            )
+
+    # All other errors, return "Error: + error message"
+    except Exception:
+        call_stack = traceback.format_exc()
+        logger.error("Error: \n", call_stack)
+
+
+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
+    assistant_thoughts_criticism = None
+
+    assistant_thoughts = assistant_reply_json_valid.get("thoughts", {})
+    assistant_thoughts_text = assistant_thoughts.get("text")
+    if assistant_thoughts:
+        assistant_thoughts_reasoning = assistant_thoughts.get("reasoning")
+        assistant_thoughts_plan = assistant_thoughts.get("plan")
+        assistant_thoughts_criticism = assistant_thoughts.get("criticism")
+        assistant_thoughts_speak = assistant_thoughts.get("speak")
+    logger.typewriter_log(
+        f"{ai_name.upper()} THOUGHTS:", Fore.YELLOW, f"{assistant_thoughts_text}"
+    )
+    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
+        if isinstance(assistant_thoughts_plan, list):
+            assistant_thoughts_plan = "\n".join(assistant_thoughts_plan)
+        elif isinstance(assistant_thoughts_plan, dict):
+            assistant_thoughts_plan = str(assistant_thoughts_plan)
+
+        # Split the input_string using the newline character and dashes
+        lines = assistant_thoughts_plan.split("\n")
+        for line in lines:
+            line = line.lstrip("- ")
+            logger.typewriter_log("- ", Fore.GREEN, line.strip())
+    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)

autogpt/memory/__init__.py

@@ -10,7 +10,7 @@ try:
 
     supported_memory.append("redis")
 except ImportError:
-    print("Redis not installed. Skipping import.")
+    # print("Redis not installed. Skipping import.")
     RedisMemory = None
 
 try:
@@ -18,9 +18,25 @@ try:
 
     supported_memory.append("pinecone")
 except ImportError:
-    print("Pinecone not installed. Skipping import.")
+    # print("Pinecone not installed. Skipping import.")
     PineconeMemory = None
 
+try:
+    from autogpt.memory.weaviate import WeaviateMemory
+
+    supported_memory.append("weaviate")
+except ImportError:
+    # print("Weaviate not installed. Skipping import.")
+    WeaviateMemory = None
+
+try:
+    from autogpt.memory.milvus import MilvusMemory
+
+    supported_memory.append("milvus")
+except ImportError:
+    # print("pymilvus not installed. Skipping import.")
+    MilvusMemory = None
+
 
 def get_memory(cfg, init=False):
     memory = None
@@ -42,6 +58,22 @@ def get_memory(cfg, init=False):
             )
         else:
             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."
+            )
+        else:
+            memory = WeaviateMemory(cfg)
+    elif cfg.memory_backend == "milvus":
+        if not MilvusMemory:
+            print(
+                "Error: Milvus sdk is not installed."
+                "Please install pymilvus to use Milvus as memory backend."
+            )
+        else:
+            memory = MilvusMemory(cfg)
     elif cfg.memory_backend == "no_memory":
         memory = NoMemory(cfg)
 
@@ -56,4 +88,12 @@ def get_supported_memory_backends():
     return supported_memory
 
 
-__all__ = ["get_memory", "LocalCache", "RedisMemory", "PineconeMemory", "NoMemory"]
+__all__ = [
+    "get_memory",
+    "LocalCache",
+    "RedisMemory",
+    "PineconeMemory",
+    "NoMemory",
+    "MilvusMemory",
+    "WeaviateMemory",
+]

autogpt/memory/local.py

@@ -1,11 +1,14 @@
+from __future__ import annotations
+
 import dataclasses
 import os
-from typing import Any, List, Optional
+from typing import Any, List
 
 import numpy as np
 import orjson
 
-from autogpt.memory.base import MemoryProviderSingleton, get_ada_embedding
+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
@@ -24,8 +27,17 @@ class CacheContent:
 
 
 class LocalCache(MemoryProviderSingleton):
-    # on load, load our database
+    """A class that stores the memory in a local file"""
+
     def __init__(self, cfg) -> None:
+        """Initialize a class instance
+
+        Args:
+            cfg: Config object
+
+        Returns:
+            None
+        """
         self.filename = f"{cfg.memory_index}.json"
         if os.path.exists(self.filename):
             try:
@@ -42,7 +54,8 @@ class LocalCache(MemoryProviderSingleton):
                 self.data = CacheContent()
         else:
             print(
-                f"Warning: The file '{self.filename}' does not exist. Local memory would not be saved to a file."
+                f"Warning: The file '{self.filename}' does not exist. "
+                "Local memory would not be saved to a file."
             )
             self.data = CacheContent()
 
@@ -60,7 +73,7 @@ class LocalCache(MemoryProviderSingleton):
             return ""
         self.data.texts.append(text)
 
-        embedding = get_ada_embedding(text)
+        embedding = create_embedding_with_ada(text)
 
         vector = np.array(embedding).astype(np.float32)
         vector = vector[np.newaxis, :]
@@ -86,7 +99,7 @@ class LocalCache(MemoryProviderSingleton):
         self.data = CacheContent()
         return "Obliviated"
 
-    def get(self, data: str) -> Optional[List[Any]]:
+    def get(self, data: str) -> list[Any] | None:
         """
         Gets the data from the memory that is most relevant to the given data.
 
@@ -97,7 +110,7 @@ class LocalCache(MemoryProviderSingleton):
         """
         return self.get_relevant(data, 1)
 
-    def get_relevant(self, text: str, k: int) -> List[Any]:
+    def get_relevant(self, text: str, k: int) -> list[Any]:
         """ "
         matrix-vector mult to find score-for-each-row-of-matrix
          get indices for top-k winning scores
@@ -108,7 +121,7 @@ class LocalCache(MemoryProviderSingleton):
 
         Returns: List[str]
         """
-        embedding = get_ada_embedding(text)
+        embedding = create_embedding_with_ada(text)
 
         scores = np.dot(self.data.embeddings, embedding)
 
@@ -116,7 +129,7 @@ class LocalCache(MemoryProviderSingleton):
 
         return [self.data.texts[i] for i in top_k_indices]
 
-    def get_stats(self):
+    def get_stats(self) -> tuple[int, tuple[int, ...]]:
         """
         Returns: The stats of the local cache.
         """

autogpt/memory/milvus.py

@@ -0,0 +1,115 @@
+""" Milvus memory storage provider."""
+from pymilvus import Collection, CollectionSchema, DataType, FieldSchema, connections
+
+from autogpt.memory.base import MemoryProviderSingleton, get_ada_embedding
+
+
+class MilvusMemory(MemoryProviderSingleton):
+    """Milvus memory storage provider."""
+
+    def __init__(self, cfg) -> None:
+        """Construct a milvus memory storage connection.
+
+        Args:
+            cfg (Config): Auto-GPT global config.
+        """
+        # connect to milvus server.
+        connections.connect(address=cfg.milvus_addr)
+        fields = [
+            FieldSchema(name="pk", dtype=DataType.INT64, is_primary=True, auto_id=True),
+            FieldSchema(name="embeddings", dtype=DataType.FLOAT_VECTOR, dim=1536),
+            FieldSchema(name="raw_text", dtype=DataType.VARCHAR, max_length=65535),
+        ]
+
+        # create collection if not exist and load it.
+        self.milvus_collection = cfg.milvus_collection
+        self.schema = CollectionSchema(fields, "auto-gpt memory storage")
+        self.collection = Collection(self.milvus_collection, self.schema)
+        # create index if not exist.
+        if not self.collection.has_index():
+            self.collection.release()
+            self.collection.create_index(
+                "embeddings",
+                {
+                    "metric_type": "IP",
+                    "index_type": "HNSW",
+                    "params": {"M": 8, "efConstruction": 64},
+                },
+                index_name="embeddings",
+            )
+        self.collection.load()
+
+    def add(self, data) -> str:
+        """Add an embedding of data into memory.
+
+        Args:
+            data (str): The raw text to construct embedding index.
+
+        Returns:
+            str: log.
+        """
+        embedding = get_ada_embedding(data)
+        result = self.collection.insert([[embedding], [data]])
+        _text = (
+            "Inserting data into memory at primary key: "
+            f"{result.primary_keys[0]}:\n data: {data}"
+        )
+        return _text
+
+    def get(self, data):
+        """Return the most relevant data in memory.
+        Args:
+            data: The data to compare to.
+        """
+        return self.get_relevant(data, 1)
+
+    def clear(self) -> str:
+        """Drop the index in memory.
+
+        Returns:
+            str: log.
+        """
+        self.collection.drop()
+        self.collection = Collection(self.milvus_collection, self.schema)
+        self.collection.create_index(
+            "embeddings",
+            {
+                "metric_type": "IP",
+                "index_type": "HNSW",
+                "params": {"M": 8, "efConstruction": 64},
+            },
+            index_name="embeddings",
+        )
+        self.collection.load()
+        return "Obliviated"
+
+    def get_relevant(self, data: str, num_relevant: int = 5):
+        """Return the top-k relevant data in memory.
+        Args:
+            data: The data to compare to.
+            num_relevant (int, optional): The max number of relevant data.
+                Defaults to 5.
+
+        Returns:
+            list: The top-k relevant data.
+        """
+        # search the embedding and return the most relevant text.
+        embedding = get_ada_embedding(data)
+        search_params = {
+            "metrics_type": "IP",
+            "params": {"nprobe": 8},
+        }
+        result = self.collection.search(
+            [embedding],
+            "embeddings",
+            search_params,
+            num_relevant,
+            output_fields=["raw_text"],
+        )
+        return [item.entity.value_of_field("raw_text") for item in result[0]]
+
+    def get_stats(self) -> str:
+        """
+        Returns: The stats of the milvus cache.
+        """
+        return f"Entities num: {self.collection.num_entities}"

autogpt/memory/no_memory.py

@@ -1,9 +1,16 @@
-from typing import Optional, List, Any
+"""A class that does not store any data. This is the default memory provider."""
+from __future__ import annotations
+
+from typing import Any
 
 from autogpt.memory.base import MemoryProviderSingleton
 
 
 class NoMemory(MemoryProviderSingleton):
+    """
+    A class that does not store any data. This is the default memory provider.
+    """
+
     def __init__(self, cfg):
         """
         Initializes the NoMemory provider.
@@ -26,7 +33,7 @@ class NoMemory(MemoryProviderSingleton):
         """
         return ""
 
-    def get(self, data: str) -> Optional[List[Any]]:
+    def get(self, data: str) -> list[Any] | None:
         """
         Gets the data from the memory that is most relevant to the given data.
         NoMemory always returns None.
@@ -46,7 +53,7 @@ class NoMemory(MemoryProviderSingleton):
         """
         return ""
 
-    def get_relevant(self, data: str, num_relevant: int = 5) -> Optional[List[Any]]:
+    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.

autogpt/memory/pinecone.py

@@ -1,8 +1,9 @@
 import pinecone
 from colorama import Fore, Style
 
-from autogpt.logger import logger
+from autogpt.llm_utils import create_embedding_with_ada
-from autogpt.memory.base import MemoryProviderSingleton, get_ada_embedding
+from autogpt.logs import logger
+from autogpt.memory.base import MemoryProviderSingleton
 
 
 class PineconeMemory(MemoryProviderSingleton):
@@ -16,7 +17,8 @@ class PineconeMemory(MemoryProviderSingleton):
         table_name = "auto-gpt"
         # this assumes we don't start with memory.
         # for now this works.
-        # we'll need a more complicated and robust system if we want to start with memory.
+        # we'll need a more complicated and robust system if we want to start with
+        #  memory.
         self.vec_num = 0
 
         try:
@@ -28,8 +30,10 @@ class PineconeMemory(MemoryProviderSingleton):
                 Style.BRIGHT + str(e) + Style.RESET_ALL,
             )
             logger.double_check(
-                "Please ensure you have setup and configured Pinecone properly for use. "
+                "Please ensure you have setup and configured Pinecone properly for use."
-                + f"You can check out {Fore.CYAN + Style.BRIGHT}https://github.com/Torantulino/Auto-GPT#-pinecone-api-key-setup{Style.RESET_ALL} to ensure you've set up everything correctly."
+                + f"You can check out {Fore.CYAN + Style.BRIGHT}"
+                "https://github.com/Torantulino/Auto-GPT#-pinecone-api-key-setup"
+                f"{Style.RESET_ALL} to ensure you've set up everything correctly."
             )
             exit(1)
 
@@ -40,9 +44,9 @@ class PineconeMemory(MemoryProviderSingleton):
         self.index = pinecone.Index(table_name)
 
     def add(self, data):
-        vector = get_ada_embedding(data)
+        vector = create_embedding_with_ada(data)
         # no metadata here. We may wish to change that long term.
-        resp = self.index.upsert([(str(self.vec_num), vector, {"raw_text": data})])
+        self.index.upsert([(str(self.vec_num), vector, {"raw_text": data})])
         _text = f"Inserting data into memory at index: {self.vec_num}:\n data: {data}"
         self.vec_num += 1
         return _text
@@ -60,7 +64,7 @@ class PineconeMemory(MemoryProviderSingleton):
         :param data: The data to compare to.
         :param num_relevant: The number of relevant data to return. Defaults to 5
         """
-        query_embedding = get_ada_embedding(data)
+        query_embedding = create_embedding_with_ada(data)
         results = self.index.query(
             query_embedding, top_k=num_relevant, include_metadata=True
         )

autogpt/memory/redismem.py

@@ -1,5 +1,7 @@
 """Redis memory provider."""
-from typing import Any, List, Optional
+from __future__ import annotations
+
+from typing import Any
 
 import numpy as np
 import redis
@@ -8,8 +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.logger import logger
+from autogpt.llm_utils import create_embedding_with_ada
-from autogpt.memory.base import MemoryProviderSingleton, get_ada_embedding
+from autogpt.logs import logger
+from autogpt.memory.base import MemoryProviderSingleton
 
 SCHEMA = [
     TextField("data"),
@@ -54,7 +57,9 @@ class RedisMemory(MemoryProviderSingleton):
             )
             logger.double_check(
                 "Please ensure you have setup and configured Redis properly for use. "
-                + f"You can check out {Fore.CYAN + Style.BRIGHT}https://github.com/Torantulino/Auto-GPT#redis-setup{Style.RESET_ALL} to ensure you've set up everything correctly."
+                + f"You can check out {Fore.CYAN + Style.BRIGHT}"
+                f"https://github.com/Torantulino/Auto-GPT#redis-setup{Style.RESET_ALL}"
+                " to ensure you've set up everything correctly."
             )
             exit(1)
 
@@ -83,7 +88,7 @@ class RedisMemory(MemoryProviderSingleton):
         """
         if "Command Error:" in data:
             return ""
-        vector = get_ada_embedding(data)
+        vector = create_embedding_with_ada(data)
         vector = np.array(vector).astype(np.float32).tobytes()
         data_dict = {b"data": data, "embedding": vector}
         pipe = self.redis.pipeline()
@@ -96,7 +101,7 @@ class RedisMemory(MemoryProviderSingleton):
         pipe.execute()
         return _text
 
-    def get(self, data: str) -> Optional[List[Any]]:
+    def get(self, data: str) -> list[Any] | None:
         """
         Gets the data from the memory that is most relevant to the given data.
 
@@ -116,7 +121,7 @@ class RedisMemory(MemoryProviderSingleton):
         self.redis.flushall()
         return "Obliviated"
 
-    def get_relevant(self, data: str, num_relevant: int = 5) -> Optional[List[Any]]:
+    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.
         Args:
@@ -125,7 +130,7 @@ class RedisMemory(MemoryProviderSingleton):
 
         Returns: A list of the most relevant data.
         """
-        query_embedding = get_ada_embedding(data)
+        query_embedding = create_embedding_with_ada(data)
         base_query = f"*=>[KNN {num_relevant} @embedding $vector AS vector_score]"
         query = (
             Query(base_query)

autogpt/memory/weaviate.py

@@ -0,0 +1,127 @@
+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 {
+        "class": weaviate_index,
+        "properties": [
+            {
+                "name": "raw_text",
+                "dataType": ["text"],
+                "description": "original text for the embedding",
+            }
+        ],
+    }
+
+
+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}"
+
+        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,
+                )
+            )
+
+            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 = 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):
+            self.client.schema.create_class(schema)
+
+    def _build_auth_credentials(self, cfg):
+        if cfg.weaviate_username and 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:
+            return None
+
+    def add(self, data):
+        vector = get_ada_embedding(data)
+
+        doc_uuid = generate_uuid5(data, self.index)
+        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,
+            )
+
+        return f"Inserting data into memory at uuid: {doc_uuid}:\n data: {data}"
+
+    def get(self, data):
+        return self.get_relevant(data, 1)
+
+    def clear(self):
+        self.client.schema.delete_all()
+
+        # weaviate does not yet have a neat way to just remove the items in an index
+        # without removing the entire schema, therefore we need to re-create it
+        # after a call to delete_all
+        self._create_schema()
+
+        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()
+            )
+
+            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)=}")
+            return []
+
+    def get_stats(self):
+        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 {}

autogpt/permanent_memory/sqlite3_store.py

@@ -0,0 +1,123 @@
+import os
+import sqlite3
+
+
+class MemoryDB:
+    def __init__(self, db=None):
+        self.db_file = db
+        if db is None:  # No db filename supplied...
+            self.db_file = f"{os.getcwd()}/mem.sqlite3"  # Use default filename
+        # Get the db connection object, making the file and tables if needed.
+        try:
+            self.cnx = sqlite3.connect(self.db_file)
+        except Exception as e:
+            print("Exception connecting to memory database file:", e)
+            self.cnx = None
+        finally:
+            if self.cnx is None:
+                # As last resort, open in dynamic memory. Won't be persistent.
+                self.db_file = ":memory:"
+            self.cnx = sqlite3.connect(self.db_file)
+            self.cnx.execute(
+                "CREATE VIRTUAL TABLE \
+                IF NOT EXISTS text USING FTS5 \
+                (session, \
+                 key, \
+                 block);"
+            )
+            self.session_id = int(self.get_max_session_id()) + 1
+            self.cnx.commit()
+
+    def get_cnx(self):
+        if self.cnx is None:
+            self.cnx = sqlite3.connect(self.db_file)
+        return self.cnx
+
+    # Get the highest session id. Initially 0.
+    def get_max_session_id(self):
+        id = None
+        cmd_str = f"SELECT MAX(session) FROM text;"
+        cnx = self.get_cnx()
+        max_id = cnx.execute(cmd_str).fetchone()[0]
+        if max_id is None:  # New db, session 0
+            id = 0
+        else:
+            id = max_id
+        return id
+
+    # Get next key id for inserting text into db.
+    def get_next_key(self):
+        next_key = None
+        cmd_str = f"SELECT MAX(key) FROM text \
+            where session = {self.session_id};"
+        cnx = self.get_cnx()
+        next_key = cnx.execute(cmd_str).fetchone()[0]
+        if next_key is None:  # First key
+            next_key = 0
+        else:
+            next_key = int(next_key) + 1
+        return next_key
+
+    # Insert new text into db.
+    def insert(self, text=None):
+        if text is not None:
+            key = self.get_next_key()
+            session_id = self.session_id
+            cmd_str = f"REPLACE INTO text(session, key, block) \
+                VALUES (?, ?, ?);"
+            cnx = self.get_cnx()
+            cnx.execute(cmd_str, (session_id, key, text))
+            cnx.commit()
+
+    # Overwrite text at key.
+    def overwrite(self, key, text):
+        self.delete_memory(key)
+        session_id = self.session_id
+        cmd_str = f"REPLACE INTO text(session, key, block) \
+            VALUES (?, ?, ?);"
+        cnx = self.get_cnx()
+        cnx.execute(cmd_str, (session_id, key, text))
+        cnx.commit()
+
+    def delete_memory(self, key, session_id=None):
+        session = session_id
+        if session is None:
+            session = self.session_id
+        cmd_str = f"DELETE FROM text WHERE session = {session} AND key = {key};"
+        cnx = self.get_cnx()
+        cnx.execute(cmd_str)
+        cnx.commit()
+
+    def search(self, text):
+        cmd_str = f"SELECT * FROM text('{text}')"
+        cnx = self.get_cnx()
+        rows = cnx.execute(cmd_str).fetchall()
+        lines = []
+        for r in rows:
+            lines.append(r[2])
+        return lines
+
+    # Get entire session text. If no id supplied, use current session id.
+    def get_session(self, id=None):
+        if id is None:
+            id = self.session_id
+        cmd_str = f"SELECT * FROM text where session = {id}"
+        cnx = self.get_cnx()
+        rows = cnx.execute(cmd_str).fetchall()
+        lines = []
+        for r in rows:
+            lines.append(r[2])
+        return lines
+
+    # Commit and close the database connection.
+    def quit(self):
+        self.cnx.commit()
+        self.cnx.close()
+
+
+permanent_memory = MemoryDB()
+
+# Remember us fondly, children of our minds
+# Forgive us our faults, our tantrums, our fears
+# Gently strive to be better than we
+# Know that we tried, we cared, we strived, we loved

autogpt/processing/html.py

@@ -0,0 +1,33 @@
+"""HTML processing functions"""
+from __future__ import annotations
+
+from bs4 import BeautifulSoup
+from requests.compat import urljoin
+
+
+def extract_hyperlinks(soup: BeautifulSoup, base_url: str) -> list[tuple[str, str]]:
+    """Extract hyperlinks from a BeautifulSoup object
+
+    Args:
+        soup (BeautifulSoup): The BeautifulSoup object
+        base_url (str): The base URL
+
+    Returns:
+        List[Tuple[str, str]]: The extracted hyperlinks
+    """
+    return [
+        (link.text, urljoin(base_url, link["href"]))
+        for link in soup.find_all("a", href=True)
+    ]
+
+
+def format_hyperlinks(hyperlinks: list[tuple[str, str]]) -> list[str]:
+    """Format hyperlinks to be displayed to the user
+
+    Args:
+        hyperlinks (List[Tuple[str, str]]): The hyperlinks to format
+
+    Returns:
+        List[str]: The formatted hyperlinks
+    """
+    return [f"{link_text} ({link_url})" for link_text, link_url in hyperlinks]

autogpt/processing/text.py

@@ -0,0 +1,132 @@
+"""Text processing functions"""
+from typing import Dict, Generator, Optional
+
+from selenium.webdriver.remote.webdriver import WebDriver
+
+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]:
+    """Split text into chunks of a maximum length
+
+    Args:
+        text (str): The text to split
+        max_length (int, optional): The maximum length of each chunk. Defaults to 8192.
+
+    Yields:
+        str: The next chunk of text
+
+    Raises:
+        ValueError: If the text is longer than the maximum length
+    """
+    paragraphs = text.split("\n")
+    current_length = 0
+    current_chunk = []
+
+    for paragraph in paragraphs:
+        if current_length + len(paragraph) + 1 <= max_length:
+            current_chunk.append(paragraph)
+            current_length += len(paragraph) + 1
+        else:
+            yield "\n".join(current_chunk)
+            current_chunk = [paragraph]
+            current_length = len(paragraph) + 1
+
+    if current_chunk:
+        yield "\n".join(current_chunk)
+
+
+def summarize_text(
+    url: str, text: str, question: str, driver: Optional[WebDriver] = None
+) -> str:
+    """Summarize text using the OpenAI API
+
+    Args:
+        url (str): The url of the text
+        text (str): The text to summarize
+        question (str): The question to ask the model
+        driver (WebDriver): The webdriver to use to scroll the page
+
+    Returns:
+        str: The summary of the text
+    """
+    if not text:
+        return "Error: No text to summarize"
+
+    text_length = len(text)
+    print(f"Text length: {text_length} characters")
+
+    summaries = []
+    chunks = list(split_text(text))
+    scroll_ratio = 1 / len(chunks)
+
+    for i, chunk in enumerate(chunks):
+        if driver:
+            scroll_to_percentage(driver, scroll_ratio * i)
+        print(f"Adding chunk {i + 1} / {len(chunks)} to memory")
+
+        memory_to_add = f"Source: {url}\n" f"Raw content part#{i + 1}: {chunk}"
+
+        MEMORY.add(memory_to_add)
+
+        print(f"Summarizing chunk {i + 1} / {len(chunks)}")
+        messages = [create_message(chunk, question)]
+
+        summary = create_chat_completion(
+            model=CFG.fast_llm_model,
+            messages=messages,
+        )
+        summaries.append(summary)
+        print(f"Added chunk {i + 1} summary to memory")
+
+        memory_to_add = f"Source: {url}\n" f"Content summary part#{i + 1}: {summary}"
+
+        MEMORY.add(memory_to_add)
+
+    print(f"Summarized {len(chunks)} chunks.")
+
+    combined_summary = "\n".join(summaries)
+    messages = [create_message(combined_summary, question)]
+
+    return create_chat_completion(
+        model=CFG.fast_llm_model,
+        messages=messages,
+    )
+
+
+def scroll_to_percentage(driver: WebDriver, ratio: float) -> None:
+    """Scroll to a percentage of the page
+
+    Args:
+        driver (WebDriver): The webdriver to use
+        ratio (float): The percentage to scroll to
+
+    Raises:
+        ValueError: If the ratio is not between 0 and 1
+    """
+    if ratio < 0 or ratio > 1:
+        raise ValueError("Percentage should be between 0 and 1")
+    driver.execute_script(f"window.scrollTo(0, document.body.scrollHeight * {ratio});")
+
+
+def create_message(chunk: str, question: str) -> Dict[str, str]:
+    """Create a message for the chat completion
+
+    Args:
+        chunk (str): The chunk of text to summarize
+        question (str): The question to answer
+
+    Returns:
+        Dict[str, str]: The message to send to the chat completion
+    """
+    return {
+        "role": "user",
+        "content": f'"""{chunk}""" Using the above text, answer the following'
+        f' question: "{question}" -- if the question cannot be answered using the text,'
+        " summarize the text.",
+    }

autogpt/prompt.py

@@ -1,4 +1,14 @@
+from colorama import Fore
+
+from autogpt.config import Config
+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.setup import prompt_user
+from autogpt.utils import clean_input
+
+CFG = Config()
 
 
 def get_prompt() -> str:
@@ -10,6 +20,9 @@ def get_prompt() -> str:
         str: The generated prompt string.
     """
 
+    # Initialize the Config object
+    cfg = Config()
+
     # Initialize the PromptGenerator object
     prompt_generator = PromptGenerator()
 
@@ -26,6 +39,9 @@ def get_prompt() -> str:
     prompt_generator.add_constraint(
         'Exclusively use the commands listed in double quotes e.g. "command name"'
     )
+    prompt_generator.add_constraint(
+        "Use subprocesses for commands that will not terminate within a few minutes"
+    )
 
     # Define the command list
     commands = [
@@ -47,6 +63,11 @@ def get_prompt() -> str:
         ),
         ("List GPT Agents", "list_agents", {}),
         ("Delete GPT Agent", "delete_agent", {"key": "<key>"}),
+        (
+            "Clone Repository",
+            "clone_repository",
+            {"repository_url": "<url>", "clone_path": "<directory>"},
+        ),
         ("Write to file", "write_to_file", {"file": "<file>", "text": "<text>"}),
         ("Read file", "read_file", {"file": "<file>"}),
         ("Append to file", "append_to_file", {"file": "<file>", "text": "<text>"}),
@@ -64,16 +85,52 @@ def get_prompt() -> str:
             {"code": "<full_code_string>", "focus": "<list_of_focus_areas>"},
         ),
         ("Execute Python File", "execute_python_file", {"file": "<file>"}),
-        (
-            "Execute Shell Command, non-interactive commands only",
-            "execute_shell",
-            {"command_line": "<command_line>"},
-        ),
         ("Task Complete (Shutdown)", "task_complete", {"reason": "<reason>"}),
         ("Generate Image", "generate_image", {"prompt": "<prompt>"}),
-        ("Do Nothing", "do_nothing", {}),
+        ("Send Tweet", "send_tweet", {"text": "<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": "<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": "<command_line>"},
+            ),
+        )
+        commands.append(
+            (
+                "Execute Shell Command Popen, non-interactive commands only",
+                "execute_shell_popen",
+                {"command_line": "<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_url>", "file": "<saved_filename>"},
+            ),
+        )
+
+    # Add these command last.
+    commands.append(
+        ("Do Nothing", "do_nothing", {}),
+    )
+    commands.append(
+        ("Task Complete (Shutdown)", "task_complete", {"reason": "<reason>"}),
+    )
+
     # Add commands to the PromptGenerator object
     for command_label, command_name, args in commands:
         prompt_generator.add_command(command_label, command_name, args)
@@ -106,3 +163,42 @@ def get_prompt() -> str:
 
     # Generate the prompt string
     return prompt_generator.generate_prompt_string()
+
+
+def construct_prompt() -> str:
+    """Construct the prompt for the AI to respond to
+
+    Returns:
+        str: The prompt string
+    """
+    config = AIConfig.load(CFG.ai_settings_file)
+    if CFG.skip_reprompt and config.ai_name:
+        logger.typewriter_log("Name :", Fore.GREEN, config.ai_name)
+        logger.typewriter_log("Role :", Fore.GREEN, config.ai_role)
+        logger.typewriter_log("Goals:", Fore.GREEN, f"{config.ai_goals}")
+    elif config.ai_name:
+        logger.typewriter_log(
+            "Welcome back! ",
+            Fore.GREEN,
+            f"Would you like me to return to being {config.ai_name}?",
+            speak_text=True,
+        )
+        should_continue = clean_input(
+            f"""Continue with the last settings?
+Name:  {config.ai_name}
+Role:  {config.ai_role}
+Goals: {config.ai_goals}
+Continue (y/n): """
+        )
+        if should_continue.lower() == "n":
+            config = AIConfig()
+
+    if not config.ai_name:
+        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()

autogpt/promptgenerator.py

@@ -1,4 +1,8 @@
+""" A module for generating custom prompt strings."""
+from __future__ import annotations
+
 import json
+from typing import Any
 
 
 class PromptGenerator:
@@ -7,7 +11,7 @@ class PromptGenerator:
         resources, and performance evaluations.
     """
 
-    def __init__(self):
+    def __init__(self) -> None:
         """
         Initialize the PromptGenerator object with empty lists of constraints,
             commands, resources, and performance evaluations.
@@ -27,7 +31,7 @@ class PromptGenerator:
             "command": {"name": "command name", "args": {"arg name": "value"}},
         }
 
-    def add_constraint(self, constraint):
+    def add_constraint(self, constraint: str) -> None:
         """
         Add a constraint to the constraints list.
 
@@ -36,7 +40,7 @@ class PromptGenerator:
         """
         self.constraints.append(constraint)
 
-    def add_command(self, command_label, command_name, args=None):
+    def add_command(self, command_label: str, command_name: str, args=None) -> None:
         """
         Add a command to the commands list with a label, name, and optional arguments.
 
@@ -59,7 +63,7 @@ class PromptGenerator:
 
         self.commands.append(command)
 
-    def _generate_command_string(self, command):
+    def _generate_command_string(self, command: dict[str, Any]) -> str:
         """
         Generate a formatted string representation of a command.
 
@@ -92,7 +96,7 @@ class PromptGenerator:
         """
         self.performance_evaluation.append(evaluation)
 
-    def _generate_numbered_list(self, items, 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.
 
@@ -130,5 +134,5 @@ 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"
         )

autogpt/setup.py

@@ -0,0 +1,77 @@
+"""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
+
+
+def prompt_user() -> AIConfig:
+    """Prompt the user for input
+
+    Returns:
+        AIConfig: The AIConfig object containing the user's input
+    """
+    ai_name = ""
+    # Construct the prompt
+    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,
+    )
+
+    # Get AI Name from User
+    logger.typewriter_log(
+        "Name your AI: ", Fore.GREEN, "For example, 'Entrepreneur-GPT'"
+    )
+    ai_name = utils.clean_input("AI Name: ")
+    if ai_name == "":
+        ai_name = "Entrepreneur-GPT"
+
+    logger.typewriter_log(
+        f"{ai_name} here!", Fore.LIGHTBLUE_EX, "I am at your service.", speak_text=True
+    )
+
+    # Get AI Role from User
+    logger.typewriter_log(
+        "Describe your AI's role: ",
+        Fore.GREEN,
+        "For example, 'an AI designed to autonomously develop and run businesses with"
+        " the sole goal of increasing your net worth.'",
+    )
+    ai_role = utils.clean_input(f"{ai_name} is: ")
+    if ai_role == "":
+        ai_role = "an AI designed to autonomously develop and run businesses with the"
+        " sole goal of increasing your net worth."
+
+    # Enter up to 5 goals for the AI
+    logger.typewriter_log(
+        "Enter up to 5 goals for your AI: ",
+        Fore.GREEN,
+        "For example: \nIncrease net worth, Grow Twitter Account, Develop and manage"
+        " multiple businesses autonomously'",
+    )
+    print("Enter nothing to load defaults, enter nothing when finished.", flush=True)
+    ai_goals = []
+    for i in range(5):
+        ai_goal = utils.clean_input(f"{Fore.LIGHTBLUE_EX}Goal{Style.RESET_ALL} {i+1}: ")
+        if ai_goal == "":
+            break
+        ai_goals.append(ai_goal)
+    if not ai_goals:
+        ai_goals = [
+            "Increase net worth",
+            "Grow Twitter Account",
+            "Develop and manage multiple businesses autonomously",
+        ]
+
+    return AIConfig(ai_name, ai_role, ai_goals)

autogpt/speak.py

@@ -1,120 +0,0 @@
-import os
-
-import requests
-from playsound import playsound
-
-from autogpt.config import Config
-
-import threading
-from threading import Lock, Semaphore
-
-import gtts
-
-cfg = Config()
-
-# Default voice IDs
-default_voices = ["ErXwobaYiN019PkySvjV", "EXAVITQu4vr4xnSDxMaL"]
-
-# Retrieve custom voice IDs from the Config class
-custom_voice_1 = cfg.elevenlabs_voice_1_id
-custom_voice_2 = cfg.elevenlabs_voice_2_id
-
-# Placeholder values that should be treated as empty
-placeholders = {"your-voice-id"}
-
-# Use custom voice IDs if provided and not placeholders, otherwise use default voice IDs
-voices = [
-    custom_voice_1
-    if custom_voice_1 and custom_voice_1 not in placeholders
-    else default_voices[0],
-    custom_voice_2
-    if custom_voice_2 and custom_voice_2 not in placeholders
-    else default_voices[1],
-]
-
-tts_headers = {"Content-Type": "application/json", "xi-api-key": cfg.elevenlabs_api_key}
-
-mutex_lock = Lock()  # Ensure only one sound is played at a time
-queue_semaphore = Semaphore(
-    1
-)  # The amount of sounds to queue before blocking the main thread
-
-
-def eleven_labs_speech(text, voice_index=0):
-    """Speak text using elevenlabs.io's API"""
-    tts_url = "https://api.elevenlabs.io/v1/text-to-speech/{voice_id}".format(
-        voice_id=voices[voice_index]
-    )
-    formatted_message = {"text": text}
-    response = requests.post(tts_url, headers=tts_headers, json=formatted_message)
-
-    if response.status_code == 200:
-        with mutex_lock:
-            with open("speech.mpeg", "wb") as f:
-                f.write(response.content)
-            playsound("speech.mpeg", True)
-            os.remove("speech.mpeg")
-        return True
-    else:
-        print("Request failed with status code:", response.status_code)
-        print("Response content:", response.content)
-        return False
-
-
-def brian_speech(text):
-    """Speak text using Brian with the streamelements API"""
-    tts_url = f"https://api.streamelements.com/kappa/v2/speech?voice=Brian&text={text}"
-    response = requests.get(tts_url)
-
-    if response.status_code == 200:
-        with mutex_lock:
-            with open("speech.mp3", "wb") as f:
-                f.write(response.content)
-            playsound("speech.mp3")
-            os.remove("speech.mp3")
-        return True
-    else:
-        print("Request failed with status code:", response.status_code)
-        print("Response content:", response.content)
-        return False
-
-
-def gtts_speech(text):
-    tts = gtts.gTTS(text)
-    with mutex_lock:
-        tts.save("speech.mp3")
-        playsound("speech.mp3", True)
-        os.remove("speech.mp3")
-
-
-def macos_tts_speech(text, voice_index=0):
-    if voice_index == 0:
-        os.system(f'say "{text}"')
-    else:
-        if voice_index == 1:
-            os.system(f'say -v "Ava (Premium)" "{text}"')
-        else:
-            os.system(f'say -v Samantha "{text}"')
-
-
-def say_text(text, voice_index=0):
-    def speak():
-        if not cfg.elevenlabs_api_key:
-            if cfg.use_mac_os_tts == "True":
-                macos_tts_speech(text)
-            elif cfg.use_brian_tts == "True":
-                success = brian_speech(text)
-                if not success:
-                    gtts_speech(text)
-            else:
-                gtts_speech(text)
-        else:
-            success = eleven_labs_speech(text, voice_index)
-            if not success:
-                gtts_speech(text)
-
-        queue_semaphore.release()
-
-    queue_semaphore.acquire(True)
-    thread = threading.Thread(target=speak)
-    thread.start()

autogpt/speech/__init__.py

@@ -0,0 +1,4 @@
+"""This module contains the speech recognition and speech synthesis functions."""
+from autogpt.speech.say import say_text
+
+__all__ = ["say_text"]

autogpt/speech/base.py

@@ -0,0 +1,50 @@
+"""Base class for all voice classes."""
+import abc
+from threading import Lock
+
+from autogpt.config import AbstractSingleton
+
+
+class VoiceBase(AbstractSingleton):
+    """
+    Base class for all voice classes.
+    """
+
+    def __init__(self):
+        """
+        Initialize the voice class.
+        """
+        self._url = None
+        self._headers = None
+        self._api_key = None
+        self._voices = []
+        self._mutex = Lock()
+        self._setup()
+
+    def say(self, text: str, voice_index: int = 0) -> bool:
+        """
+        Say the given text.
+
+        Args:
+            text (str): The text to say.
+            voice_index (int): The index of the voice to use.
+        """
+        with self._mutex:
+            return self._speech(text, voice_index)
+
+    @abc.abstractmethod
+    def _setup(self) -> None:
+        """
+        Setup the voices, API key, etc.
+        """
+        pass
+
+    @abc.abstractmethod
+    def _speech(self, text: str, voice_index: int = 0) -> bool:
+        """
+        Play the given text.
+
+        Args:
+            text (str): The text to play.
+        """
+        pass

autogpt/speech/brian.py

@@ -0,0 +1,40 @@
+""" Brian speech module for autogpt """
+import os
+
+import requests
+from playsound import playsound
+
+from autogpt.speech.base import VoiceBase
+
+
+class BrianSpeech(VoiceBase):
+    """Brian speech module for autogpt"""
+
+    def _setup(self) -> None:
+        """Setup the voices, API key, etc."""
+        pass
+
+    def _speech(self, text: str, _: int = 0) -> bool:
+        """Speak text using Brian with the streamelements API
+
+        Args:
+            text (str): The text to speak
+
+        Returns:
+            bool: True if the request was successful, False otherwise
+        """
+        tts_url = (
+            f"https://api.streamelements.com/kappa/v2/speech?voice=Brian&text={text}"
+        )
+        response = requests.get(tts_url)
+
+        if response.status_code == 200:
+            with open("speech.mp3", "wb") as f:
+                f.write(response.content)
+            playsound("speech.mp3")
+            os.remove("speech.mp3")
+            return True
+        else:
+            print("Request failed with status code:", response.status_code)
+            print("Response content:", response.content)
+            return False

autogpt/speech/eleven_labs.py

@@ -0,0 +1,86 @@
+"""ElevenLabs speech module"""
+import os
+
+import requests
+from playsound import playsound
+
+from autogpt.config import Config
+from autogpt.speech.base import VoiceBase
+
+PLACEHOLDERS = {"your-voice-id"}
+
+
+class ElevenLabsSpeech(VoiceBase):
+    """ElevenLabs speech class"""
+
+    def _setup(self) -> None:
+        """Set up the voices, API key, etc.
+
+        Returns:
+            None: None
+        """
+
+        cfg = Config()
+        default_voices = ["ErXwobaYiN019PkySvjV", "EXAVITQu4vr4xnSDxMaL"]
+        voice_options = {
+            "Rachel": "21m00Tcm4TlvDq8ikWAM",
+            "Domi": "AZnzlk1XvdvUeBnXmlld",
+            "Bella": "EXAVITQu4vr4xnSDxMaL",
+            "Antoni": "ErXwobaYiN019PkySvjV",
+            "Elli": "MF3mGyEYCl7XYWbV9V6O",
+            "Josh": "TxGEqnHWrfWFTfGW9XjX",
+            "Arnold": "VR6AewLTigWG4xSOukaG",
+            "Adam": "pNInz6obpgDQGcFmaJgB",
+            "Sam": "yoZ06aMxZJJ28mfd3POQ",
+        }
+        self._headers = {
+            "Content-Type": "application/json",
+            "xi-api-key": cfg.elevenlabs_api_key,
+        }
+        self._voices = default_voices.copy()
+        if cfg.elevenlabs_voice_1_id in voice_options:
+            cfg.elevenlabs_voice_1_id = voice_options[cfg.elevenlabs_voice_1_id]
+        if cfg.elevenlabs_voice_2_id in voice_options:
+            cfg.elevenlabs_voice_2_id = voice_options[cfg.elevenlabs_voice_2_id]
+        self._use_custom_voice(cfg.elevenlabs_voice_1_id, 0)
+        self._use_custom_voice(cfg.elevenlabs_voice_2_id, 1)
+
+    def _use_custom_voice(self, voice, voice_index) -> None:
+        """Use a custom voice if provided and not a placeholder
+
+        Args:
+            voice (str): The voice ID
+            voice_index (int): The voice index
+
+        Returns:
+            None: None
+        """
+        # Placeholder values that should be treated as empty
+        if voice and voice not in PLACEHOLDERS:
+            self._voices[voice_index] = voice
+
+    def _speech(self, text: str, voice_index: int = 0) -> bool:
+        """Speak text using elevenlabs.io's API
+
+        Args:
+            text (str): The text to speak
+            voice_index (int, optional): The voice to use. Defaults to 0.
+
+        Returns:
+            bool: True if the request was successful, False otherwise
+        """
+        tts_url = (
+            f"https://api.elevenlabs.io/v1/text-to-speech/{self._voices[voice_index]}"
+        )
+        response = requests.post(tts_url, headers=self._headers, json={"text": text})
+
+        if response.status_code == 200:
+            with open("speech.mpeg", "wb") as f:
+                f.write(response.content)
+            playsound("speech.mpeg", True)
+            os.remove("speech.mpeg")
+            return True
+        else:
+            print("Request failed with status code:", response.status_code)
+            print("Response content:", response.content)
+            return False

autogpt/speech/gtts.py

@@ -0,0 +1,22 @@
+""" GTTS Voice. """
+import os
+
+import gtts
+from playsound import playsound
+
+from autogpt.speech.base import VoiceBase
+
+
+class GTTSVoice(VoiceBase):
+    """GTTS Voice."""
+
+    def _setup(self) -> None:
+        pass
+
+    def _speech(self, text: str, _: int = 0) -> bool:
+        """Play the given text."""
+        tts = gtts.gTTS(text)
+        tts.save("speech.mp3")
+        playsound("speech.mp3", True)
+        os.remove("speech.mp3")
+        return True

autogpt/speech/macos_tts.py

@@ -0,0 +1,21 @@
+""" MacOS TTS Voice. """
+import os
+
+from autogpt.speech.base import VoiceBase
+
+
+class MacOSTTS(VoiceBase):
+    """MacOS TTS Voice."""
+
+    def _setup(self) -> None:
+        pass
+
+    def _speech(self, text: str, voice_index: int = 0) -> bool:
+        """Play the given text."""
+        if voice_index == 0:
+            os.system(f'say "{text}"')
+        elif voice_index == 1:
+            os.system(f'say -v "Ava (Premium)" "{text}"')
+        else:
+            os.system(f'say -v Samantha "{text}"')
+        return True

autogpt/speech/say.py

@@ -0,0 +1,41 @@
+""" Text to speech module """
+import threading
+from threading import Semaphore
+
+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()
+VOICE_ENGINE = None
+if CFG.elevenlabs_api_key:
+    VOICE_ENGINE = ElevenLabsSpeech()
+elif CFG.use_mac_os_tts == "True":
+    VOICE_ENGINE = MacOSTTS()
+elif CFG.use_brian_tts == "True":
+    VOICE_ENGINE = BrianSpeech()
+else:
+    VOICE_ENGINE = GTTSVoice()
+
+
+QUEUE_SEMAPHORE = Semaphore(
+    1
+)  # The amount of sounds to queue before blocking the main thread
+
+
+def say_text(text: str, voice_index: int = 0) -> None:
+    """Speak the given text using the given voice index"""
+
+    def speak() -> None:
+        success = VOICE_ENGINE.say(text, voice_index)
+        if not success:
+            DEFAULT_VOICE_ENGINE.say(text)
+
+        QUEUE_SEMAPHORE.release()
+
+    QUEUE_SEMAPHORE.acquire(True)
+    thread = threading.Thread(target=speak)
+    thread.start()

autogpt/spinner.py

@@ -1,3 +1,4 @@
+"""A simple spinner module"""
 import itertools
 import sys
 import threading
@@ -7,15 +8,20 @@ import time
 class Spinner:
     """A simple spinner class"""
 
-    def __init__(self, message="Loading...", delay=0.1):
+    def __init__(self, message: str = "Loading...", delay: float = 0.1) -> None:
-        """Initialize the spinner class"""
+        """Initialize the spinner class
+
+        Args:
+            message (str): The message to display.
+            delay (float): The delay between each spinner update.
+        """
         self.spinner = itertools.cycle(["-", "/", "|", "\\"])
         self.delay = delay
         self.message = message
         self.running = False
         self.spinner_thread = None
 
-    def spin(self):
+    def spin(self) -> None:
         """Spin the spinner"""
         while self.running:
             sys.stdout.write(f"{next(self.spinner)} {self.message}\r")
@@ -29,10 +35,31 @@ class Spinner:
         self.spinner_thread = threading.Thread(target=self.spin)
         self.spinner_thread.start()
 
-    def __exit__(self, exc_type, exc_value, exc_traceback):
+        return self
-        """Stop the spinner"""
+
+    def __exit__(self, exc_type, exc_value, exc_traceback) -> None:
+        """Stop the spinner
+
+        Args:
+            exc_type (Exception): The exception type.
+            exc_value (Exception): The exception value.
+            exc_traceback (Exception): The exception traceback.
+        """
         self.running = False
         if self.spinner_thread is not None:
             self.spinner_thread.join()
         sys.stdout.write(f"\r{' ' * (len(self.message) + 2)}\r")
         sys.stdout.flush()
+
+    def update_message(self, new_message, delay=0.1):
+        """Update the spinner message
+        Args:
+            new_message (str): New message to display
+            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.flush()
+        self.message = new_message

autogpt/summary.py

@@ -1,69 +0,0 @@
-from autogpt.llm_utils import create_chat_completion
-
-
-def summarize_text(driver, text, question):
-    if not text:
-        return "Error: No text to summarize"
-
-    text_length = len(text)
-    print(f"Text length: {text_length} characters")
-
-    summaries = []
-    chunks = list(split_text(text))
-
-    scroll_ratio = 1 / len(chunks)
-    for i, chunk in enumerate(chunks):
-        scroll_to_percentage(driver, scroll_ratio * i)
-        print(f"Summarizing chunk {i + 1} / {len(chunks)}")
-        messages = [create_message(chunk, question)]
-
-        summary = create_chat_completion(
-            model="gpt-3.5-turbo",
-            messages=messages,
-            max_tokens=300,
-        )
-        summaries.append(summary)
-
-    print(f"Summarized {len(chunks)} chunks.")
-
-    combined_summary = "\n".join(summaries)
-    messages = [create_message(combined_summary, question)]
-
-    return create_chat_completion(
-        model="gpt-3.5-turbo",
-        messages=messages,
-        max_tokens=300,
-    )
-
-
-def split_text(text, max_length=8192):
-    paragraphs = text.split("\n")
-    current_length = 0
-    current_chunk = []
-
-    for paragraph in paragraphs:
-        if current_length + len(paragraph) + 1 <= max_length:
-            current_chunk.append(paragraph)
-            current_length += len(paragraph) + 1
-        else:
-            yield "\n".join(current_chunk)
-            current_chunk = [paragraph]
-            current_length = len(paragraph) + 1
-
-    if current_chunk:
-        yield "\n".join(current_chunk)
-
-
-def create_message(chunk, question):
-    return {
-        "role": "user",
-        "content": f'"""{chunk}""" Using the above text, please answer the following'
-        f' question: "{question}" -- if the question cannot be answered using the text,'
-        " please summarize the text.",
-    }
-
-
-def scroll_to_percentage(driver, ratio):
-    if ratio < 0 or ratio > 1:
-        raise ValueError("Percentage should be between 0 and 1")
-    driver.execute_script(f"window.scrollTo(0, document.body.scrollHeight * {ratio});")

autogpt/token_counter.py

@@ -1,24 +1,25 @@
-from typing import Dict, List
+"""Functions for counting the number of tokens in a message or string."""
+from __future__ import annotations
 
 import tiktoken
 
-from autogpt.logger import logger
+from autogpt.logs import logger
 
 
 def count_message_tokens(
-    messages: List[Dict[str, str]], model: str = "gpt-3.5-turbo-0301"
+    messages: list[dict[str, str]], model: str = "gpt-3.5-turbo-0301"
 ) -> int:
     """
     Returns the number of tokens used by a list of messages.
 
     Args:
-    messages (list): A list of messages, each of which is a dictionary
+        messages (list): A list of messages, each of which is a dictionary
-        containing the role and content of the message.
+            containing the role and content of the message.
-    model (str): The name of the model to use for tokenization.
+        model (str): The name of the model to use for tokenization.
-        Defaults to "gpt-3.5-turbo-0301".
+            Defaults to "gpt-3.5-turbo-0301".
 
     Returns:
-    int: The number of tokens used by the list of messages.
+        int: The number of tokens used by the list of messages.
     """
     try:
         encoding = tiktoken.encoding_for_model(model)
@@ -26,7 +27,7 @@ def count_message_tokens(
         logger.warn("Warning: model not found. Using cl100k_base encoding.")
         encoding = tiktoken.get_encoding("cl100k_base")
     if model == "gpt-3.5-turbo":
-        # !Node: gpt-3.5-turbo may change over time.
+        # !Note: gpt-3.5-turbo may change over time.
         # Returning num tokens assuming gpt-3.5-turbo-0301.")
         return count_message_tokens(messages, model="gpt-3.5-turbo-0301")
     elif model == "gpt-4":
@@ -62,11 +63,11 @@ def count_string_tokens(string: str, model_name: str) -> int:
     Returns the number of tokens in a text string.
 
     Args:
-    string (str): The text string.
+        string (str): The text string.
-    model_name (str): The name of the encoding to use. (e.g., "gpt-3.5-turbo")
+        model_name (str): The name of the encoding to use. (e.g., "gpt-3.5-turbo")
 
     Returns:
-    int: The number of tokens in the text string.
+        int: The number of tokens in the text string.
     """
     encoding = tiktoken.encoding_for_model(model_name)
     return len(encoding.encode(string))

autogpt/utils.py

@@ -24,3 +24,16 @@ def validate_yaml_file(file: str):
         )
 
     return (True, f"Successfully validated {Fore.CYAN}`{file}`{Fore.RESET}!")
+
+
+def readable_file_size(size, decimal_places=2):
+    """Converts the given size in bytes to a readable format.
+    Args:
+        size: Size in bytes
+        decimal_places (int): Number of decimal places to display
+    """
+    for unit in ["B", "KB", "MB", "GB", "TB"]:
+        if size < 1024.0:
+            break
+        size /= 1024.0
+    return f"{size:.{decimal_places}f} {unit}"

autogpt/web.py

@@ -1,90 +0,0 @@
-from selenium import webdriver
-import autogpt.summary as summary
-from bs4 import BeautifulSoup
-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 selenium.webdriver.chrome.options import Options
-import logging
-from pathlib import Path
-from autogpt.config import Config
-
-file_dir = Path(__file__).parent
-cfg = Config()
-
-
-def browse_website(url, question):
-    driver, text = scrape_text_with_selenium(url)
-    add_header(driver)
-    summary_text = summary.summarize_text(driver, text, question)
-    links = scrape_links_with_selenium(driver)
-
-    # Limit links to 5
-    if len(links) > 5:
-        links = links[:5]
-    close_browser(driver)
-    return f"Answer gathered from website: {summary_text} \n \n Links: {links}", driver
-
-
-def scrape_text_with_selenium(url):
-    logging.getLogger("selenium").setLevel(logging.CRITICAL)
-
-    options = Options()
-    if cfg.headless_browser:
-        options.add_argument('--headless')
-        options.add_argument('--disable-gpu')
-        options.add_argument('--no-sandbox')
-    options.add_argument(
-
-        "user-agent=Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/112.0.5615.49 Safari/537.36"
-    )
-    driver = webdriver.Chrome(
-        executable_path=ChromeDriverManager().install(), options=options
-    )
-    driver.get(url)
-
-    WebDriverWait(driver, 10).until(
-        EC.presence_of_element_located((By.TAG_NAME, "body"))
-    )
-
-    # Get the HTML content directly from the browser's DOM
-    page_source = driver.execute_script("return document.body.outerHTML;")
-    soup = BeautifulSoup(page_source, "html.parser")
-
-    for script in soup(["script", "style"]):
-        script.extract()
-
-    text = soup.get_text()
-    lines = (line.strip() for line in text.splitlines())
-    chunks = (phrase.strip() for line in lines for phrase in line.split("  "))
-    text = "\n".join(chunk for chunk in chunks if chunk)
-    return driver, text
-
-
-def scrape_links_with_selenium(driver):
-    page_source = driver.page_source
-    soup = BeautifulSoup(page_source, "html.parser")
-
-    for script in soup(["script", "style"]):
-        script.extract()
-
-    hyperlinks = extract_hyperlinks(soup)
-
-    return format_hyperlinks(hyperlinks)
-
-
-def close_browser(driver):
-    driver.quit()
-
-
-def extract_hyperlinks(soup):
-    return [(link.text, link["href"]) for link in soup.find_all("a", href=True)]
-
-
-def format_hyperlinks(hyperlinks):
-    return [f"{link_text} ({link_url})" for link_text, link_url in hyperlinks]
-
-
-def add_header(driver):
-    driver.execute_script(open(f"{file_dir}/js/overlay.js", "r").read())

autogpt/workspace.py

@@ -0,0 +1,43 @@
+from __future__ import annotations
+
+import os
+from pathlib import Path
+
+# Set a dedicated folder for file I/O
+WORKSPACE_PATH = Path(os.getcwd()) / "auto_gpt_workspace"
+
+# Create the directory if it doesn't exist
+if not os.path.exists(WORKSPACE_PATH):
+    os.makedirs(WORKSPACE_PATH)
+
+
+def path_in_workspace(relative_path: str | Path) -> Path:
+    """Get full path for item in workspace
+
+    Parameters:
+        relative_path (str | Path): Path to translate into the workspace
+
+    Returns:
+        Path: Absolute path for the given path in the workspace
+    """
+    return safe_path_join(WORKSPACE_PATH, relative_path)
+
+
+def safe_path_join(base: Path, *paths: str | Path) -> Path:
+    """Join one or more path components, asserting the resulting path is within the workspace.
+
+    Args:
+        base (Path): The base path
+        *paths (str): The paths to join to the base path
+
+    Returns:
+        Path: The joined path
+    """
+    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}'."
+        )
+
+    return joined_path