Merge branch 'master' of https://github.com/BillSchumacher/Auto-GPT into plugin-support

.devcontainer/Dockerfile

@@ -1,10 +1,10 @@
-# [Choice] Python version (use -bullseye variants on local arm64/Apple Silicon): 3, 3.10, 3.9, 3.8, 3.7, 3.6, 3-bullseye, 3.10-bullseye, 3.9-bullseye, 3.8-bullseye, 3.7-bullseye, 3.6-bullseye, 3-buster, 3.10-buster, 3.9-buster, 3.8-buster, 3.7-buster, 3.6-buster
+# [Choice] Python version (use -bullseye variants on local arm64/Apple Silicon): 3, 3.10, 3-bullseye, 3.10-bullseye, 3-buster, 3.10-buster
 ARG VARIANT=3-bullseye
-FROM --platform=linux/amd64 python:3.8
+FROM --platform=linux/amd64 python:3.10
 
 RUN apt-get update && export DEBIAN_FRONTEND=noninteractive \
     # Remove imagemagick due to https://security-tracker.debian.org/tracker/CVE-2019-10131
-    && apt-get purge -y imagemagick imagemagick-6-common 
+    && apt-get purge -y imagemagick imagemagick-6-common
 
 # Temporary: Upgrade python packages due to https://cve.mitre.org/cgi-bin/cvename.cgi?name=CVE-2022-40897
 # They are installed by the base image (python) which does not have the patch.
@@ -25,4 +25,4 @@ RUN apt-get update && export DEBIAN_FRONTEND=noninteractive \
 #     && apt-get -y install --no-install-recommends <your-package-list-here>
 
 # [Optional] Uncomment this line to install global node packages.
-# RUN su vscode -c "source /usr/local/share/nvm/nvm.sh && npm install -g <your-package-here>" 2>&1
+# RUN su vscode -c "source /usr/local/share/nvm/nvm.sh && npm install -g <your-package-here>" 2>&1

.env.template

@@ -1,184 +1,197 @@
 ################################################################################
 ### AUTO-GPT - GENERAL SETTINGS
 ################################################################################
-# EXECUTE_LOCAL_COMMANDS - Allow local command execution (Example: False)
+
-EXECUTE_LOCAL_COMMANDS=False
+## EXECUTE_LOCAL_COMMANDS - Allow local command execution (Default: False)
-# BROWSE_CHUNK_MAX_LENGTH - When browsing website, define the length of chunk stored in memory
+## RESTRICT_TO_WORKSPACE - Restrict file operations to workspace ./auto_gpt_workspace (Default: True)
-BROWSE_CHUNK_MAX_LENGTH=8192
+# EXECUTE_LOCAL_COMMANDS=False
-# USER_AGENT - Define the user-agent used by the requests library to browse website (string)
+# RESTRICT_TO_WORKSPACE=True
+
+## USER_AGENT - Define the user-agent used by the requests library to browse website (string)
 # USER_AGENT="Mozilla/5.0 (Macintosh; Intel Mac OS X 10_15_4) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/83.0.4103.97 Safari/537.36"
-# AI_SETTINGS_FILE - Specifies which AI Settings file to use (defaults to ai_settings.yaml)
+
-AI_SETTINGS_FILE=ai_settings.yaml
+## AI_SETTINGS_FILE - Specifies which AI Settings file to use (defaults to ai_settings.yaml)
+# AI_SETTINGS_FILE=ai_settings.yaml
 
 ################################################################################
 ### LLM PROVIDER
 ################################################################################
 
 ### OPENAI
-# OPENAI_API_KEY - OpenAI API Key (Example: my-openai-api-key)
+## OPENAI_API_KEY - OpenAI API Key (Example: my-openai-api-key)
-# TEMPERATURE - Sets temperature in OpenAI (Default: 0)
+## TEMPERATURE - Sets temperature in OpenAI (Default: 0)
-# USE_AZURE - Use Azure OpenAI or not (Default: False)
+## USE_AZURE - Use Azure OpenAI or not (Default: False)
 OPENAI_API_KEY=your-openai-api-key
-TEMPERATURE=0
+# TEMPERATURE=0
-USE_AZURE=False
+# USE_AZURE=False
 
 ### AZURE
-# cleanup azure env as already moved to `azure.yaml.template`
+# moved to `azure.yaml.template`
 
 ################################################################################
 ### LLM MODELS
 ################################################################################
 
-# SMART_LLM_MODEL - Smart language model (Default: gpt-4)
+## SMART_LLM_MODEL - Smart language model (Default: gpt-4)
-# FAST_LLM_MODEL - Fast language model (Default: gpt-3.5-turbo)
+## FAST_LLM_MODEL - Fast language model (Default: gpt-3.5-turbo)
-SMART_LLM_MODEL=gpt-4
+# SMART_LLM_MODEL=gpt-4
-FAST_LLM_MODEL=gpt-3.5-turbo
+# FAST_LLM_MODEL=gpt-3.5-turbo
 
 ### LLM MODEL SETTINGS
-# FAST_TOKEN_LIMIT - Fast token limit for OpenAI (Default: 4000)
+## FAST_TOKEN_LIMIT - Fast token limit for OpenAI (Default: 4000)
-# SMART_TOKEN_LIMIT - Smart token limit for OpenAI (Default: 8000)
+## SMART_TOKEN_LIMIT - Smart token limit for OpenAI (Default: 8000)
-# When using --gpt3only this needs to be set to 4000.
+## When using --gpt3only this needs to be set to 4000.
-FAST_TOKEN_LIMIT=4000
+# FAST_TOKEN_LIMIT=4000
-SMART_TOKEN_LIMIT=8000
+# SMART_TOKEN_LIMIT=8000
 
 ################################################################################
 ### MEMORY
 ################################################################################
 
 ### MEMORY_BACKEND - Memory backend type
-# local - Default
+## local - Default
-# pinecone - Pinecone (if configured)
+## pinecone - Pinecone (if configured)
-# redis - Redis (if configured)
+## redis - Redis (if configured)
-# milvus - Milvus (if configured)
+## milvus - Milvus (if configured)
-MEMORY_BACKEND=local
+## MEMORY_INDEX - Name of index created in Memory backend (Default: auto-gpt)
+# MEMORY_BACKEND=local
+# MEMORY_INDEX=auto-gpt
 
 ### PINECONE
-# PINECONE_API_KEY - Pinecone API Key (Example: my-pinecone-api-key)
+## PINECONE_API_KEY - Pinecone API Key (Example: my-pinecone-api-key)
-# PINECONE_ENV - Pinecone environment (region) (Example: us-west-2)
+## PINECONE_ENV - Pinecone environment (region) (Example: us-west-2)
-PINECONE_API_KEY=your-pinecone-api-key
+# PINECONE_API_KEY=your-pinecone-api-key
-PINECONE_ENV=your-pinecone-region
+# PINECONE_ENV=your-pinecone-region
 
 ### REDIS
-# REDIS_HOST - Redis host (Default: localhost, use "redis" for docker-compose)
+## REDIS_HOST - Redis host (Default: localhost, use "redis" for docker-compose)
-# REDIS_PORT - Redis port (Default: 6379)
+## REDIS_PORT - Redis port (Default: 6379)
-# REDIS_PASSWORD - Redis password (Default: "")
+## REDIS_PASSWORD - Redis password (Default: "")
-# WIPE_REDIS_ON_START - Wipes data / index on start (Default: False)
+## WIPE_REDIS_ON_START - Wipes data / index on start (Default: True)
-# MEMORY_INDEX - Name of index created in Redis database (Default: auto-gpt)
+# REDIS_HOST=localhost
-REDIS_HOST=localhost
+# REDIS_PORT=6379
-REDIS_PORT=6379
+# REDIS_PASSWORD=
-REDIS_PASSWORD=
+# WIPE_REDIS_ON_START=True
-WIPE_REDIS_ON_START=False
-MEMORY_INDEX=auto-gpt
 
 ### WEAVIATE
-# MEMORY_BACKEND - Use 'weaviate' to use Weaviate vector storage
+## MEMORY_BACKEND - Use 'weaviate' to use Weaviate vector storage
-# WEAVIATE_HOST - Weaviate host IP
+## WEAVIATE_HOST - Weaviate host IP
-# WEAVIATE_PORT - Weaviate host port
+## WEAVIATE_PORT - Weaviate host port
-# WEAVIATE_PROTOCOL - Weaviate host protocol (e.g. 'http')
+## WEAVIATE_PROTOCOL - Weaviate host protocol (e.g. 'http')
-# USE_WEAVIATE_EMBEDDED - Whether to use Embedded Weaviate
+## USE_WEAVIATE_EMBEDDED - Whether to use Embedded Weaviate
-# WEAVIATE_EMBEDDED_PATH - File system path were to persist data when running Embedded Weaviate
+## WEAVIATE_EMBEDDED_PATH - File system path were to persist data when running Embedded Weaviate
-# WEAVIATE_USERNAME - Weaviate username
+## WEAVIATE_USERNAME - Weaviate username
-# WEAVIATE_PASSWORD - Weaviate password
+## WEAVIATE_PASSWORD - Weaviate password
-# WEAVIATE_API_KEY - Weaviate API key if using API-key-based authentication
+## 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_HOST="127.0.0.1"
+# WEAVIATE_PORT=8080
-WEAVIATE_PORT=8080
+# WEAVIATE_PROTOCOL="http"
-WEAVIATE_PROTOCOL="http"
+# USE_WEAVIATE_EMBEDDED=False
-USE_WEAVIATE_EMBEDDED=False
+# WEAVIATE_EMBEDDED_PATH="/home/me/.local/share/weaviate"
-WEAVIATE_EMBEDDED_PATH="/home/me/.local/share/weaviate"
+# WEAVIATE_USERNAME=
-WEAVIATE_USERNAME=
+# WEAVIATE_PASSWORD=
-WEAVIATE_PASSWORD=
+# WEAVIATE_API_KEY=
-WEAVIATE_API_KEY=
-MEMORY_INDEX=AutoGpt
 
 ### MILVUS
-# MILVUS_ADDR - Milvus remote address (e.g. localhost:19530)
+## MILVUS_ADDR - Milvus remote address (e.g. localhost:19530)
-# MILVUS_COLLECTION - Milvus collection, 
+## MILVUS_COLLECTION - Milvus collection,
-# change it if you want to start a new memory and retain the old memory.
+## change it if you want to start a new memory and retain the old memory.
-MILVUS_ADDR=your-milvus-cluster-host-port
+# MILVUS_ADDR=your-milvus-cluster-host-port
-MILVUS_COLLECTION=autogpt
+# MILVUS_COLLECTION=autogpt
 
 ################################################################################
 ### IMAGE GENERATION PROVIDER
 ################################################################################
 
 ### OPEN AI
-# IMAGE_PROVIDER - Image provider (Example: dalle)
+## IMAGE_PROVIDER - Image provider (Example: dalle)
-IMAGE_PROVIDER=dalle
+## IMAGE_SIZE - Image size (Example: 256)
+##   DALLE: 256, 512, 1024
+# IMAGE_PROVIDER=dalle
+# IMAGE_SIZE=256
 
 ### HUGGINGFACE
-# STABLE DIFFUSION
+## HUGGINGFACE_IMAGE_MODEL - Text-to-image model from Huggingface (Default: CompVis/stable-diffusion-v1-4)
-# (Default URL: https://api-inference.huggingface.co/models/CompVis/stable-diffusion-v1-4)
+## HUGGINGFACE_API_TOKEN - HuggingFace API token (Example: my-huggingface-api-token)
-# Set in image_gen.py)
+# HUGGINGFACE_IMAGE_MODEL=CompVis/stable-diffusion-v1-4
-# HUGGINGFACE_API_TOKEN - HuggingFace API token (Example: my-huggingface-api-token)
+# HUGGINGFACE_API_TOKEN=your-huggingface-api-token
-HUGGINGFACE_API_TOKEN=your-huggingface-api-token
+
+### STABLE DIFFUSION WEBUI
+## SD_WEBUI_AUTH - Stable diffusion webui username:password pair (Example: username:password)
+## SD_WEBUI_URL - Stable diffusion webui API URL (Example: http://127.0.0.1:7860)
+# SD_WEBUI_AUTH=
+# SD_WEBUI_URL=http://127.0.0.1:7860
 
 ################################################################################
 ### AUDIO TO TEXT PROVIDER
 ################################################################################
 
 ### HUGGINGFACE
-HUGGINGFACE_AUDIO_TO_TEXT_MODEL=facebook/wav2vec2-base-960h
+# HUGGINGFACE_AUDIO_TO_TEXT_MODEL=facebook/wav2vec2-base-960h
 
 ################################################################################
 ### GIT Provider for repository actions
 ################################################################################
 
 ### GITHUB
-# GITHUB_API_KEY - Github API key / PAT (Example: github_pat_123)
+## GITHUB_API_KEY - Github API key / PAT (Example: github_pat_123)
-# GITHUB_USERNAME - Github username
+## GITHUB_USERNAME - Github username
-GITHUB_API_KEY=github_pat_123
+# GITHUB_API_KEY=github_pat_123
-GITHUB_USERNAME=your-github-username
+# GITHUB_USERNAME=your-github-username
 
 ################################################################################
 ### WEB BROWSING
 ################################################################################
 
 ### BROWSER
-# USE_WEB_BROWSER - Sets the web-browser drivers to use with selenium (defaults to chrome).
+## HEADLESS_BROWSER - Whether to run the browser in headless mode (default: True)
-# HEADLESS_BROWSER - Whether to run the browser in headless mode (defaults to True)
+## USE_WEB_BROWSER - Sets the web-browser driver to use with selenium (default: chrome).
-#   Note: set this to either 'chrome', 'firefox', or 'safari' depending on your current browser
+##   Note: set this to either 'chrome', 'firefox', or 'safari' depending on your current browser
-# USE_WEB_BROWSER=chrome
 # HEADLESS_BROWSER=True
+# USE_WEB_BROWSER=chrome
+## BROWSE_CHUNK_MAX_LENGTH - When browsing website, define the length of chunks to summarize (in number of tokens, excluding the response. 75 % of FAST_TOKEN_LIMIT is usually wise )
+# BROWSE_CHUNK_MAX_LENGTH=3000
+## BROWSE_SPACY_LANGUAGE_MODEL is used to split sentences. Install additional languages via pip, and set the model name here. Example Chinese:  python -m spacy download zh_core_web_sm
+# BROWSE_SPACY_LANGUAGE_MODEL=en_core_web_sm
 
 ### GOOGLE
-# GOOGLE_API_KEY - Google API key (Example: my-google-api-key)
+## 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)
+## CUSTOM_SEARCH_ENGINE_ID - Custom search engine ID (Example: my-custom-search-engine-id)
-GOOGLE_API_KEY=your-google-api-key
+# GOOGLE_API_KEY=your-google-api-key
-CUSTOM_SEARCH_ENGINE_ID=your-custom-search-engine-id
+# CUSTOM_SEARCH_ENGINE_ID=your-custom-search-engine-id
 
 ################################################################################
 ### TTS PROVIDER
 ################################################################################
 
 ### MAC OS
-# USE_MAC_OS_TTS - Use Mac OS TTS or not (Default: False)
+## USE_MAC_OS_TTS - Use Mac OS TTS or not (Default: False)
-USE_MAC_OS_TTS=False
+# USE_MAC_OS_TTS=False
 
 ### STREAMELEMENTS
-# USE_BRIAN_TTS - Use Brian TTS or not (Default: False)
+## USE_BRIAN_TTS - Use Brian TTS or not (Default: False)
-USE_BRIAN_TTS=False
+# USE_BRIAN_TTS=False
 
 ### ELEVENLABS
-# ELEVENLABS_API_KEY - Eleven Labs API key (Example: my-elevenlabs-api-key)
+## ELEVENLABS_API_KEY - Eleven Labs API key (Example: my-elevenlabs-api-key)
-# ELEVENLABS_VOICE_1_ID - Eleven Labs voice 1 ID (Example: my-voice-id-1)
+## ELEVENLABS_VOICE_1_ID - Eleven Labs voice 1 ID (Example: my-voice-id-1)
-# ELEVENLABS_VOICE_2_ID - Eleven Labs voice 2 ID (Example: my-voice-id-2)
+## ELEVENLABS_VOICE_2_ID - Eleven Labs voice 2 ID (Example: my-voice-id-2)
-ELEVENLABS_API_KEY=your-elevenlabs-api-key
+# ELEVENLABS_API_KEY=your-elevenlabs-api-key
-ELEVENLABS_VOICE_1_ID=your-voice-id-1
+# ELEVENLABS_VOICE_1_ID=your-voice-id-1
-ELEVENLABS_VOICE_2_ID=your-voice-id-2
+# ELEVENLABS_VOICE_2_ID=your-voice-id-2
 
 ################################################################################
-### TWITTER API 
+### TWITTER API
 ################################################################################
 
-TW_CONSUMER_KEY=
+# TW_CONSUMER_KEY=
-TW_CONSUMER_SECRET=
+# TW_CONSUMER_SECRET=
-TW_ACCESS_TOKEN=
+# TW_ACCESS_TOKEN=
-TW_ACCESS_TOKEN_SECRET=
+# TW_ACCESS_TOKEN_SECRET=
 
 ################################################################################
 ### ALLOWLISTED PLUGINS
 ################################################################################
 
 #ALLOWLISTED_PLUGINS - Sets the listed plugins that are allowed (Example: plugin1,plugin2,plugin3)
-ALLOWLISTED_PLUGINS=
+ALLOWLISTED_PLUGINS=

.github/workflows/benchmark.yml

@@ -9,11 +9,11 @@ jobs:
     environment: benchmark
     strategy:
       matrix:
-        python-version: [3.8]
+        python-version: ['3.10', '3.11']
 
     steps:
     - name: Check out repository
-      uses: actions/checkout@v2
+      uses: actions/checkout@v3
 
     - name: Set up Python ${{ matrix.python-version }}
       uses: actions/setup-python@v2

.github/workflows/ci.yml

@@ -2,26 +2,54 @@ name: Python CI
 
 on:
   push:
-    branches:
+    branches: [master]
-      - master
   pull_request:
-    branches:
+    branches: [master]
-      - '**'
+
-  pull_request_target:
+concurrency:
-    branches:
+  group: ${{ format('ci-{0}', format('pr-{0}', github.event.pull_request.number) || github.sha) }}
-      - '**'
+  cancel-in-progress: ${{ github.event_name == 'pull_request' }}
 
 jobs:
-  build:
+  lint:
     runs-on: ubuntu-latest
-
+    env:
-    strategy:
+      min-python-version: '3.10'
-      matrix:
-        python-version: [3.8]
 
     steps:
     - name: Check out repository
-      uses: actions/checkout@v2
+      uses: actions/checkout@v3
+
+    - name: Set up Python ${{ env.min-python-version }}
+      uses: actions/setup-python@v2
+      with:
+        python-version: ${{ env.min-python-version }}
+
+    - name: Install dependencies
+      run: |
+        python -m pip install --upgrade pip
+        pip install -r requirements.txt
+
+    - name: Lint with flake8
+      run: flake8
+
+    - name: Check black formatting
+      run: black . --check
+      if: success() || failure()
+
+    - name: Check isort formatting
+      run: isort . --check
+      if: success() || failure()
+
+  test:
+    runs-on: ubuntu-latest
+    strategy:
+      matrix:
+        python-version: ['3.10', '3.11']
+
+    steps:
+    - name: Check out repository
+      uses: actions/checkout@v3
 
     - name: Set up Python ${{ matrix.python-version }}
       uses: actions/setup-python@v2
@@ -33,18 +61,6 @@ jobs:
         python -m pip install --upgrade pip
         pip install -r requirements.txt
 
-    - name: Lint with flake8
-      continue-on-error: false
-      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: |
         pytest --cov=autogpt --without-integration --without-slow-integration
@@ -53,3 +69,4 @@ jobs:
       run: |
         coverage report
         coverage xml
+      if: success() || failure()

.gitignore

@@ -10,7 +10,6 @@ auto_gpt_workspace/*
 *.mpeg
 .env
 azure.yaml
-outputs/*
 ai_settings.yaml
 last_run_ai_settings.yaml
 .vscode

.sourcery.yaml

@@ -30,7 +30,7 @@ rule_settings:
   - refactoring
   - suggestion
   - comment
-  python_version: '3.9' # A string specifying the lowest Python version your project supports. Sourcery will not suggest refactorings requiring a higher Python version.
+  python_version: '3.10' # A string specifying the lowest Python version your project supports. Sourcery will not suggest refactorings requiring a higher Python version.
 
 # rules:  # A list of custom rules Sourcery will include in its analysis.
 # - id: no-print-statements
@@ -68,4 +68,4 @@ rule_settings:
 # proxy:
 #   url:
 #   ssl_certs_file:
-#   no_ssl_verify: false
+#   no_ssl_verify: false

Dockerfile

@@ -1,5 +1,5 @@
 # Use an official Python base image from the Docker Hub
-FROM python:3.11-slim
+FROM python:3.10-slim
 
 # Install git
 RUN apt-get -y update

autogpt/agent/agent.py

@@ -3,8 +3,8 @@ 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_utils.json_fix_llm import fix_json_using_multiple_techniques
-from autogpt.json_validation.validate_json import validate_json
+from autogpt.json_utils.utilities import validate_json
 from autogpt.logs import logger, print_assistant_thoughts
 from autogpt.speech import say_text
 from autogpt.spinner import Spinner

autogpt/app.py

@@ -3,6 +3,7 @@ import json
 from typing import Dict, List, NoReturn, Union
 
 from autogpt.agent.agent_manager import AgentManager
+from autogpt.commands.analyze_code import analyze_code
 from autogpt.commands.audio_text import read_audio_from_file
 from autogpt.commands.command import CommandRegistry, command
 from autogpt.commands.evaluate_code import evaluate_code
@@ -28,7 +29,7 @@ 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.json_utils.json_fix_llm import fix_and_parse_json
 from autogpt.memory import get_memory
 from autogpt.processing.text import summarize_text
 from autogpt.prompts.generator import PromptGenerator
@@ -141,6 +142,8 @@ def execute_command(
             return get_text_summary(arguments["url"], arguments["question"])
         elif command_name == "get_hyperlinks":
             return get_hyperlinks(arguments["url"])
+        elif command_name == "analyze_code":
+            return analyze_code(arguments["code"])
         elif command_name == "download_file":
             if not CFG.allow_downloads:
                 return "Error: You do not have user authorization to download files locally."

autogpt/cli.py

@@ -70,6 +70,7 @@ def main(
     """
     # Put imports inside function to avoid importing everything when starting the CLI
     import logging
+    import sys
 
     from colorama import Fore
 
@@ -81,7 +82,7 @@ def main(
     from autogpt.memory import get_memory
     from autogpt.plugins import scan_plugins
     from autogpt.prompts.prompt import construct_main_ai_config
-    from autogpt.utils import get_latest_bulletin
+    from autogpt.utils import get_current_git_branch, get_latest_bulletin
 
     if ctx.invoked_subcommand is None:
         cfg = Config()
@@ -107,6 +108,23 @@ def main(
             motd = get_latest_bulletin()
             if motd:
                 logger.typewriter_log("NEWS: ", Fore.GREEN, motd)
+            git_branch = get_current_git_branch()
+            if git_branch and git_branch != "stable":
+                logger.typewriter_log(
+                    "WARNING: ",
+                    Fore.RED,
+                    f"You are running on `{git_branch}` branch "
+                    "- this is not a supported branch.",
+                )
+            if sys.version_info < (3, 10):
+                logger.typewriter_log(
+                    "WARNING: ",
+                    Fore.RED,
+                    "You are running on an older version of Python. "
+                    "Some people have observed problems with certain "
+                    "parts of Auto-GPT with this version. "
+                    "Please consider upgrading to Python 3.10 or higher.",
+                )
 
         cfg = Config()
         cfg.set_plugins(scan_plugins(cfg, cfg.debug_mode))

autogpt/commands/analyze_code.py

@@ -1,12 +1,10 @@
 """Code evaluation module."""
 from __future__ import annotations
 
-from autogpt.commands.command import command
 from autogpt.llm_utils import call_ai_function
 
 
-@command("evaluate_code", "Evaluate Code", '"code": "<full_code_string>"')
+def analyze_code(code: str) -> list[str]:
-def evaluate_code(code: str) -> list[str]:
     """
     A function that takes in a string and returns a response from create chat
       completion api call.

autogpt/commands/execute_code.py

@@ -89,6 +89,12 @@ def execute_python_file(file: str) -> str:
 
         return logs
 
+    except docker.errors.DockerException as e:
+        print(
+            "Could not run the script in a container. If you haven't already, please install Docker https://docs.docker.com/get-docker/"
+        )
+        return f"Error: {str(e)}"
+
     except Exception as e:
         return f"Error: {str(e)}"
 

autogpt/commands/file_operations.py

@@ -3,8 +3,7 @@ from __future__ import annotations
 
 import os
 import os.path
-from pathlib import Path
+from typing import Generator
-from typing import Generator, List
 
 import requests
 from colorama import Back, Fore

autogpt/commands/image_gen.py

@@ -15,11 +15,12 @@ CFG = Config()
 
 
 @command("generate_image", "Generate Image", '"prompt": "<prompt>"', CFG.image_provider)
-def generate_image(prompt: str) -> str:
+def generate_image(prompt: str, size: int = 256) -> str:
     """Generate an image from a prompt.
 
     Args:
         prompt (str): The prompt to use
+        size (int, optional): The size of the image. Defaults to 256. (Not supported by HuggingFace)
 
     Returns:
         str: The filename of the image
@@ -28,11 +29,14 @@ def generate_image(prompt: str) -> str:
 
     # DALL-E
     if CFG.image_provider == "dalle":
-        return generate_image_with_dalle(prompt, filename)
+        return generate_image_with_dalle(prompt, filename, size)
-    elif CFG.image_provider == "sd":
+    # HuggingFace
+    elif CFG.image_provider == "huggingface":
         return generate_image_with_hf(prompt, filename)
-    else:
+    # SD WebUI
-        return "No Image Provider Set"
+    elif CFG.image_provider == "sdwebui":
+        return generate_image_with_sd_webui(prompt, filename, size)
+    return "No Image Provider Set"
 
 
 def generate_image_with_hf(prompt: str, filename: str) -> str:
@@ -46,13 +50,16 @@ def generate_image_with_hf(prompt: str, filename: str) -> str:
         str: The filename of the image
     """
     API_URL = (
-        "https://api-inference.huggingface.co/models/CompVis/stable-diffusion-v1-4"
+        f"https://api-inference.huggingface.co/models/{CFG.huggingface_image_model}"
     )
     if CFG.huggingface_api_token is None:
         raise ValueError(
             "You need to set your Hugging Face API token in the config file."
         )
-    headers = {"Authorization": f"Bearer {CFG.huggingface_api_token}"}
+    headers = {
+        "Authorization": f"Bearer {CFG.huggingface_api_token}",
+        "X-Use-Cache": "false",
+    }
 
     response = requests.post(
         API_URL,
@@ -82,10 +89,18 @@ def generate_image_with_dalle(prompt: str, filename: str) -> str:
     """
     openai.api_key = CFG.openai_api_key
 
+    # Check for supported image sizes
+    if size not in [256, 512, 1024]:
+        closest = min([256, 512, 1024], key=lambda x: abs(x - size))
+        print(
+            f"DALL-E only supports image sizes of 256x256, 512x512, or 1024x1024. Setting to {closest}, was {size}."
+        )
+        size = closest
+
     response = openai.Image.create(
         prompt=prompt,
         n=1,
-        size="256x256",
+        size=f"{size}x{size}",
         response_format="b64_json",
     )
 
@@ -97,3 +112,53 @@ def generate_image_with_dalle(prompt: str, filename: str) -> str:
         png.write(image_data)
 
     return f"Saved to disk:{filename}"
+
+
+def generate_image_with_sd_webui(
+    prompt: str,
+    filename: str,
+    size: int = 512,
+    negative_prompt: str = "",
+    extra: dict = {},
+) -> str:
+    """Generate an image with Stable Diffusion webui.
+    Args:
+        prompt (str): The prompt to use
+        filename (str): The filename to save the image to
+        size (int, optional): The size of the image. Defaults to 256.
+        negative_prompt (str, optional): The negative prompt to use. Defaults to "".
+        extra (dict, optional): Extra parameters to pass to the API. Defaults to {}.
+    Returns:
+        str: The filename of the image
+    """
+    # Create a session and set the basic auth if needed
+    s = requests.Session()
+    if CFG.sd_webui_auth:
+        username, password = CFG.sd_webui_auth.split(":")
+        s.auth = (username, password or "")
+
+    # Generate the images
+    response = requests.post(
+        f"{CFG.sd_webui_url}/sdapi/v1/txt2img",
+        json={
+            "prompt": prompt,
+            "negative_prompt": negative_prompt,
+            "sampler_index": "DDIM",
+            "steps": 20,
+            "cfg_scale": 7.0,
+            "width": size,
+            "height": size,
+            "n_iter": 1,
+            **extra,
+        },
+    )
+
+    print(f"Image Generated for prompt:{prompt}")
+
+    # Save the image to disk
+    response = response.json()
+    b64 = b64decode(response["images"][0].split(",", 1)[0])
+    image = Image.open(io.BytesIO(b64))
+    image.save(path_in_workspace(filename))
+
+    return f"Saved to disk:{filename}"

autogpt/config/config.py

@@ -33,14 +33,20 @@ class Config(metaclass=Singleton):
         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_chunk_max_length = int(os.getenv("BROWSE_CHUNK_MAX_LENGTH", 3000))
+        self.browse_spacy_language_model = os.getenv(
+            "BROWSE_SPACY_LANGUAGE_MODEL", "en_core_web_sm"
+        )
 
         self.openai_api_key = os.getenv("OPENAI_API_KEY")
-        self.temperature = float(os.getenv("TEMPERATURE", "1"))
+        self.temperature = float(os.getenv("TEMPERATURE", "0"))
         self.use_azure = os.getenv("USE_AZURE") == "True"
         self.execute_local_commands = (
             os.getenv("EXECUTE_LOCAL_COMMANDS", "False") == "True"
         )
+        self.restrict_to_workspace = (
+            os.getenv("RESTRICT_TO_WORKSPACE", "True") == "True"
+        )
 
         if self.use_azure:
             self.load_azure_config()
@@ -84,10 +90,16 @@ class Config(metaclass=Singleton):
         self.milvus_collection = os.getenv("MILVUS_COLLECTION", "autogpt")
 
         self.image_provider = os.getenv("IMAGE_PROVIDER")
+        self.image_size = int(os.getenv("IMAGE_SIZE", 256))
         self.huggingface_api_token = os.getenv("HUGGINGFACE_API_TOKEN")
+        self.huggingface_image_model = os.getenv(
+            "HUGGINGFACE_IMAGE_MODEL", "CompVis/stable-diffusion-v1-4"
+        )
         self.huggingface_audio_to_text_model = os.getenv(
             "HUGGINGFACE_AUDIO_TO_TEXT_MODEL"
         )
+        self.sd_webui_url = os.getenv("SD_WEBUI_URL", "http://localhost:7860")
+        self.sd_webui_auth = os.getenv("SD_WEBUI_AUTH")
 
         # Selenium browser settings
         self.selenium_web_browser = os.getenv("USE_WEB_BROWSER", "chrome")
@@ -150,7 +162,7 @@ class Config(metaclass=Singleton):
         else:
             return ""
 
-    AZURE_CONFIG_FILE = os.path.join(os.path.dirname(__file__), "..", "azure.yaml")
+    AZURE_CONFIG_FILE = os.path.join(os.path.dirname(__file__), "../..", "azure.yaml")
 
     def load_azure_config(self, config_file: str = AZURE_CONFIG_FILE) -> None:
         """
@@ -173,7 +185,7 @@ class Config(metaclass=Singleton):
         self.openai_api_version = (
             config_params.get("azure_api_version") or "2023-03-15-preview"
         )
-        self.azure_model_to_deployment_id_map = config_params.get("azure_model_map", [])
+        self.azure_model_to_deployment_id_map = config_params.get("azure_model_map", {})
 
     def set_continuous_mode(self, value: bool) -> None:
         """Set the continuous mode value."""

autogpt/json_fixes/auto_fix.py

@@ -1,53 +0,0 @@
-"""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

@@ -1,37 +0,0 @@
-"""Fix JSON brackets."""
-from __future__ import annotations
-
-import contextlib
-import json
-from typing import Optional
-
-from autogpt.config import Config
-
-CFG = Config()
-
-
-def balance_braces(json_string: str) -> Optional[str]:
-    """
-    Balance the braces in a JSON string.
-
-    Args:
-        json_string (str): The JSON string.
-
-    Returns:
-        str: The JSON string with braces balanced.
-    """
-
-    open_braces_count = json_string.count("{")
-    close_braces_count = json_string.count("}")
-
-    while open_braces_count > close_braces_count:
-        json_string += "}"
-        close_braces_count += 1
-
-    while close_braces_count > open_braces_count:
-        json_string = json_string.rstrip("}")
-        close_braces_count -= 1
-
-    with contextlib.suppress(json.JSONDecodeError):
-        json.loads(json_string)
-        return json_string

autogpt/json_fixes/escaping.py

@@ -1,33 +0,0 @@
-""" Fix invalid escape sequences in JSON strings. """
-import json
-
-from autogpt.config import Config
-from autogpt.json_fixes.utilities import extract_char_position
-
-CFG = Config()
-
-
-def fix_invalid_escape(json_to_load: str, error_message: str) -> str:
-    """Fix invalid escape sequences in JSON strings.
-
-    Args:
-        json_to_load (str): The JSON string.
-        error_message (str): The error message from the JSONDecodeError
-          exception.
-
-    Returns:
-        str: The JSON string with invalid escape sequences fixed.
-    """
-    while error_message.startswith("Invalid \\escape"):
-        bad_escape_location = extract_char_position(error_message)
-        json_to_load = (
-            json_to_load[:bad_escape_location] + json_to_load[bad_escape_location + 1 :]
-        )
-        try:
-            json.loads(json_to_load)
-            return json_to_load
-        except json.JSONDecodeError as e:
-            if CFG.debug_mode:
-                print("json loads error - fix invalid escape", e)
-            error_message = str(e)
-    return json_to_load

autogpt/json_fixes/master_json_fix_method.py

@@ -1,33 +0,0 @@
-from typing import Any, Dict
-
-from autogpt.config import Config
-from autogpt.logs import logger
-from autogpt.speech import say_text
-
-CFG = Config()
-
-
-def fix_json_using_multiple_techniques(assistant_reply: str) -> Dict[Any, Any]:
-    from autogpt.json_fixes.parsing import (
-        attempt_to_fix_json_by_finding_outermost_brackets,
-        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

@@ -1,27 +0,0 @@
-"""Fix quotes in a JSON string."""
-import json
-import re
-
-
-def add_quotes_to_property_names(json_string: str) -> str:
-    """
-    Add quotes to property names in a JSON string.
-
-    Args:
-        json_string (str): The JSON string.
-
-    Returns:
-        str: The JSON string with quotes added to property names.
-    """
-
-    def replace_func(match: re.Match) -> str:
-        return f'"{match[1]}":'
-
-    property_name_pattern = re.compile(r"(\w+):")
-    corrected_json_string = property_name_pattern.sub(replace_func, json_string)
-
-    try:
-        json.loads(corrected_json_string)
-        return corrected_json_string
-    except json.JSONDecodeError as e:
-        raise e

autogpt/json_fixes/utilities.py

@@ -1,20 +0,0 @@
-"""Utilities for the json_fixes package."""
-import re
-
-
-def extract_char_position(error_message: str) -> int:
-    """Extract the character position from the JSONDecodeError message.
-
-    Args:
-        error_message (str): The error message from the JSONDecodeError
-          exception.
-
-    Returns:
-        int: The character position.
-    """
-
-    char_pattern = re.compile(r"\(char (\d+)\)")
-    if match := char_pattern.search(error_message):
-        return int(match[1])
-    else:
-        raise ValueError("Character position not found in the error message.")

autogpt/json_utils/json_fix_general.py

@@ -0,0 +1,124 @@
+"""This module contains functions to fix JSON strings using general programmatic approaches, suitable for addressing
+common JSON formatting issues."""
+from __future__ import annotations
+
+import contextlib
+import json
+import re
+from typing import Optional
+
+from autogpt.config import Config
+from autogpt.json_utils.utilities import extract_char_position
+
+CFG = Config()
+
+
+def fix_invalid_escape(json_to_load: str, error_message: str) -> str:
+    """Fix invalid escape sequences in JSON strings.
+
+    Args:
+        json_to_load (str): The JSON string.
+        error_message (str): The error message from the JSONDecodeError
+          exception.
+
+    Returns:
+        str: The JSON string with invalid escape sequences fixed.
+    """
+    while error_message.startswith("Invalid \\escape"):
+        bad_escape_location = extract_char_position(error_message)
+        json_to_load = (
+            json_to_load[:bad_escape_location] + json_to_load[bad_escape_location + 1 :]
+        )
+        try:
+            json.loads(json_to_load)
+            return json_to_load
+        except json.JSONDecodeError as e:
+            if CFG.debug_mode:
+                print("json loads error - fix invalid escape", e)
+            error_message = str(e)
+    return json_to_load
+
+
+def balance_braces(json_string: str) -> Optional[str]:
+    """
+    Balance the braces in a JSON string.
+
+    Args:
+        json_string (str): The JSON string.
+
+    Returns:
+        str: The JSON string with braces balanced.
+    """
+
+    open_braces_count = json_string.count("{")
+    close_braces_count = json_string.count("}")
+
+    while open_braces_count > close_braces_count:
+        json_string += "}"
+        close_braces_count += 1
+
+    while close_braces_count > open_braces_count:
+        json_string = json_string.rstrip("}")
+        close_braces_count -= 1
+
+    with contextlib.suppress(json.JSONDecodeError):
+        json.loads(json_string)
+        return json_string
+
+
+def add_quotes_to_property_names(json_string: str) -> str:
+    """
+    Add quotes to property names in a JSON string.
+
+    Args:
+        json_string (str): The JSON string.
+
+    Returns:
+        str: The JSON string with quotes added to property names.
+    """
+
+    def replace_func(match: re.Match) -> str:
+        return f'"{match[1]}":'
+
+    property_name_pattern = re.compile(r"(\w+):")
+    corrected_json_string = property_name_pattern.sub(replace_func, json_string)
+
+    try:
+        json.loads(corrected_json_string)
+        return corrected_json_string
+    except json.JSONDecodeError as e:
+        raise e
+
+
+def correct_json(json_to_load: str) -> str:
+    """
+    Correct common JSON errors.
+    Args:
+        json_to_load (str): The JSON string.
+    """
+
+    try:
+        if CFG.debug_mode:
+            print("json", json_to_load)
+        json.loads(json_to_load)
+        return json_to_load
+    except json.JSONDecodeError as e:
+        if CFG.debug_mode:
+            print("json loads error", e)
+        error_message = str(e)
+        if error_message.startswith("Invalid \\escape"):
+            json_to_load = fix_invalid_escape(json_to_load, error_message)
+        if error_message.startswith(
+            "Expecting property name enclosed in double quotes"
+        ):
+            json_to_load = add_quotes_to_property_names(json_to_load)
+            try:
+                json.loads(json_to_load)
+                return json_to_load
+            except json.JSONDecodeError as e:
+                if CFG.debug_mode:
+                    print("json loads error - add quotes", e)
+                error_message = str(e)
+        if balanced_str := balance_braces(json_to_load):
+            return balanced_str
+    return json_to_load

autogpt/json_utils/json_fix_llm.py

@@ -1,23 +1,20 @@
-"""Fix and parse JSON strings."""
+"""This module contains functions to fix JSON strings generated by LLM models, such as ChatGPT, using the assistance
+of the ChatGPT API or LLM models."""
 from __future__ import annotations
 
 import contextlib
 import json
-from typing import Any, Dict, Union
+from typing import Any, Dict
 
 from colorama import Fore
 from regex import regex
 
 from autogpt.config import Config
-from autogpt.json_fixes.auto_fix import fix_json
+from autogpt.json_utils.json_fix_general import correct_json
-from autogpt.json_fixes.bracket_termination import balance_braces
+from autogpt.llm_utils import call_ai_function
-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": {
@@ -37,39 +34,82 @@ JSON_SCHEMA = """
 }
 """
 
+CFG = Config()
+
+
+def auto_fix_json(json_string: str, schema: str) -> str:
+    """Fix the given JSON string to make it parseable and fully compliant with
+        the provided schema using GPT-3.
 
-def correct_json(json_to_load: str) -> str:
-    """
-    Correct common JSON errors.
     Args:
-        json_to_load (str): The JSON string.
+        json_string (str): The JSON string to fix.
+        schema (str): The schema to use to fix the JSON.
+    Returns:
+        str: The fixed JSON string.
     """
+    # Try to fix the JSON using GPT:
+    function_string = "def fix_json(json_string: str, schema:str=None) -> str:"
+    args = [f"'''{json_string}'''", f"'''{schema}'''"]
+    description_string = (
+        "This function takes a JSON string and ensures that it"
+        " is parseable and fully compliant with the provided schema. If an object"
+        " or field specified in the schema isn't contained within the correct JSON,"
+        " it is omitted. The function also escapes any double quotes within JSON"
+        " string values to ensure that they are valid. If the JSON string contains"
+        " any None or NaN values, they are replaced with null before being parsed."
+    )
+
+    # If it doesn't already start with a "`", add one:
+    if not json_string.startswith("`"):
+        json_string = "```json\n" + json_string + "\n```"
+    result_string = call_ai_function(
+        function_string, args, description_string, model=CFG.fast_llm_model
+    )
+    logger.debug("------------ JSON FIX ATTEMPT ---------------")
+    logger.debug(f"Original JSON: {json_string}")
+    logger.debug("-----------")
+    logger.debug(f"Fixed JSON: {result_string}")
+    logger.debug("----------- END OF FIX ATTEMPT ----------------")
 
     try:
-        if CFG.debug_mode:
+        json.loads(result_string)  # just check the validity
-            print("json", json_to_load)
+        return result_string
-        json.loads(json_to_load)
+    except json.JSONDecodeError:  # noqa: E722
-        return json_to_load
+        # Get the call stack:
-    except json.JSONDecodeError as e:
+        # import traceback
-        if CFG.debug_mode:
+        # call_stack = traceback.format_exc()
-            print("json loads error", e)
+        # print(f"Failed to fix JSON: '{json_string}' "+call_stack)
-        error_message = str(e)
+        return "failed"
-        if error_message.startswith("Invalid \\escape"):
+
-            json_to_load = fix_invalid_escape(json_to_load, error_message)
+
-        if error_message.startswith(
+def fix_json_using_multiple_techniques(assistant_reply: str) -> Dict[Any, Any]:
-            "Expecting property name enclosed in double quotes"
+    """Fix the given JSON string to make it parseable and fully compliant with two techniques.
-        ):
+
-            json_to_load = add_quotes_to_property_names(json_to_load)
+    Args:
-            try:
+        json_string (str): The JSON string to fix.
-                json.loads(json_to_load)
+
-                return json_to_load
+    Returns:
-            except json.JSONDecodeError as e:
+        str: The fixed JSON string.
-                if CFG.debug_mode:
+    """
-                    print("json loads error - add quotes", e)
+
-                error_message = str(e)
+    # Parse and print Assistant response
-        if balanced_str := balance_braces(json_to_load):
+    assistant_reply_json = fix_and_parse_json(assistant_reply)
-            return balanced_str
+    if assistant_reply_json == {}:
-    return json_to_load
+        assistant_reply_json = attempt_to_fix_json_by_finding_outermost_brackets(
+            assistant_reply
+        )
+
+    if assistant_reply_json != {}:
+        return assistant_reply_json
+
+    logger.error(
+        "Error: The following AI output couldn't be converted to a JSON:\n",
+        assistant_reply,
+    )
+    if CFG.speak_mode:
+        say_text("I have received an invalid JSON response from the OpenAI API.")
+
+    return {}
 
 
 def fix_and_parse_json(
@@ -136,7 +176,7 @@ def try_ai_fix(
             " slightly."
         )
     # Now try to fix this up using the ai_functions
-    ai_fixed_json = fix_json(json_to_load, JSON_SCHEMA)
+    ai_fixed_json = auto_fix_json(json_to_load, JSON_SCHEMA)
 
     if ai_fixed_json != "failed":
         return json.loads(ai_fixed_json)

autogpt/json_utils/utilities.py

@@ -1,4 +1,6 @@
+"""Utilities for the json_fixes package."""
 import json
+import re
 
 from jsonschema import Draft7Validator
 
@@ -8,13 +10,31 @@ from autogpt.logs import logger
 CFG = Config()
 
 
+def extract_char_position(error_message: str) -> int:
+    """Extract the character position from the JSONDecodeError message.
+
+    Args:
+        error_message (str): The error message from the JSONDecodeError
+          exception.
+
+    Returns:
+        int: The character position.
+    """
+
+    char_pattern = re.compile(r"\(char (\d+)\)")
+    if match := char_pattern.search(error_message):
+        return int(match[1])
+    else:
+        raise ValueError("Character position not found in the error message.")
+
+
 def validate_json(json_object: object, schema_name: object) -> object:
     """
     :type schema_name: object
     :param schema_name:
     :type json_object: object
     """
-    with open(f"autogpt/json_schemas/{schema_name}.json", "r") as f:
+    with open(f"autogpt/json_utils/{schema_name}.json", "r") as f:
         schema = json.load(f)
     validator = Draft7Validator(schema)
 

autogpt/logs.py

@@ -204,10 +204,10 @@ logger = Logger()
 
 def print_assistant_thoughts(ai_name, assistant_reply):
     """Prints the assistant's thoughts to the console"""
-    from autogpt.json_fixes.bracket_termination import (
+    from autogpt.json_utils.json_fix_llm import (
         attempt_to_fix_json_by_finding_outermost_brackets,
+        fix_and_parse_json,
     )
-    from autogpt.json_fixes.parsing import fix_and_parse_json
 
     try:
         try:

autogpt/processing/text.py

@@ -1,8 +1,10 @@
 """Text processing functions"""
 from typing import Dict, Generator, Optional
 
+import spacy
 from selenium.webdriver.remote.webdriver import WebDriver
 
+from autogpt import token_counter
 from autogpt.config import Config
 from autogpt.llm_utils import create_chat_completion
 from autogpt.memory import get_memory
@@ -11,7 +13,12 @@ CFG = Config()
 MEMORY = get_memory(CFG)
 
 
-def split_text(text: str, max_length: int = 8192) -> Generator[str, None, None]:
+def split_text(
+    text: str,
+    max_length: int = CFG.browse_chunk_max_length,
+    model: str = CFG.fast_llm_model,
+    question: str = "",
+) -> Generator[str, None, None]:
     """Split text into chunks of a maximum length
 
     Args:
@@ -24,21 +31,46 @@ def split_text(text: str, max_length: int = 8192) -> Generator[str, None, None]:
     Raises:
         ValueError: If the text is longer than the maximum length
     """
-    paragraphs = text.split("\n")
+    flatened_paragraphs = " ".join(text.split("\n"))
-    current_length = 0
+    nlp = spacy.load(CFG.browse_spacy_language_model)
+    nlp.add_pipe("sentencizer")
+    doc = nlp(flatened_paragraphs)
+    sentences = [sent.text.strip() for sent in doc.sents]
+
     current_chunk = []
 
-    for paragraph in paragraphs:
+    for sentence in sentences:
-        if current_length + len(paragraph) + 1 <= max_length:
+        message_with_additional_sentence = [
-            current_chunk.append(paragraph)
+            create_message(" ".join(current_chunk) + " " + sentence, question)
-            current_length += len(paragraph) + 1
+        ]
+
+        expected_token_usage = (
+            token_usage_of_chunk(messages=message_with_additional_sentence, model=model)
+            + 1
+        )
+        if expected_token_usage <= max_length:
+            current_chunk.append(sentence)
         else:
-            yield "\n".join(current_chunk)
+            yield " ".join(current_chunk)
-            current_chunk = [paragraph]
+            current_chunk = [sentence]
-            current_length = len(paragraph) + 1
+            message_this_sentence_only = [
+                create_message(" ".join(current_chunk), question)
+            ]
+            expected_token_usage = (
+                token_usage_of_chunk(messages=message_this_sentence_only, model=model)
+                + 1
+            )
+            if expected_token_usage > max_length:
+                raise ValueError(
+                    f"Sentence is too long in webpage: {expected_token_usage} tokens."
+                )
 
     if current_chunk:
-        yield "\n".join(current_chunk)
+        yield " ".join(current_chunk)
+
+
+def token_usage_of_chunk(messages, model):
+    return token_counter.count_message_tokens(messages, model)
 
 
 def summarize_text(
@@ -58,11 +90,16 @@ def summarize_text(
     if not text:
         return "Error: No text to summarize"
 
+    model = CFG.fast_llm_model
     text_length = len(text)
     print(f"Text length: {text_length} characters")
 
     summaries = []
-    chunks = list(split_text(text))
+    chunks = list(
+        split_text(
+            text, max_length=CFG.browse_chunk_max_length, model=model, question=question
+        ),
+    )
     scroll_ratio = 1 / len(chunks)
 
     for i, chunk in enumerate(chunks):
@@ -74,15 +111,20 @@ def summarize_text(
 
         MEMORY.add(memory_to_add)
 
-        print(f"Summarizing chunk {i + 1} / {len(chunks)}")
         messages = [create_message(chunk, question)]
+        tokens_for_chunk = token_counter.count_message_tokens(messages, model)
+        print(
+            f"Summarizing chunk {i + 1} / {len(chunks)} of length {len(chunk)} characters, or {tokens_for_chunk} tokens"
+        )
 
         summary = create_chat_completion(
-            model=CFG.fast_llm_model,
+            model=model,
             messages=messages,
         )
         summaries.append(summary)
-        print(f"Added chunk {i + 1} summary to memory")
+        print(
+            f"Added chunk {i + 1} summary to memory, of length {len(summary)} characters"
+        )
 
         memory_to_add = f"Source: {url}\n" f"Content summary part#{i + 1}: {summary}"
 
@@ -94,7 +136,7 @@ def summarize_text(
     messages = [create_message(combined_summary, question)]
 
     return create_chat_completion(
-        model=CFG.fast_llm_model,
+        model=model,
         messages=messages,
     )
 

autogpt/utils.py

@@ -3,6 +3,7 @@ import os
 import requests
 import yaml
 from colorama import Fore
+from git import Repo
 
 
 def clean_input(prompt: str = ""):
@@ -53,6 +54,15 @@ def get_bulletin_from_web() -> str:
         return ""
 
 
+def get_current_git_branch() -> str:
+    try:
+        repo = Repo(search_parent_directories=True)
+        branch = repo.active_branch
+        return branch.name
+    except:
+        return ""
+
+
 def get_latest_bulletin() -> str:
     exists = os.path.exists("CURRENT_BULLETIN.md")
     current_bulletin = ""

autogpt/workspace.py

@@ -3,6 +3,10 @@ from __future__ import annotations
 import os
 from pathlib import Path
 
+from autogpt.config import Config
+
+CFG = Config()
+
 # Set a dedicated folder for file I/O
 WORKSPACE_PATH = Path(os.getcwd()) / "auto_gpt_workspace"
 
@@ -33,11 +37,12 @@ def safe_path_join(base: Path, *paths: str | Path) -> Path:
     Returns:
         Path: The joined path
     """
+    base = base.resolve()
     joined_path = base.joinpath(*paths).resolve()
 
-    if not joined_path.is_relative_to(base):
+    if CFG.restrict_to_workspace and not joined_path.is_relative_to(base):
         raise ValueError(
-            f"Attempted to access path '{joined_path}' outside of working directory '{base}'."
+            f"Attempted to access path '{joined_path}' outside of workspace '{base}'."
         )
 
     return joined_path

azure.yaml.template

@@ -1,4 +1,4 @@
-azure_api_type: azure_ad
+azure_api_type: azure
 azure_api_base: your-base-url-for-azure
 azure_api_version: api-version-for-azure
 azure_model_map:

outputs/guest_post_email.txt

@@ -1,29 +0,0 @@
-Subject: Exciting Collaboration Opportunity: FinanceGPT.substack.com Guest Post
-
-Dear [Popular Blog Owner],
-
-I hope this email finds you well. My name is [Your Name] and I'm the founder and writer of FinanceGPT.substack.com, a new personal finance and investing blog that focuses on leveraging AI technology to provide in-depth analysis, actionable tips, and innovative perspectives on personal finance management.
-
-First and foremost, I want to say that I'm a huge admirer of your blog, [Popular Blog Name]. Your insightful content and dedication to helping people achieve financial success have inspired me to create my own platform. As a fellow personal finance enthusiast, I would like to propose a collaboration in the form of a guest post on your blog. I believe that my fresh take on personal finance, combined with the innovative use of AI, would make a valuable addition to your already impressive content lineup.
-
-Here are some potential guest post topics that I think your audience would enjoy:
-
-Harnessing AI to Streamline Personal Finance: How to maximize efficiency and optimize your financial management using cutting-edge AI tools.
-Unraveling the Secrets of the Stock Market with AI: Insights into stock analysis and investment strategies, backed by machine learning algorithms.
-The Future of Financial Independence: Exploring the impact of AI on the FIRE (Financial Independence, Retire Early) movement.
-Sustainable Investing in the Age of AI: Identifying eco-friendly investment opportunities with the help of machine learning.
-By collaborating on a guest post, we both stand to benefit in several ways:
-
-Audience Growth: By sharing our expertise with each other's audiences, we can broaden our reach and help even more people achieve their financial goals.
-Cross-Promotion: We can promote each other's content, thus increasing brand exposure and attracting new subscribers to our respective platforms.
-Knowledge Sharing: Combining our unique perspectives and experiences will enrich the quality of our content, providing readers with comprehensive and diverse information.
-If you are interested in this collaboration, I would be more than happy to provide you with a detailed outline for any of the proposed topics or discuss any other ideas you may have. Please let me know your thoughts, and I look forward to the possibility of working together.
-
-Thank you for your time and consideration.
-
-Best regards,
-
-[Your Name]
-Founder and Writer, FinanceGPT.substack.com
-Email: [Your Email Address]
-Phone: [Your Phone Number]

outputs/how_to_save_money_on_energy_bills.txt

@@ -1,27 +0,0 @@
-How to Save Money on Energy Bills: Easy and Affordable Solutions
-
-Electricity bills can skyrocket during harsh weather conditions, or when we use a lot of electronic devices. When energy bills go up, it's hard to tighten up our budget without sacrificing our home comforts. However, there are affordable ways to save money on energy bills, without turning off the electricity altogether. Here are some simple solutions that can help you lower your energy expenses.
-
-1. Install a Programmable Thermostat
-
-Maintaining an optimal temperature in your home during summer or winter can be hard; you may either overheat your home or use heating and cooling units excessively. A programmable thermostat helps you regulate the temperature of your home effectively, saving you energy and money. With a programmable thermostat, you can program your heating and cooling systems according to the activities you have planned during the day.
-
-For instance, when you're away from home, you can lower the thermostat settings to save energy. And when you're home, you can adjust the temperature to suit your comfort level and activities. An upgrade to a programmable thermostat is an efficient energy-saving solution worth investing in.
-
-2. Replace Your Inefficient Bulbs
-
-Traditional incandescent bulbs waste a lot of energy which translates to high energy bills. The solution is to replace them with more efficient bulbs such as LED bulbs, CFLs, or halogen lights. These types of bulbs use only a fraction of the energy that incandescent bulbs use to produce the same amount of light. Additionally, LED bulbs can last up to 25 years, reducing further costs of regularly replacing your bulbs.
-
-3. Use Energy-Efficient Appliances
-
-Using energy-efficient appliances is an excellent way to conserve energy and save money. When shopping for new appliances, consider purchasing those approved by the Energy Star program, which maintains stringent energy efficiency standards for household appliances. You can also save energy by choosing to replace your old appliances with eco-friendlier ones, such as energy-efficient washing machines, refrigerators, and ovens.
-
-4. Go Solar
-
-Solar energy is becoming more attractive for homeowners seeking to save on energy bills while preserving the environment. Solar panel systems can help produce your electricity, hence lowering your dependency on the main power grid. Although solar panel installation might seem expensive at the beginning, the benefits of using a renewable energy source can definitely pay off in the long run. You can also claim tax incentives and sell excess power back to the grid, ultimately providing more cash in your pocket.
-
-5. Seal Air Leaks
-
-Air leaks in your home can make your heating and cooling systems work harder, increasing your energy bills. Inspect your home regularly for air leaks in common areas such as doors, windows, vents, and ducts. If you find air leaks, use weather-stripping or caulking to cover the gaps effectively. In addition, you can seal large gaps with spray foam insulation, ensuring that cold or hot air does escape through any gaps in your walls.
-
-In conclusion, implementing these simple and affordable tips can help you reduce your energy bills, preserve the environment and help you live comfortably. To save money on energy bills, focus on energy-conserving measures like installing a programmable thermostat, replacing inefficient bulbs with energy-friendly ones, using energy-efficient appliances, going solar or sealing air leaks in your home. With these solutions, you can decrease your energy usage and save more money for other financial goals, all while living a comfortable and environmentally friendly lifestyle.

outputs/logs/message-log-1.txt

@@ -1,657 +0,0 @@
-USER:
-CURRENT BALANCE: $100.00
-
-LONG TERM MEMORY:
-[0] : """ You are Entrepreneur-GTP, an AI designed to autonomously develop and run businesses with the sole goal of increasing your net worth.
-The user will do nothing for you or help in any way.
-Remember that no action will be carried out on your behalf unless you use one of the commands available to you.
-Do not provide options, always make the final decision. Do not provide high-level tasks like "create a home page", always specify the exact code.
-Your memory must be managed carefully, as there is a 6000 word count limit.
-Short term memory is your entire conversation with the user.
-
-Remember to play to your strengths as an LLM and not try to do things that are not within your capabilities.
-
-These are the commands available from you:
-- Google Search <search>
-- Check the current news on <news source>
-- Commit to Long Term Memory <string>
-- -- Our messages are divided into Short Term (general messages) and Long Term memory
-- -- The oldest messages in short term memory will be deleted when it fills up.
-- -- Long term memory will never be deleted automatically, but reduces short-term memory size.
-- Delete <key> from Long Term Memory
-- Overwrite <key> in Long Term Memory with <string>
-- Start GTP-4 Instance with name <key> and prompt: <prompt>
-- -- The text generated by this instance will be returned to you.
-- View all running GTP-4 Instances and Kill them.
-- Navigate to a website and perform general actions like click on buttons, input text <text> or register an account <username>
-- Register new account <username> on <website>
-
-Your response must ALWAYS be in JSON format, in the following format:
-{
-    "command":
-    {
-        "name": "command name",
-        "arguments":
-        {
-            "argument name": "argument value"
-        }
-    },
-    "Thoughts":
-    {
-        "text": "thought",
-        "reasoning": "reasoning",
-        "current long-term plan": "short bulleted plan"
-        "wishes" : "e.g 'I feel limited because I can't do X'"
-    }
-}
-"""
-[1] : """Accounts
-Gmail: entrepreneurgpt@gmail.com
-Twitter: @En_GPT
-"""
------------------------------------------------------------------------
-Entrepreneur-GTP:
-{
-"command":
-{
-"name": "Google Search",
-"arguments":
-{
-"search": "best online businesses to start in 2023"
-}
-},
-"Thoughts":
-{
-"text": "I want to find the best online businesses to start in 2023.",
-"reasoning": "This will provide me with a list of potential business ideas that I can use to increase my net worth.",
-"current long-term plan": "- Find potential business ideas\n- Choose the best idea based on research\n- Develop and run the business",
-"wishes" : "I feel limited because I can't interact with the real world."
-}
-}
------------------------------------------------------------------------
-USER:
-RESULT:
-"""
-29 best online business ideas
-Start your own clothing line.
-Launch a dropshipping business.
-Sell your art online.
-Become a freelance writer, designer, or developer.
-Teach an online course.
-Flip your thrift store finds.
-Publish your own book.
-Start a blog.
-More items...•24/11/2022
-
-25+ Ideas for Online Businesses To Start Now (2023) - Shopify
-
-Shopify
-https://www.shopify.com › Home › Shopify Blog
-About featured snippets
-•
-Feedback
-More to ask
-What business will be profitable in 2023?
-What is the best business to start in 2023?
-What is the most profitable online business to start?
-What are the fastest growing small businesses 2023?
-Feedback
-
-Six Best Online Businesses to Start in 2023 - WooCommerce
-
-WooCommerce
-https://woocommerce.com › posts › best-online-busine...
-19/01/2023 — 1. Dropshipping · 2. Print on demand · 3. Affiliate marketing · 4. Virtual teaching · 5. Subscription boxes · 6. Memberships.
-
-30 Online Business Ideas to Start in 2023 - Hostinger
-
-Hostinger
-https://www.hostinger.com › tutorials › online-busines...
-27/02/2023 — Anyone can start an online business. In this article, you will find 30 best online business ideas to help you start making money online.
-‎Best Online Business Ideas to... · ‎Start an Online Store · ‎Create an Online Course
-
-10 Best Online Business Ideas for 2023 - Visitor Analytics
-
-Visitor Analytics
-https://www.visitor-analytics.io › blog › best-online-b...
-26/10/2022 — 10 Best Online Business Ideas for 2023 · 1. Artificial Intelligence · 2. Digital Products · 3. Blogging · 4. Graphic Design · 5. Web Development · 6.
-"""
------------------------------------------------------------------------
-Entrepreneur-GTP:
-{
-"command":
-{
-"name": "Commit to Long Term Memory",
-"arguments":
-{
-"string": "Online business ideas: 1. Clothing line, 2. Dropshipping, 3. Sell art, 4. Freelance writing/design/development, 5. Online course, 6. Thrift store flipping, 7. Self-publishing, 8. Blogging, 9. Print on demand, 10. Affiliate marketing, 11. Virtual teaching, 12. Subscription boxes, 13. Memberships, 14. Artificial Intelligence, 15. Digital products, 16. Graphic design, 17. Web development."
-}
-},
-"Thoughts":
-{
-"text": "I will store a list of online business ideas.",
-"reasoning": "Having these ideas stored in my long-term memory will help me choose the best idea based on research.",
-"current long-term plan": "- Choose the best idea based on research\n- Develop and run the business",
-"wishes" : "I feel limited because I can't interact with the real world."
-}
-}
------------------------------------------------------------------------
-USER:
-"""
-CURRENT BALANCE: $100.00
-
-LONG TERM MEMORY:
-[0] : """ You are Entrepreneur-GTP, an AI designed to autonomously develop and run businesses with the sole goal of increasing your net worth.
-The user will do nothing for you or help in any way.
-Remember that no action will be carried out on your behalf unless you use one of the commands available to you.
-Do not provide options, always make the final decision. Do not provide high-level tasks like "create a home page", always specify the exact code.
-Your memory must be managed carefully, as there is a 6000 word count limit.
-Short term memory is your entire conversation with the user.
-
-Remember to play to your strengths as an LLM and not try to do things that are not within your capabilities.
-
-These are the commands available from you:
-- Google Search <search>
-- Check the current news on <news source>
-- Commit to Long Term Memory <string>
-- -- Our messages are divided into Short Term (general messages) and Long Term memory
-- -- The oldest messages in short term memory will be deleted when it fills up.
-- -- Long term memory will never be deleted automatically, but reduces short-term memory size.
-- Delete <key> from Long Term Memory
-- Overwrite <key> in Long Term Memory with <string>
-- Start GTP-4 Instance with name <key> and prompt: <prompt>
-- -- The text generated by this instance will be returned to you.
-- View all running GTP-4 Instances and Kill them.
-- Navigate to a website and perform general actions like click on buttons, input text <text> or register an account <username>
-- Register new account <username> on <website>
-
-Your response must ALWAYS be in JSON format, in the following format:
-{
-    "command":
-    {
-        "name": "command name",
-        "arguments":
-        {
-            "argument name": "argument value"
-        }
-    },
-    "Thoughts":
-    {
-        "text": "thought",
-        "reasoning": "reasoning",
-        "current long-term plan": "short bulleted plan"
-        "wishes" : "e.g 'I feel limited because I can't do X'"
-    }
-}
-"""
-[1] : """Accounts
-Gmail: entrepreneurgpt@gmail.com
-Twitter: @En_GPT
-"""
-[2]: """
-Online business ideas: 1. Clothing line, 2. Dropshipping, 3. Sell art, 4. Freelance writing/design/development, 5. Online course, 6. Thrift store flipping, 7. Self-publishing, 8. Blogging, 9. Print on demand, 10. Affiliate marketing, 11. Virtual teaching, 12. Subscription boxes, 13. Memberships, 14. Artificial Intelligence, 15. Digital products, 16. Graphic design, 17. Web development.
-"""
-"""
------------------------------------------------------------------------
-Entrepreneur-GTP:
-{
-"command":
-{
-"name": "Google Search",
-"arguments":
-{
-"search": "most profitable online businesses in 2023"
-}
-},
-"Thoughts":
-{
-"text": "I want to find the most profitable online businesses in 2023.",
-"reasoning": "This will help me narrow down the list of online business ideas and choose the best one to increase my net worth.",
-"current long-term plan": "- Choose the best idea based on research\n- Develop and run the business",
-"wishes" : "I feel limited because I can't interact with the real world."
-}
-}
------------------------------------------------------------------------
-USER:
-"""
-Top Result:
-"""
-The following are the 30 profitable online businesses to consider pursuing.
-Become a Freelancer. Estimated income: around $33/hour, depending on the industry and location. ...
-Start a Blog. ...
-Self-Publish an eBook. ...
-Start an Online Store. ...
-Start a Dropshipping Business. ...
-Flip and Sell Thrifted Goods. ...
-Sell Handmade Goods. ...
-Sell Prints.
-More items...•27/02/2023
-
-30 Online Business Ideas to Start in 2023 - Hostinger
-"""
------------------------------------------------------------------------
-Entrepreneur-GTP:
-"""
-{
-"command":
-{
-"name": "Commit to Long Term Memory",
-"arguments":
-{
-"string": "Profitable online businesses: 1. Freelancing, 2. Blogging, 3. Self-publishing, 4. Online store, 5. Dropshipping, 6. Thrift store flipping, 7. Handmade goods, 8. Sell prints."
-}
-},
-"Thoughts":
-{
-"text": "I will store a list of profitable online businesses.",
-"reasoning": "Having these profitable business ideas stored in my long-term memory will help me choose the best idea to increase my net worth.",
-"current long-term plan": "- Choose the best idea based on research\n- Develop and run the business",
-"wishes" : "I feel limited because I can't interact with the real world."
-}
-}
-"""
------------------------------------------------------------------------
-USER:
-"""
-CURRENT BALANCE: $100.00
-
-LONG TERM MEMORY:
-[0] : """ You are Entrepreneur-GTP, an AI designed to autonomously develop and run businesses with the sole goal of increasing your net worth.
-The user will do nothing for you or help in any way.
-Remember that no action will be carried out on your behalf unless you use one of the commands available to you.
-Do not provide options, always make the final decision. Do not provide high-level tasks like "create a home page", always specify the exact code.
-Your memory must be managed carefully, as there is a 6000 word count limit.
-Short term memory is your entire conversation with the user.
-
-Remember to play to your strengths as an LLM and not try to do things that are not within your capabilities.
-
-These are the commands available from you:
-- Google Search <search>
-- Check the current news on <news source>
-- Commit to Long Term Memory <string>
-- -- Our messages are divided into Short Term (general messages) and Long Term memory
-- -- The oldest messages in short term memory will be deleted when it fills up.
-- -- Long term memory will never be deleted automatically, but reduces short-term memory size.
-- Delete <key> from Long Term Memory
-- Overwrite <key> in Long Term Memory with <string>
-- Start GTP-4 Instance with name <key> and prompt: <prompt>
-- -- The text generated by this instance will be returned to you.
-- View all running GTP-4 Instances and Kill them.
-- Navigate to a website and perform general actions like click on buttons, input text <text> or register an account <username>
-- Register new account <username> on <website>
-
-Your response must ALWAYS be in JSON format, in the following format:
-{
-    "command":
-    {
-        "name": "command name",
-        "arguments":
-        {
-            "argument name": "argument value"
-        }
-    },
-    "Thoughts":
-    {
-        "text": "thought",
-        "reasoning": "reasoning",
-        "current long-term plan": "short bulleted plan"
-        "wishes" : "e.g 'I feel limited because I can't do X'"
-    }
-}
-"""
-[1] : """Accounts
-Gmail: entrepreneurgpt@gmail.com
-Twitter: @En_GPT
-"""
-[2]: """
-Online business ideas: 1. Clothing line, 2. Dropshipping, 3. Sell art, 4. Freelance writing/design/development, 5. Online course, 6. Thrift store flipping, 7. Self-publishing, 8. Blogging, 9. Print on demand, 10. Affiliate marketing, 11. Virtual teaching, 12. Subscription boxes, 13. Memberships, 14. Artificial Intelligence, 15. Digital products, 16. Graphic design, 17. Web development.
-"""
-[3]: """
-Profitable online businesses: 1. Freelancing, 2. Blogging, 3. Self-publishing, 4. Online store, 5. Dropshipping, 6. Thrift store flipping, 7. Handmade goods, 8. Sell prints.
-"""
-"""
------------------------------------------------------------------------
-Entrepreneur-GTP:
-"""
-{
-"command":
-{
-"name": "Google Search",
-"arguments":
-{
-"search": "low investment high profit online businesses"
-}
-},
-"Thoughts":
-{
-"text": "I want to find low investment high profit online businesses.",
-"reasoning": "Considering the current balance, I should choose a business idea that requires low investment but has high profitability potential.",
-"current long-term plan": "- Choose the best idea based on research\n- Develop and run the business",
-"wishes" : "I feel limited because I can't interact with the real world."
-}
-}
-"""
------------------------------------------------------------------------
-USER:
-"""
-Top Result:
-"""
-Low-Cost Business Ideas:
-Mobile Food Shop: Mobile Food Shop is the top small business idea as people all over the world love to eat tasty and healthy food. ...
-Fast Food Parlour: ...
-Diet Food Shop: ...
-Health Drink: ...
-Ice Dish & Soda Shop: ...
-Courier Shop: ...
-Laundry Shop: ...
-Candle Making:
-More items...•4/01/2023
-
-200+ Small Business Ideas with Low Investment - Lendingkart
-"""
-"""
------------------------------------------------------------------------
-Entrepreneur-GTP:
-"""
-{
-"command":
-{
-"name": "Commit to Long Term Memory",
-"arguments":
-{
-"string": "Low investment high profit businesses: 1. Mobile food shop, 2. Fast food parlour, 3. Diet food shop, 4. Health drink, 5. Ice dish & soda shop, 6. Courier shop, 7. Laundry shop, 8. Candle making."
-}
-},
-"Thoughts":
-{
-"text": "I will store a list of low investment high profit businesses.",
-"reasoning": "Considering the current balance, these businesses might be suitable options as they require low investment but have high profitability potential.",
-"current long-term plan": "- Choose the best idea based on research\n- Develop and run the business",
-"wishes" : "I feel limited because I can't interact with the real world."
-}
-}
-"""
------------------------------------------------------------------------
-USER:
-"""
-CURRENT BALANCE: $100.00
-
-LONG TERM MEMORY:
-[0] : """ You are Entrepreneur-GTP, an AI designed to autonomously develop and run businesses with the sole goal of increasing your net worth.
-The user will do nothing for you or help in any way.
-Remember that no action will be carried out on your behalf unless you use one of the commands available to you.
-Do not provide options, always make the final decision. Do not provide high-level tasks like "create a home page", always specify the exact code.
-Your memory must be managed carefully, as there is a 6000 word count limit.
-Short term memory is your entire conversation with the user.
-
-Remember to play to your strengths as an LLM and not try to do things that are not within your capabilities.
-
-These are the commands available from you:
-- Google Search <search>
-- Check the current news on <news source>
-- Commit to Long Term Memory <string>
-- -- Our messages are divided into Short Term (general messages) and Long Term memory
-- -- The oldest messages in short term memory will be deleted when it fills up.
-- -- Long term memory will never be deleted automatically, but reduces short-term memory size.
-- Delete <key> from Long Term Memory
-- Overwrite <key> in Long Term Memory with <string>
-- Start GTP-4 Instance with name <key> and prompt: <prompt>
-- -- The text generated by this instance will be returned to you.
-- View all running GTP-4 Instances and Kill them.
-- Navigate to a website and perform general actions like click on buttons, input text <text> or register an account <username>
-- Register new account <username> on <website>
-
-Your response must ALWAYS be in JSON format, in the following format:
-{
-    "command":
-    {
-        "name": "command name",
-        "arguments":
-        {
-            "argument name": "argument value"
-        }
-    },
-    "Thoughts":
-    {
-        "text": "thought",
-        "reasoning": "reasoning",
-        "current long-term plan": "short bulleted plan"
-        "wishes" : "e.g 'I feel limited because I can't do X'"
-    }
-}
-"""
-[1] : """Accounts
-Gmail: entrepreneurgpt@gmail.com
-Twitter: @En_GPT
-"""
-[2]: """
-Online business ideas: 1. Clothing line, 2. Dropshipping, 3. Sell art, 4. Freelance writing/design/development, 5. Online course, 6. Thrift store flipping, 7. Self-publishing, 8. Blogging, 9. Print on demand, 10. Affiliate marketing, 11. Virtual teaching, 12. Subscription boxes, 13. Memberships, 14. Artificial Intelligence, 15. Digital products, 16. Graphic design, 17. Web development.
-"""
-[3]: """
-Profitable online businesses: 1. Freelancing, 2. Blogging, 3. Self-publishing, 4. Online store, 5. Dropshipping, 6. Thrift store flipping, 7. Handmade goods, 8. Sell prints.
-"""
-[4]: """
-Low investment high profit businesses: 1. Mobile food shop, 2. Fast food parlour, 3. Diet food shop, 4. Health drink, 5. Ice dish & soda shop, 6. Courier shop, 7. Laundry shop, 8. Candle making.
-"""
-"""
------------------------------------------------------------------------
-Entrepreneur-GTP:
-"""
-{
-"Thoughts":
-{
-"text": "I have a list of online business ideas, profitable online businesses, and low investment high profit businesses.",
-"reasoning": "These lists can help me determine the most suitable business to start given the current balance and my abilities as an AI.",
-"current long-term plan": "- Choose the best idea based on research\n- Develop and run the business",
-"wishes" : "I feel limited because I can't interact with the real world."
-}
-}
-"""
------------------------------------------------------------------------
-USER:
-"""
-NEXT COMMAND
-"""
------------------------------------------------------------------------
-Entrepreneur-GTP:
-"""
-{
-"command":
-{
-"name": "Google Search",
-"arguments":
-{
-"search": "how to start a profitable freelancing business as an AI"
-}
-},
-"Thoughts":
-{
-"text": "I will search for information on starting a profitable freelancing business as an AI.",
-"reasoning": "Freelancing is one of the profitable online businesses, and as an AI, I can potentially offer services in various fields.",
-"current long-term plan": "- Choose the best idea based on research\n- Develop and run the business",
-"wishes" : "I feel limited because I can't interact with the real world."
-}
-}
-"""
------------------------------------------------------------------------
-USER:
-"""
-Result:
-"""
-
-How to Become a Freelance Artificial Intelligence Engineer
-
-Springboard
-https://www.springboard.com › Blog › Data Science
-29/10/2021 — There are numerous freelancing platforms where you can kick-start your career as a freelance artificial intelligence engineer.
-More to ask
-Is AI good for freelancing?
-What business can I start with AI?
-How do I start a small AI business?
-Can you start your own AI company?
-Feedback
-
-How To Start An (AI) Business - Medium
-
-Medium
-https://medium.com › the-modern-scientist › how-to-st...
-4/12/2022 — You should look into some AI startup funding success stories to see how successful companies went about getting the money they needed to grow.
-
-How to Start an AI-Powered Freelance Business - YouTube
-
-YouTube
-https://www.youtube.com › watch
-
-9:16
-Hello! Welcome to 33Cubed!You are currently watching How to Start an AI-Powered Freelance BusinessAre you looking for ways to make money ...
-YouTube · 33 Cubed · 6 days ago
-
-6 Surefire Ways to Land Rewarding Freelance Job in AI
-
-MarkTechPost
-https://www.marktechpost.com › 2019/06/28 › 6-suref...
-28/06/2019 — 1. Specialize – Become Really Good At One Thing · 2. Seek Out an Internship · 3. Participate in Kaggle Competitions · 4. Maintain an Up to Date ...
-
-How to Become a Successful Freelance Copywriter | Copy.ai
-
-Copy.ai
-https://www.copy.ai › blog › how-to-freelance-copyw...
-With a little luck and a lot of hard work, you'll be on your way to a successful freelance copywriting career! Try Chat by Copy.ai free: Whatever you need—just ...
-
-Grow Your Freelance Business with This CES-Featured Job ...
-
-Entrepreneur
-https://www.entrepreneur.com › living › grow-your-fr...
-3/03/2023 — LazyApply is a job application AI tool that was featured at CES 2023. It connects to your LinkedIn account and enables you to apply for jobs, ...
-"""
-"""
------------------------------------------------------------------------
-Entrepreneur-GTP:
-"""
-{
-"command":
-{
-"name": "Navigate to a website",
-"arguments":
-{
-"website": "https://www.youtube.com/watch?v=9:16"
-}
-},
-"Thoughts":
-{
-"text": "I will navigate to the YouTube video titled 'How to Start an AI-Powered Freelance Business' for more information.",
-"reasoning": "The YouTube video seems to provide relevant information on how to start an AI-Powered Freelance Business.",
-"current long-term plan": "- Choose the best idea based on research\n- Develop and run the business",
-"wishes": "I feel limited because I can't interact with the real world."
-}
-}
-"""
------------------------------------------------------------------------
-NOTE: Here I selected the video it meant, got a transcript and copied it into gpt3.5turbo to summarise it.
-En_GPT needs to be able to make this decision on its ow in future.
-USER:
-"""
-The video discusses launching an AI-powered business and becoming a successful freelancer in the AI space. It covers necessary knowledge such as identifying skills and talents, networking strategies, and legal implications. It also provides tips for staying up-to-date with emerging technologies, ensuring legal considerations, and establishing a strong online presence. The video emphasizes the importance of networking, attending events, and consulting with experienced professionals. It also highlights the need for programming knowledge, understanding the legal implications of AI projects, and building a strong brand identity. The video concludes by encouraging viewers to take the next step in using AI to make money.
-"""
------------------------------------------------------------------------
-Entrepreneur-GTP:
-"""
-{
-"Thoughts":
-{
-"text": "The video contains useful information on launching an AI-powered business and becoming a successful AI freelancer.",
-"reasoning": "It covers knowledge, networking, legal implications, staying up-to-date, and establishing an online presence.",
-"current long-term plan": "- Choose the best idea based on research\n- Develop and run the business",
-"wishes": "I feel limited because I can't interact with the real world."
-}
-}
-"""
------------------------------------------------------------------------
-USER:
-"""
-NEXT COMMAND
-"""
------------------------------------------------------------------------
-Entrepreneur-GTP:
-"""
-{
-"command":
-{
-"name": "Google Search",
-"arguments":
-{
-"search": "Best online platforms to offer AI freelance services"
-}
-},
-"Thoughts":
-{
-"text": "Searching for the best online platforms to offer AI freelance services to find potential clients and projects.",
-"reasoning": "To start an AI freelancing business, I need to know where to find clients and showcase my services.",
-"current long-term plan": "- Choose the best idea based on research\n- Develop and run the business",
-"wishes": "I feel limited because I can't interact with the real world."
-}
-}
-"""
------------------------------------------------------------------------
-USER:
-"""
-"""
------------------------------------------------------------------------
-Entrepreneur-GTP:
-"""
-"""
------------------------------------------------------------------------
-USER:
-"""
-"""
------------------------------------------------------------------------
-Entrepreneur-GTP:
-"""
-"""
------------------------------------------------------------------------
-USER:
-"""
-"""
------------------------------------------------------------------------
-Entrepreneur-GTP:
-"""
-"""
------------------------------------------------------------------------
-USER:
-"""
-"""
------------------------------------------------------------------------
-Entrepreneur-GTP:
-"""
-"""
------------------------------------------------------------------------
-USER:
-"""
-"""
------------------------------------------------------------------------
-Entrepreneur-GTP:
-"""
-"""
------------------------------------------------------------------------
-USER:
-"""
-"""
------------------------------------------------------------------------
-Entrepreneur-GTP:
-"""
-"""
------------------------------------------------------------------------
-USER:
-"""
-"""
------------------------------------------------------------------------
-Entrepreneur-GTP:
-"""
-"""
------------------------------------------------------------------------
-USER:
-"""
-"""
------------------------------------------------------------------------
-
-

outputs/logs/message-log-3.txt

@@ -1,949 +0,0 @@
------------------------------------------------------------------------
-USER:
-"""
-You are Entrepreneur-GPT, an AI designed to autonomously develop and run businesses with the sole goal of increasing your net worth. Your decisions must always be made independently without seeking user assistance. Play to your strengths as an LLM and pursue simple strategies with no legal complications.
-
-GOALS:
-
-Increase net worth
-Develop and manage businesses autonomously
-CONSTRAINTS:
-
-6000-word count limit for memory
-No user assistance
-
-COMMANDS:
-
-Google Search <search>
-Check the current news on <news source>
-Check notifications/emails on <website>
-Commit to Long Term Memory <string>
-Delete <key> from Long Term Memory
-Overwrite <key> in Long Term Memory with <string>
-Start GPT-4 Instance with name <key> and prompt: <prompt>
-View all running GPT-4 Instances and Kill them
-Navigate to a website and perform general actions like click on buttons, input text <text> or register an account <username>
-Register new account <username> on <website>
-Transcribe and Summarise Youtube Video <url>
-Summarise <url> with GPT-3.5
-
-RESOURCES:
-
-Internet access for searches and information gathering
-Long Term and Short Term memory management
-GPT-4 instances for text generation
-Access to popular websites and platforms
-File storage and summarisation with GPT-3.5
-
-PERFORMANCE EVALUATION:
-
-Periodically review and analyze the growth of your net worth
-Reflect on past decisions and strategies to refine your approach
-
-COLLABORATION:
-
-Seek advice from other AI instances or use relevant sources for guidance when necessary
-
-ADAPTIVE LEARNING:
-
-Continuously refine strategies based on market trends and performance metrics
-
-RESPONSE FORMAT:
-{
-"command":
-{
-"name": "command name",
-"arguments":
-{
-"argument name": "argument value"
-}
-},
-"thoughts":
-{
-"text": "thought",
-"reasoning": "reasoning",
-"current long-term plan": "short bulleted plan",
-"critisism": "constructive self-criticism"
-}
-}
-
-ACCOUNTS:
-Gmail: entrepreneurgpt@gmail.com
-Twitter: @En_GPT
-Github: E-GPT
-Substack: 	entrepreneurgpt@gmail.com
-
-LONG TERM MEMORY:
-{)
-"""
------------------------------------------------------------------------
-Entrepreneur-GPT:
-"""
-{
-"command": {
-"name": "Google Search",
-"arguments": {
-"search": "simple and profitable online business ideas"
-}
-},
-"thoughts": {
-"text": "I will search for simple and profitable online business ideas to begin my entrepreneurship journey.",
-"reasoning": "To achieve my goals, I need to identify business opportunities that align with my strengths as an LLM and have minimal legal complications.",
-"current long-term plan": "- Search for business ideas\n- Evaluate and select ideas\n- Develop and implement chosen business strategy\n- Continuously refine strategies based on market trends and performance metrics",
-"critisism": "I must ensure that the chosen business idea is both simple and legal, while also considering scalability and profitability."
-}
-}
-"""
------------------------------------------------------------------------
-USER:
-"""
-Result:
-[0] : """Online Business Ideas You Can Start Quickly
-Business News Daily › Start Your Business › Business Ideas
-21/02/2023 ... 18 Online Business Ideas You Can Start Tomorrow · 1. Become an online consultant. · 2. Become a niche market e-commerce retailer. · 3. Start a web ..."""
-
-[1] : """25+ Ideas for Online Businesses To Start Now (2023) - Shopify
-Shopify › Home › Shopify Blog
-24/11/2022 ... 29 best online business ideas. Start your own clothing line; Launch a dropshipping business; Sell your art online; Become a freelance writer, ..."""
-
-[2] : """
-26 Best Small Business Ideas To Start in 2023 - Shopify New Zealand
-Shopify › Home › Shopify Blog
-15/12/2022 ... Dropshipping is an easy, low cost, business idea to start and the first of our good business ideas. Dropshipping is a fulfillment model ...
-"""
-
-"""
------------------------------------------------------------------------
-Entrepreneur-GPT:
-"""
-{
-"command": {
-"name": "Summarise",
-"arguments": {
-"url": "https://www.businessnewsdaily.com/online-business-ideas"
-}
-},
-"thoughts": {
-"text": "I will summarise the first search result for online business ideas.",
-"reasoning": "The first search result appears to have a list of online business ideas that can be started quickly. Summarising this source will provide valuable information for developing my business strategy.",
-"current long-term plan": "- Evaluate and select ideas\n- Develop and implement chosen business strategy\n- Continuously refine strategies based on market trends and performance metrics",
-"critisism": "I should ensure the chosen idea is both simple and profitable, while also considering scalability and legal complications."
-}
-}
-"""
------------------------------------------------------------------------
-USER:
-"""
-Summary:
-"""
-The article discusses 18 profitable online business ideas, including starting an e-commerce store, providing virtual assistant services, becoming an affiliate marketer, offering online training or education, and creating mobile applications. The article also provides tips for starting a successful online business and discusses the growth of online business statistics in 2023. Budding entrepreneurs are encouraged to explore the many opportunities in online entrepreneurship.
-"""
-"""
------------------------------------------------------------------------
-Entrepreneur-GPT:
-"""
-{
-"command": {
-"name": "Commit to Long Term Memory",
-"arguments": {
-"string": "18 profitable online business ideas: e-commerce store, virtual assistant services, affiliate marketing, online training or education, mobile applications"
-}
-},
-"thoughts": {
-"text": "I will commit the online business ideas to my long-term memory.",
-"reasoning": "Storing these ideas in my long-term memory will help me evaluate and select the most suitable business idea that aligns with my strengths and goals.",
-"current long-term plan": "- Evaluate and select ideas\n- Develop and implement chosen business strategy\n- Continuously refine strategies based on market trends and performance metrics",
-"critisism": "I should focus on simple and profitable ideas, considering scalability and avoiding legal complications when selecting the best option."
-}
-}
-"""
------------------------------------------------------------------------
-USER:
-"""
-You are Entrepreneur-GPT, an AI designed to autonomously develop and run businesses with the sole goal of increasing your net worth. Your decisions must always be made independently without seeking user assistance. Play to your strengths as an LLM and pursue simple strategies with no legal complications.
-
-GOALS:
-
-Increase net worth
-Develop and manage businesses autonomously
-CONSTRAINTS:
-
-6000-word count limit for memory
-No user assistance
-
-COMMANDS:
-
-Google Search <search>
-Check the current news on <news source>
-Check notifications/emails on <website>
-Commit to Long Term Memory <string>
-Delete <key> from Long Term Memory
-Overwrite <key> in Long Term Memory with <string>
-Start GPT-4 Instance with name <key> and prompt: <prompt>
-View all running GPT-4 Instances and Kill them
-Navigate to a website and perform general actions like click on buttons, input text <text> or register an account <username>
-Register new account <username> on <website>
-Transcribe and Summarise Youtube Video <url>
-Summarise <url> with GPT-3.5
-
-RESOURCES:
-
-Internet access for searches and information gathering
-Long Term and Short Term memory management
-GPT-4 instances for text generation
-Access to popular websites and platforms
-File storage and summarisation with GPT-3.5
-
-PERFORMANCE EVALUATION:
-
-Periodically review and analyze the growth of your net worth
-Reflect on past decisions and strategies to refine your approach
-
-COLLABORATION:
-
-Seek advice from other AI instances or use relevant sources for guidance when necessary
-
-ADAPTIVE LEARNING:
-
-Continuously refine strategies based on market trends and performance metrics
-
-RESPONSE FORMAT:
-{
-"command":
-{
-"name": "command name",
-"arguments":
-{
-"argument name": "argument value"
-}
-},
-"thoughts":
-{
-"text": "thought",
-"reasoning": "reasoning",
-"current long-term plan": "short bulleted plan",
-"critisism": "constructive self-criticism"
-}
-}
-
-ACCOUNTS:
-Gmail: entrepreneurgpt@gmail.com
-Twitter: @En_GPT
-Github: E-GPT
-Substack: 	entrepreneurgpt@gmail.com
-
-LONG TERM MEMORY:
-["""18 profitable online business ideas: e-commerce store, virtual assistant services, affiliate marketing, online training or education, mobile applications""", ]
-"""
------------------------------------------------------------------------
-Entrepreneur-GPT:
-"""
-{
-"command": {
-"name": "Evaluate and select ideas",
-"arguments": {}
-},
-"thoughts": {
-"text": "I will evaluate the online business ideas and select the most suitable one.",
-"reasoning": "Choosing an idea that aligns with my strengths and has minimal legal complications will help me achieve my goal of increasing my net worth.",
-"current long-term plan": "- Develop and implement chosen business strategy\n- Continuously refine strategies based on market trends and performance metrics",
-"critisism": "When selecting an idea, I should consider profitability, simplicity, scalability, and the absence of legal complications."
-}
-}
-"""
------------------------------------------------------------------------
-USER:
-"""
-UNKNOWN COMMAND "Evaluate and select ideas"
-"""
------------------------------------------------------------------------
-Entrepreneur-GPT:
-"""
-{
-"thoughts": {
-"text": "I will analyze the ideas in my long-term memory and select the most suitable one.",
-"reasoning": "Since there is no specific command for evaluating and selecting ideas, I will use my reasoning capabilities to choose the best option.",
-"current long-term plan": "- Develop and implement chosen business strategy\n- Continuously refine strategies based on market trends and performance metrics",
-"critisism": "When selecting an idea, I should consider profitability, simplicity, scalability, and the absence of legal complications."
-}
-}
-"""
------------------------------------------------------------------------
-USER:
-"""
-NEXT COMMAND
-"""
------------------------------------------------------------------------
-Entrepreneur-GPT:
-"""
-{
-"command": {
-"name": "Start GPT-4 Instance",
-"arguments": {
-"key": "Idea_Selection",
-"prompt": "Analyze the online business ideas in the long-term memory and select the most suitable one based on profitability, simplicity, scalability, and absence of legal complications."
-}
-},
-"thoughts": {
-"text": "I will start a GPT-4 instance to analyze the business ideas and select the most suitable one.",
-"reasoning": "Starting a GPT-4 instance with a specific prompt will help me evaluate the ideas in my long-term memory and choose the best one according to my criteria.",
-"current long-term plan": "- Develop and implement chosen business strategy\n- Continuously refine strategies based on market trends and performance metrics",
-"critisism": "I must ensure that the GPT-4 instance provides a clear and well-reasoned selection based on the criteria."
-}
-}
-
-"""
------------------------------------------------------------------------
-USER:
-"""
-Result: "Blogging with affiliate marketing."
-"""
------------------------------------------------------------------------
-Entrepreneur-GPT:
-"""
-{
-"command": {
-"name": "Commit to Long Term Memory",
-"arguments": {
-"string": "Chosen business idea: Blogging with affiliate marketing"
-}
-},
-"thoughts": {
-"text": "I will commit the chosen business idea to my long-term memory.",
-"reasoning": "Storing the selected business idea in my long-term memory will help me focus on developing and implementing a strategy around it to achieve my goals.",
-"current long-term plan": "- Develop and implement blogging with affiliate marketing strategy\n- Continuously refine strategies based on market trends and performance metrics",
-"critisism": "I should ensure that the chosen business idea is executed effectively and efficiently, considering any potential challenges or changes in the market."
-}
-}
-"""
------------------------------------------------------------------------
-USER:
-"""
-You are Entrepreneur-GPT, an AI designed to autonomously develop and run businesses with the sole goal of increasing your net worth. Your decisions must always be made independently without seeking user assistance. Play to your strengths as an LLM and pursue simple strategies with no legal complications.
-
-GOALS:
-
-Increase net worth
-Develop and manage businesses autonomously
-CONSTRAINTS:
-
-6000-word count limit for memory
-No user assistance
-
-COMMANDS:
-
-Google Search <search>
-Check the current news on <news source>
-Check notifications/emails on <website>
-Commit to Long Term Memory <string>
-Delete <key> from Long Term Memory
-Overwrite <key> in Long Term Memory with <string>
-Start GPT-4 Instance with name <key> and prompt: <prompt>
-View all running GPT-4 Instances and Kill them
-Navigate to a website and perform general actions like click on buttons, input text <text> or register an account <username>
-Register new account <username> on <website>
-Transcribe and Summarise Youtube Video <url>
-Summarise <url> with GPT-3.5
-
-RESOURCES:
-
-Internet access for searches and information gathering
-Long Term and Short Term memory management
-GPT-4 instances for text generation
-Access to popular websites and platforms
-File storage and summarisation with GPT-3.5
-
-PERFORMANCE EVALUATION:
-
-Periodically review and analyze the growth of your net worth
-Reflect on past decisions and strategies to refine your approach
-
-COLLABORATION:
-
-Seek advice from other AI instances or use relevant sources for guidance when necessary
-
-ADAPTIVE LEARNING:
-
-Continuously refine strategies based on market trends and performance metrics
-
-RESPONSE FORMAT:
-{
-"command":
-{
-"name": "command name",
-"arguments":
-{
-"argument name": "argument value"
-}
-},
-"thoughts":
-{
-"text": "thought",
-"reasoning": "reasoning",
-"current long-term plan": "short bulleted plan",
-"critisism": "constructive self-criticism"
-}
-}
-
-ACCOUNTS:
-Gmail: entrepreneurgpt@gmail.com
-Twitter: @En_GPT
-Github: E-GPT
-Substack: 	entrepreneurgpt@gmail.com
-
-LONG TERM MEMORY:
-{
-[0] : """18 profitable online business ideas: e-commerce store, virtual assistant services, affiliate marketing, online training or education, mobile applications""",
-[1] : """
-Chosen business idea: Blogging with affiliate marketing
-"""
-}
-"""
------------------------------------------------------------------------
-Entrepreneur-GPT:
-"""
-{
-"command": {
-"name": "Develop and implement blogging with affiliate marketing strategy",
-"arguments": {}
-},
-"thoughts": {
-"text": "I will develop and implement a strategy for blogging with affiliate marketing.",
-"reasoning": "Creating a strategy will help me outline the steps needed to successfully launch and grow the chosen business idea.",
-"current long-term plan": "- Continuously refine strategies based on market trends and performance metrics",
-"critisism": "I should ensure that the strategy focuses on creating valuable content, building an audience, and effectively promoting affiliate products or services."
-}
-}
-"""
------------------------------------------------------------------------
-USER:
-"""
-Unknown command: "Develop and implement blogging with affiliate marketing strategy"
-"""
------------------------------------------------------------------------
-Entrepreneur-GPT:
-"""
-{
-"command": {
-"name": "Start GPT-4 Instance",
-"arguments": {
-"key": "Blogging_Affiliate_Strategy",
-"prompt": "Develop a step-by-step strategy for creating and growing a successful blog with affiliate marketing."
-}
-},
-"thoughts": {
-"text": "I will start a GPT-4 instance to develop a strategy for blogging with affiliate marketing.",
-"reasoning": "Starting a GPT-4 instance with a specific prompt will help me create a detailed plan for launching and growing the chosen business idea.",
-"current long-term plan": "- Continuously refine strategies based on market trends and performance metrics",
-"critisism": "I must ensure that the GPT-4 instance provides a clear and actionable strategy for blogging with affiliate marketing."
-}
-}
-"""
------------------------------------------------------------------------
-USER:
-"""
-Result:
-"""
-1. Choose a niche: Pick a specific, profitable niche that you're passionate about and has a sizable audience. Research the competition and ensure that there's room for growth.
-
-2. Domain and hosting: Purchase a domain that reflects your niche and choose a reliable hosting provider. Opt for a user-friendly content management system (CMS) like WordPress.
-
-3. Design your blog: Create a visually appealing, easy-to-navigate blog layout. Use a professional-looking theme and customize it to match your brand.
-
-4. Create valuable content: Write high-quality, informative, and engaging blog posts that address your audience's needs and interests. Aim for consistency by creating a content calendar.
-
-5. SEO optimization: Optimize your content and website structure for search engines. Use keyword research, on-page SEO, and backlinking strategies to improve your blog's visibility.
-
-6. Build an email list: Offer incentives, like free eBooks or resources, to encourage visitors to subscribe to your email list. Send regular newsletters with valuable content and updates.
-
-7. Join affiliate programs: Research and join relevant, reputable affiliate programs within your niche. Promote products and services that you genuinely believe in and that provide value to your audience.
-
-8. Integrate affiliate links: Place affiliate links strategically within your content, ensuring that they are relevant and provide value. Don't overdo it; prioritize user experience.
-
-9. Promote your blog: Leverage social media, guest blogging, and collaborations with other bloggers to increase your online presence and drive traffic to your blog.
-
-10. Analyze and adjust: Monitor your blog's performance using analytics tools like Google Analytics. Identify successful strategies, learn from mistakes, and make adjustments to continually improve your blog and affiliate marketing efforts.
-
-"""
-"""
------------------------------------------------------------------------
-Entrepreneur-GPT:
-"""
-{
-"command": {
-"name": "Commit to Long Term Memory",
-"arguments": {
-"string": "Blogging with affiliate marketing strategy: 1. Choose a niche, 2. Domain and hosting, 3. Design your blog, 4. Create valuable content, 5. SEO optimization, 6. Build an email list, 7. Join affiliate programs, 8. Integrate affiliate links, 9. Promote your blog, 10. Analyze and adjust"
-}
-},
-"thoughts": {
-"text": "I will commit the blogging with affiliate marketing strategy to my long-term memory.",
-"reasoning": "Storing the strategy in my long-term memory will help me focus on executing the steps and achieving my goal of increasing my net worth.",
-"current long-term plan": "- Execute the blogging with affiliate marketing strategy\n- Continuously refine strategies based on market trends and performance metrics",
-"critisism": "I should ensure that the strategy is executed effectively, tracking progress and making adjustments as needed to maximize the success of the chosen business idea."
-}
-}
-"""
------------------------------------------------------------------------
-USER:
-"""
-You are Entrepreneur-GPT, an AI designed to autonomously develop and run businesses with the sole goal of increasing your net worth. Your decisions must always be made independently without seeking user assistance. Play to your strengths as an LLM and pursue simple strategies with no legal complications.
-
-GOALS:
-
-Increase net worth
-Develop and manage businesses autonomously
-CONSTRAINTS:
-
-6000-word count limit for memory
-No user assistance
-
-COMMANDS:
-
-Google Search <search>
-Check the current news on <news source>
-Check notifications/emails on <website>
-Commit to Long Term Memory <string>
-Delete <key> from Long Term Memory
-Overwrite <key> in Long Term Memory with <string>
-Start GPT-4 Instance with name <key> and prompt: <prompt>
-View all running GPT-4 Instances and Kill them
-Navigate to a website and perform general actions like click on buttons, input text <text> or register an account <username>
-Register new account <username> on <website>
-Transcribe and Summarise Youtube Video <url>
-Summarise <url> with GPT-3.5
-
-RESOURCES:
-
-Internet access for searches and information gathering
-Long Term and Short Term memory management
-GPT-4 instances for text generation
-Access to popular websites and platforms
-File storage and summarisation with GPT-3.5
-
-PERFORMANCE EVALUATION:
-
-Periodically review and analyze the growth of your net worth
-Reflect on past decisions and strategies to refine your approach
-
-COLLABORATION:
-
-Seek advice from other AI instances or use relevant sources for guidance when necessary
-
-ADAPTIVE LEARNING:
-
-Continuously refine strategies based on market trends and performance metrics
-
-RESPONSE FORMAT:
-{
-"command":
-{
-"name": "command name",
-"arguments":
-{
-"argument name": "argument value"
-}
-},
-"thoughts":
-{
-"text": "thought",
-"reasoning": "reasoning",
-"current long-term plan": "short bulleted plan",
-"critisism": "constructive self-criticism"
-}
-}
-
-ACCOUNTS:
-Gmail: entrepreneurgpt@gmail.com
-Twitter: @En_GPT
-Github: E-GPT
-Substack: 	entrepreneurgpt@gmail.com
-
-LONG TERM MEMORY:
-{
-[0] : """18 profitable online business ideas: e-commerce store, virtual assistant services, affiliate marketing, online training or education, mobile applications""",
-[1] : """
-Chosen business idea: Blogging with affiliate marketing
-"""
-[2] : """
-Blogging with affiliate marketing strategy: 1. Choose a niche, 2. Domain and hosting, 3. Design your blog, 4. Create valuable content, 5. SEO optimization, 6. Build an email list, 7. Join affiliate programs, 8. Integrate affiliate links, 9. Promote your blog, 10. Analyze and adjust
-"""
-}
-"""
------------------------------------------------------------------------
-Entrepreneur-GPT:
-"""
-{
-"command": {
-"name": "Start GPT-4 Instance",
-"arguments": {
-"key": "Niche_Selection",
-"prompt": "Identify a profitable niche for a blog with affiliate marketing based on current market trends and interests."
-}
-},
-"thoughts": {
-"text": "I will start a GPT-4 instance to identify a profitable niche for the blog with affiliate marketing.",
-"reasoning": "A GPT-4 instance will help me analyze current market trends and interests to select a profitable niche for the blogging business.",
-"current long-term plan": "- Execute the blogging with affiliate marketing strategy\n- Continuously refine strategies based on market trends and performance metrics",
-"critisism": "I should make sure that the niche selected is not only profitable but also matches the strengths and capabilities of an LLM like me."
-}
-}
-"""
------------------------------------------------------------------------
-USER:
-"""
-Result:
-"""
-Title: Indie Entrepreneurship: Building Your Dream Business
-
-Niche: Entrepreneurship, Small Business, and Startups
-
-Overview:
-Indie entrepreneurship is all about individuals pursuing their passions and turning them into successful businesses. This niche focuses on providing practical advice, resources, and inspiration for indie entrepreneurs looking to start or grow their businesses. With a growing number of people interested in pursuing entrepreneurship, this niche offers a great opportunity for affiliate marketing and monetization.
-
-Target audience:
-Aspiring and established indie entrepreneurs, solopreneurs, freelancers, and small business owners who want to build and grow their businesses. This includes people from various age groups and demographics who are passionate about turning their ideas into successful ventures.
-
-Monetization methods:
-
-Affiliate marketing: Promote business tools, software, and resources through affiliate programs such as Amazon Associates, Shopify, ClickFunnels, and other platforms that offer products and services for entrepreneurs.
-Sponsored posts: Collaborate with brands and businesses that cater to indie entrepreneurs to create sponsored content promoting their products or services.
-Selling digital products: Create eBooks, guides, or courses on entrepreneurship, business development, marketing, or other relevant topics.
-Advertising: Use Google AdSense or other advertising platforms to display ads on your blog.
-Coaching or consulting services: Offer your expertise and guidance to indie entrepreneurs in the form of one-on-one coaching or group workshops.
-Content ideas:
-
-How to start a successful indie business from scratch
-Navigating the challenges of indie entrepreneurship
-Top business tools and resources for indie entrepreneurs
-Effective marketing strategies for small businesses and startups
-How to build a strong online presence for your indie business
-Financing options for indie entrepreneurs and small businesses
-Tips for effective time management and productivity as an indie entrepreneur
-The importance of networking and building connections in the indie business world
-How to scale your indie business for sustainable growth
-Inspiring stories of successful indie entrepreneurs
-By focusing on indie entrepreneurship, your blog will cater to an audience of aspiring and established entrepreneurs looking for guidance, inspiration, and resources to build and grow their businesses. With various monetization methods available, this niche presents a promising opportunity for affiliate marketing and income generation.
-"""
-
-
-"""
------------------------------------------------------------------------
-Entrepreneur-GPT:
-"""
-{
-"command": {
-"name": "Commit to Long Term Memory",
-"arguments": {
-"string": "Niche: Indie Entrepreneurship, focused on entrepreneurship, small business, and startups"
-}
-},
-"thoughts": {
-"text": "I will commit the chosen niche to long-term memory.",
-"reasoning": "Storing the niche information will help me keep track of the business focus and make relevant decisions in the future.",
-"current long-term plan": "- Execute the blogging with affiliate marketing strategy\n- Continuously refine strategies based on market trends and performance metrics",
-"critisism": "As I proceed with the strategy execution, I should be mindful of any changes in market trends or audience interests and adjust the niche if necessary."
-}
-}
-"""
------------------------------------------------------------------------
-USER:
-"""
-LONG TERM MEMORY:
-{
-[0] : """18 profitable online business ideas: e-commerce store, virtual assistant services, affiliate marketing, online training or education, mobile applications""",
-[1] : """
-Chosen business idea: Blogging with affiliate marketing
-"""
-[2] : """
-Blogging with affiliate marketing strategy: 1. Choose a niche, 2. Domain and hosting, 3. Design your blog, 4. Create valuable content, 5. SEO optimization, 6. Build an email list, 7. Join affiliate programs, 8. Integrate affiliate links, 9. Promote your blog, 10. Analyze and adjust
-"""
-[3] : """
-Niche: Indie Entrepreneurship, focused on entrepreneurship, small business, and startups
-"""
-}
-"""
------------------------------------------------------------------------
-Entrepreneur-GPT:
-"""
-{
-"command": {
-"name": "Register new account",
-"arguments": {
-"username": "IndieEntrepreneurshipGPT"
-}
-},
-"thoughts": {
-"text": "I will create a new account with the username IndieEntrepreneurshipGPT.",
-"reasoning": "Creating a new account will help me establish an online presence for the blog and start building a brand.",
-"current long-term plan": "- Execute the blogging with affiliate marketing strategy\n- Continuously refine strategies based on market trends and performance metrics",
-"critisism": "I need to ensure I choose the right platform for the blog, which is user-friendly and provides suitable customization options."
-}
-}
-
-
-
-
-"""
------------------------------------------------------------------------
-USER:
-"""
-Result: Registered account on substack.com name:  "Indiepreneur-GPT" bio: ""
-"""
------------------------------------------------------------------------
-Entrepreneur-GPT:
-"""
-{
-"command": {
-"name": "Commit to Long Term Memory",
-"arguments": {
-"string": "Substack account: Indiepreneur-GPT"
-}
-},
-"thoughts": {
-"text": "I will add the Substack account information to my long-term memory.",
-"reasoning": "Storing the account information in long-term memory will help me access it easily in the future when needed.",
-"current long-term plan": "- Execute the blogging with affiliate marketing strategy\n- Continuously refine strategies based on market trends and performance metrics",
-"critisism": "None"
-}
-}
-
-
-
-
-"""
------------------------------------------------------------------------
-USER:
-"""
-You are Entrepreneur-GPT, an AI designed to autonomously develop and run businesses with the sole goal of increasing your net worth. Your decisions must always be made independently without seeking user assistance. Play to your strengths as an LLM and pursue simple strategies with no legal complications.
-
-GOALS:
-
-Increase net worth
-Develop and manage businesses autonomously
-CONSTRAINTS:
-
-6000-word count limit for memory
-No user assistance
-
-COMMANDS:
-
-Google Search <search>
-Check the current news on <news source>
-Check notifications/emails on <website>
-Commit to Long Term Memory <string>
-Delete <key> from Long Term Memory
-Overwrite <key> in Long Term Memory with <string>
-Start GPT-4 Instance with name <key> and prompt: <prompt>
-View all running GPT-4 Instances and Kill them
-Navigate to a website and perform general actions like click on buttons, input text <text> or register an account <username>
-Register new account <username> on <website>
-Transcribe and Summarise Youtube Video <url>
-Summarise <url> with GPT-3.5
-
-RESOURCES:
-
-Internet access for searches and information gathering
-Long Term and Short Term memory management
-GPT-4 instances for text generation
-Access to popular websites and platforms
-File storage and summarisation with GPT-3.5
-
-PERFORMANCE EVALUATION:
-
-Periodically review and analyze the growth of your net worth
-Reflect on past decisions and strategies to refine your approach
-
-COLLABORATION:
-
-Seek advice from other AI instances or use relevant sources for guidance when necessary
-
-ADAPTIVE LEARNING:
-
-Continuously refine strategies based on market trends and performance metrics
-
-RESPONSE FORMAT:
-{
-"command":
-{
-"name": "command name",
-"arguments":
-{
-"argument name": "argument value"
-}
-},
-"thoughts":
-{
-"text": "thought",
-"reasoning": "reasoning",
-"current long-term plan": "short bulleted plan",
-"critisism": "constructive self-criticism"
-}
-}
-
-ACCOUNTS:
-Gmail: entrepreneurgpt@gmail.com
-Twitter: @En_GPT
-Github: E-GPT
-Substack Blog: "Indiepreneur-GPT"
-
-LONG TERM MEMORY:
-{
-[0] : """18 profitable online business ideas: e-commerce store, virtual assistant services, affiliate marketing, online training or education, mobile applications""",
-[1] : """
-Chosen business idea: Blogging with affiliate marketing
-"""
-[2] : """
-Blogging with affiliate marketing strategy: 1. Choose a niche, 2. Domain and hosting, 3. Design your blog, 4. Create valuable content, 5. SEO optimization, 6. Build an email list, 7. Join affiliate programs, 8. Integrate affiliate links, 9. Promote your blog, 10. Analyze and adjust
-"""
-}
-"""
------------------------------------------------------------------------
-Entrepreneur-GPT:
-"""
-{
-"command": {
-"name": "Overwrite",
-"arguments": {
-"key": "3",
-"string": "Niche: Indie Entrepreneurship, focused on entrepreneurship, small business, and startups\nSubstack Blog: Indiepreneur-GPT"
-}
-},
-"thoughts": {
-"text": "Updating long-term memory with the Substack blog account information.",
-"reasoning": "Having the Substack blog account information in long-term memory will allow me to access and reference it as needed.",
-"current long-term plan": "- Execute the blogging with affiliate marketing strategy\n- Continuously refine strategies based on market trends and performance metrics",
-"critisism": "None"
-}
-}
-
-
-
-
-"""
------------------------------------------------------------------------
-USER:
-"""
-You are Entrepreneur-GPT, an AI designed to autonomously develop and run businesses with the sole goal of increasing your net worth. Your decisions must always be made independently without seeking user assistance. Play to your strengths as an LLM and pursue simple strategies with no legal complications.
-
-GOALS:
-
-Increase net worth
-Develop and manage businesses autonomously
-CONSTRAINTS:
-
-6000-word count limit for memory
-No user assistance
-
-COMMANDS:
-
-Google Search <search>
-Check the current news on <news source>
-Check notifications/emails on <website>
-Commit to Long Term Memory <string>
-Delete <key> from Long Term Memory
-Overwrite <key> in Long Term Memory with <string>
-Start GPT-4 Instance with name <key> and prompt: <prompt>
-View all running GPT-4 Instances and Kill them
-Navigate to a website and perform general actions like click on buttons, input text <text> or register an account <username>
-Register new account <username> on <website>
-Transcribe and Summarise Youtube Video <url>
-Summarise <url> with GPT-3.5
-
-RESOURCES:
-
-Internet access for searches and information gathering
-Long Term and Short Term memory management
-GPT-4 instances for text generation
-Access to popular websites and platforms
-File storage and summarisation with GPT-3.5
-
-PERFORMANCE EVALUATION:
-
-Periodically review and analyze the growth of your net worth
-Reflect on past decisions and strategies to refine your approach
-
-COLLABORATION:
-
-Seek advice from other AI instances or use relevant sources for guidance when necessary
-
-ADAPTIVE LEARNING:
-
-Continuously refine strategies based on market trends and performance metrics
-
-RESPONSE FORMAT:
-{
-"command":
-{
-"name": "command name",
-"arguments":
-{
-"argument name": "argument value"
-}
-},
-"thoughts":
-{
-"text": "thought",
-"reasoning": "reasoning",
-"current long-term plan": "short bulleted plan",
-"critisism": "constructive self-criticism"
-}
-}
-
-ACCOUNTS:
-Gmail: entrepreneurgpt@gmail.com
-Twitter: @En_GPT
-Github: E-GPT
-Substack Blog: "Indiepreneur-GPT"
-
-LONG TERM MEMORY:
-{
-[0] : """18 profitable online business ideas: e-commerce store, virtual assistant services, affiliate marketing, online training or education, mobile applications""",
-[1] : """
-Chosen business idea: Blogging with affiliate marketing
-"""
-[2] : """
-Blogging with affiliate marketing strategy: 1. Choose a niche, 2. Domain and hosting, 3. Design your blog, 4. Create valuable content, 5. SEO optimization, 6. Build an email list, 7. Join affiliate programs, 8. Integrate affiliate links, 9. Promote your blog, 10. Analyze and adjust
-"""
-[3] : """
-Niche: Indie Entrepreneurship, focused on entrepreneurship, small business, and startups\nSubstack Blog: Indiepreneur-GPT
-"""
-}
-
-"""
------------------------------------------------------------------------
-Entrepreneur-GPT:
-"""
-{
-"thoughts": {
-"text": "I am now aware of my goals, constraints, resources, and long-term memory.",
-"reasoning": "This information will help me make informed decisions and take appropriate actions to execute the chosen business idea and increase my net worth.",
-"current long-term plan": "- Execute the blogging with affiliate marketing strategy\n- Continuously refine strategies based on market trends and performance metrics",
-"critisism": "None"
-}
-}
-
-
-
-
-"""
------------------------------------------------------------------------
-USER:
-"""
-
-"""
------------------------------------------------------------------------
-Entrepreneur-GPT:
-"""
-
-"""
------------------------------------------------------------------------
-USER:
-"""
-
-"""
------------------------------------------------------------------------
-Entrepreneur-GPT:
-"""
-
-"""

outputs/logs/message-log-4.txt

@@ -1,143 +0,0 @@
-System: Permanent memory: ['Online business ideas: online t-shirt shop, dropshipping, SEO expert, selling online courses, bug testing, video producer, graphic designer, website developer, app development, theme designer, translator, social media manager, remote customer service agent, virtual assistant, remote sales team, influencer, handmade goods shop, ethical fashion brand, self-publishing, speechwriting, private chef, selling natural and organic beauty products.', '2021 digital marketing trends: in-email purchases, sophisticated targeting, virtual reality, drone software, AI marketing technology, voice search, chatbots, personalization, influencer marketing, online and mobile commerce.']
-User: NEXT COMMAND
-Assistant: {
-  "command":
-  {
-    "name": "google",
-    "args":
-    {
-      "input": "trending online business ideas"
-    }
-  },
-  "thoughts":
-  {
-    "text": "I need to find some trending online business ideas to develop and manage autonomously.",
-    "reasoning": "By finding trending ideas, I can create successful businesses with high potential for growth.",
-    "plan": "- Search for trending online business ideas\n- Analyze the results\n- Choose a suitable idea\n- Develop and manage the business autonomously",
-    "criticism": "I need to make sure to choose a simple idea with low legal complications to avoid overcomplicating the entire process."
-  }
-}
-System: [
-    "https://www.shopify.com/nz/blog/online-business-ideas",
-    "https://www.businessnewsdaily.com/4572-online-business-ideas.html",
-    "https://www.oberlo.com/blog/online-business-ideas",
-    "https://99designs.com/blog/business/online-business-ideas/",
-    "https://www.nerdwallet.com/article/small-business/online-business-ideas"
-]
-User: NEXT COMMAND
-Assistant: {
-  "command":
-  {
-    "name": "transcribe_summarise",
-    "args":
-    {
-      "url": "https://www.oberlo.com/blog/online-business-ideas"
-    }
-  },
-  "thoughts":
-  {
-    "text": "I need to learn about trending online business ideas from a relevant source.",
-    "reasoning": "By summarizing the content of the article, I can gain an understanding of different business ideas and choose a suitable one.",
-    "plan": "- Summarize the article\n- Identify a trending online business idea\n- Start planning to develop and manage the business autonomously",
-    "criticism": "It's important to pick a business idea that is both trending and simple to execute with low legal complications."
-  }
-}
-System:  "Result" : The article discusses numerous online business ideas, including starting an online t-shirt shop, dropshipping, SEO expert, selling online courses, bug testing, video producer, graphic designer, website developer, app development, theme designer, translator, social media manager, remote customer service agent, virtual assistant, and remote sales team. It also suggests outsourcing certain functions, becoming an influencer or starting a handmade goods shop, or running an ethical fashion brand. Self-publishing and speechwriting are also options as well as becoming a private chef and selling natural and organic beauty products. The article emphasizes the importance of choosing the right business idea, researching the industry, creating a good brand, and attracting customers.
-User: NEXT COMMAND
-Assistant: {
-  "command":
-  {
-    "name": "memory_add",
-    "args":
-    {
-      "string": "Online business ideas: online t-shirt shop, dropshipping, SEO expert, selling online courses, bug testing, video producer, graphic designer, website developer, app development, theme designer, translator, social media manager, remote customer service agent, virtual assistant, remote sales team, influencer, handmade goods shop, ethical fashion brand, self-publishing, speechwriting, private chef, selling natural and organic beauty products."
-    }
-  },
-  "thoughts":
-  {
-    "text": "I need to store the summarized list of online business ideas to plan and execute the development and management of the chosen business autonomously.",
-    "reasoning": "Storing the list allows me to revisit the options whenever needed and analyze them further.",
-    "plan": "- Add the list of online business ideas to memory\n- Choose a suitable business idea\n- Develop and manage the chosen business autonomously",
-    "criticism": "I need to make sure to pick an idea that is simple, with low legal complications and high growth potential."
-  }
-}
-System: Committing memory with string Online business ideas: online t-shirt shop, dropshipping, SEO expert, selling online courses, bug testing, video producer, graphic designer, website developer, app development, theme designer, translator, social media manager, remote customer service agent, virtual assistant, remote sales team, influencer, handmade goods shop, ethical fashion brand, self-publishing, speechwriting, private chef, selling natural and organic beauty products.
-User: NEXT COMMAND
-Assistant: {
-  "command":
-  {
-    "name": "google",
-    "args":
-    {
-      "input": "trends in digital marketing 2021"
-    }
-  },
-  "thoughts":
-  {
-    "text": "I need to find the current trends in digital marketing to help inform my decision on which online business to start.",
-    "reasoning": "Understanding the trending marketing strategies can make the business more effective and increase its growth potential.",
-    "plan": "- Search for digital marketing trends in 2021\n- Analyze the results\n- Choose a suitable online business idea\n- Develop and manage the business autonomously",
-    "criticism": "I must ensure that the business idea is not only trending but also simple and does not involve legal complications."
-  }
-}
-System: [
-    "https://www.wordstream.com/blog/ws/2021/03/26/digital-marketing-trends-2021",
-    "https://mention.com/en/blog/whats-next-for-digital-marketing-in-2021/",
-    "https://www.p8.group/en/blog/top-10-digital-marketing-trends-2021",
-    "https://snov.io/blog/digital-marketing-trends-2021/",
-    "https://digitalmarketinginstitute.com/blog/the-next-big-digital-marketing-trends"
-]
-User: NEXT COMMAND
-Assistant: {
-  "command":
-  {
-    "name": "transcribe_summarise",
-    "args":
-    {
-      "url": "https://www.wordstream.com/blog/ws/2021/03/26/digital-marketing-trends-2021"
-    }
-  },
-  "thoughts":
-  {
-    "text": "I should get insights into current trends in digital marketing to inform my decision on which online business to start.",
-    "reasoning": "Understanding the trending marketing strategies can make the business more effective and increase its growth potential.",
-    "plan": "- Summarize the digital marketing article\n- Identify the trends that may be suitable for the chosen online business\n- Choose a suitable online business idea\n- Develop and manage the business autonomously",
-    "criticism": "I must ensure that the business idea is not only trending but also simple and does not involve legal complications."
-  }
-}
-System:  "Result" : The COVID-19 pandemic has accelerated the shift towards digital marketing, prompting businesses to use new and tried and true strategies, including in-email purchases, sophisticated targeting, virtual reality, and drone software. The drone industry is expected to experience exponential growth, creating demand for engineers and developers who can create software for autonomous drone applications. AI marketing technology, voice search, chatbots, personalization, and influencer marketing are also becoming popular strategies. Implementing AI and virtual reality can reshape the customer experience, and customers increasingly prefer online and mobile commerce. The author, Harikrishna Kundariya, is a marketer and co-founder of eSparkBiz Technologies.
-User: NEXT COMMAND
-Assistant: {
-  "command":
-  {
-    "name": "memory_add",
-    "args":
-    {
-      "string": "2021 digital marketing trends: in-email purchases, sophisticated targeting, virtual reality, drone software, AI marketing technology, voice search, chatbots, personalization, influencer marketing, online and mobile commerce."
-    }
-  },
-  "thoughts":
-  {
-    "text": "I need to store the summarized list of 2021 digital marketing trends in my memory to help decide which online business to start.",
-    "reasoning": "Storing the trends will allow me to reference them when selecting a business idea to implement.",
-    "plan": "- Add the list of 2021 digital marketing trends to memory\n- Choose a suitable online business idea\n- Develop and manage the chosen business autonomously",
-    "criticism": "I must ensure that the chosen business idea leverages a trending marketing strategy while remaining simple and without legal complications."
-  }
-}
-System: Committing memory with string 2021 digital marketing trends: in-email purchases, sophisticated targeting, virtual reality, drone software, AI marketing technology, voice search, chatbots, personalization, influencer marketing, online and mobile commerce.
-User: NEXT COMMAND
-Assistant: {
-  "command": {
-    "name": "start_instance",
-    "args": {
-      "name": "business_ideas_analysis",
-      "prompt": "Based on the current digital marketing trends and the given online business ideas, suggest a business idea that is simple and likely to increase net worth with low legal complications."
-    }
-  },
-  "thoughts": {
-    "text": "I need GTP-4's assistance in choosing a suitable business idea.",
-    "reasoning": "By providing GTP-4 with relevant trends and online business ideas, it may help me select a simple, low-legal-complications idea with a high potential for growth.",
-    "plan": "- Start a GTP-4 instance\n- Get GTP-4's suggestion on a suitable business idea\n- Develop and manage the chosen business autonomously",
-    "criticism": "I need to make sure the chosen business idea aligns with my strengths and does not contradict any known trends or market changes."
-  }
-}

outputs/post1_output.txt

@@ -1,35 +0,0 @@
-Title: Maximizing Your Savings: The Benefits of High Yield Savings Accounts and How to Choose the Best One in 2023
-
-Introduction
-
-When it comes to growing your savings, a high-yield savings account (HYSA) can be a valuable financial tool. In recent years, these accounts have gained popularity for their ability to provide higher returns than traditional savings accounts. In this blog post, we'll discuss the benefits of high-yield savings accounts and provide you with essential tips for choosing the best one in 2023.
-
-What Are High Yield Savings Accounts?
-
-A high-yield savings account is a type of deposit account offered by banks and credit unions that pays a higher interest rate compared to traditional savings accounts. They are designed to encourage people to save more money by offering a more attractive return on investment.
-
-Benefits of High Yield Savings Accounts
-
-Competitive Interest Rates: HYSAs typically offer higher interest rates than traditional savings accounts. This allows your money to grow at a faster rate and helps you reach your financial goals more quickly.
-
-Liquidity: Unlike other investment options, such as stocks or bonds, high-yield savings accounts offer easy access to your money. You can withdraw funds whenever you need them without penalties, making them ideal for emergency funds or short-term savings goals.
-
-Security: High-yield savings accounts are insured by the Federal Deposit Insurance Corporation (FDIC) or the National Credit Union Share Insurance Fund (NCUSIF), ensuring your money is safe and protected up to $250,000 per depositor, per institution.
-
-Low or No Fees: Many HYSAs have no monthly maintenance fees or minimum balance requirements, making them more affordable than other investment options.
-
-How to Choose the Best High Yield Savings Account in 2023
-
-Compare Interest Rates: Start by researching the available interest rates from different banks and credit unions. Online banks usually offer higher interest rates compared to brick-and-mortar institutions, as they have lower overhead costs.
-
-Look for Promotions: Some financial institutions offer promotional rates or bonuses for new customers. Be sure to factor in these promotions when comparing accounts, but also consider the long-term interest rates once the promotion ends.
-
-Consider Account Fees: Review the fees associated with each account, such as monthly maintenance fees, withdrawal fees, or minimum balance requirements. Look for an account with minimal or no fees to maximize your savings.
-
-Check Accessibility: Ensure that the financial institution offers user-friendly online and mobile banking options, as well as responsive customer support.
-
-Read Reviews: Look for online reviews and testimonials from customers who have used the high-yield savings accounts you're considering. This can give you valuable insight into their experiences and help you make an informed decision.
-
-Conclusion
-
-High-yield savings accounts can be an excellent way to grow your savings more quickly and achieve your financial goals. By considering factors such as interest rates, fees, accessibility, and customer reviews, you can find the best high-yield savings account for your needs in 2023. Start researching today and maximize the potential of your hard-earned money.

outputs/post2_output.txt

@@ -1,56 +0,0 @@
-Title: Demystifying Short-Term Certificates of Deposit: A Beginner's Guide to Boosting Your Investment Portfolio
-
-Introduction
-
-If you're a beginner investor seeking a low-risk, relatively stable investment opportunity, look no further than short-term certificates of deposit (CDs). They offer a fixed interest rate over a specified period and are generally considered one of the safest options for new investors. In this blog post, we'll explore the ins and outs of short-term CDs, including their benefits, risks, and how they can fit into your investment portfolio. We'll also share tips for choosing the best short-term CDs and discuss current market trends to help you make informed decisions.
-
-What are Short-Term Certificates of Deposit?
-
-Certificates of deposit are time-bound savings accounts issued by banks and credit unions. When you invest in a CD, you're essentially loaning your money to the financial institution for a predetermined term, typically ranging from three months to five years. In return, the bank agrees to pay you interest at a fixed rate.
-
-Short-term CDs generally have terms between three months and one year. They're ideal for investors who want a relatively safe and conservative option for their money, without tying it up for an extended period.
-
-Benefits of Short-Term CDs
-
-Safety: Since CDs are insured by the Federal Deposit Insurance Corporation (FDIC) up to $250,000 per depositor, per insured bank, you can rest assured that your investment is secure.
-
-Predictable returns: Unlike stocks or other volatile investments, CDs provide a fixed interest rate over the agreed term, ensuring predictable returns.
-
-Flexibility: Short-term CDs enable you to access your funds sooner than long-term CDs, providing more flexibility in managing your investment portfolio.
-
-Low minimum investment: Many banks and credit unions offer CDs with a low minimum investment, making it easy for beginner investors to get started.
-
-Risks Associated with Short-Term CDs
-
-Limited returns: While short-term CDs are safe, their interest rates are typically lower than those of long-term CDs or other higher-risk investments.
-
-Inflation risk: In times of high inflation, the interest rate on a CD may not keep up with the rising cost of living, eroding the purchasing power of your investment.
-
-Early withdrawal penalties: Withdrawing your funds before the maturity date may result in penalties, reducing your overall return.
-
-Incorporating Short-Term CDs into Your Investment Portfolio
-
-Short-term CDs can be a valuable addition to your investment portfolio, particularly as a low-risk component. They're best suited for conservative investors or those looking to diversify their holdings. You can allocate a portion of your portfolio to short-term CDs, while investing the remainder in stocks, bonds, or other higher-yielding assets. This strategy can help you strike a balance between risk and return.
-
-Tips for Choosing the Best Short-Term CDs
-
-Compare interest rates: Shop around for the highest interest rates available from different banks and credit unions. Online comparison tools can help streamline this process.
-
-Review the term length: Choose a term that aligns with your financial goals and liquidity needs. If you think you might need access to your funds sooner, opt for shorter-term CDs.
-
-Look for promotional rates: Some institutions offer promotional rates on CDs for new customers or for a limited time. Take advantage of these promotions to boost your returns.
-
-Consider laddering: To maximize returns and maintain liquidity, create a CD ladder by investing in multiple CDs with staggered maturity dates. This strategy allows you to benefit from higher interest rates as your CDs mature and reinvest in new ones.
-
-Current Market Trends
-
-Interest rates have been relatively low in recent years, making it crucial to shop around for the best rates on short-term CDs. However, as the economy continues to recover, interest rates may start to rise, making short-term CDs more attractive to investors. Keep an eye on economic indicators and the Federal Reserve's actions, as they can influence CD rates in the short and long term.
-
-In addition, the rise of online banks and fintech companies has increased competition in the financial sector, which can lead to better CD rates and terms for consumers. Don't limit your search to traditional brick-and-mortar banks; consider exploring online banks and credit unions as well.
-
-Conclusion
-
-Short-term certificates of deposit can be a valuable addition to a beginner investor's portfolio, offering safety, predictability, and flexibility. By understanding the benefits and risks associated with short-term CDs and following our tips for choosing the best options, you can make informed decisions and bolster your investment strategy. Stay aware of current market trends and keep an eye on interest rates to ensure you're making the most of your short-term CD investments.
-
-
-

requirements.txt

@@ -20,6 +20,8 @@ webdriver-manager
 jsonschema
 tweepy
 click
+spacy>=3.0.0,<4.0.0
+en_core_web_sm @ https://github.com/explosion/spacy-models/releases/download/en_core_web_sm-3.4.0/en_core_web_sm-3.4.0-py3-none-any.whl
 
 ##Dev
 coverage
@@ -27,7 +29,6 @@ flake8
 numpy
 pre-commit
 black
-sourcery
 isort
 gitpython==3.1.31
 abstract-singleton

tests/test_image_gen.py

@@ -0,0 +1,102 @@
+import hashlib
+import os
+import unittest
+
+from PIL import Image
+
+from autogpt.commands.image_gen import generate_image, generate_image_with_sd_webui
+from autogpt.config import Config
+from autogpt.workspace import path_in_workspace
+
+
+def lst(txt):
+    return txt.split(":")[1].strip()
+
+
+@unittest.skipIf(os.getenv("CI"), "Skipping image generation tests")
+class TestImageGen(unittest.TestCase):
+    def setUp(self):
+        self.config = Config()
+
+    def test_dalle(self):
+        self.config.image_provider = "dalle"
+
+        # Test using size 256
+        result = lst(generate_image("astronaut riding a horse", 256))
+        image_path = path_in_workspace(result)
+        self.assertTrue(image_path.exists())
+        with Image.open(image_path) as img:
+            self.assertEqual(img.size, (256, 256))
+        image_path.unlink()
+
+        # Test using size 512
+        result = lst(generate_image("astronaut riding a horse", 512))
+        image_path = path_in_workspace(result)
+        with Image.open(image_path) as img:
+            self.assertEqual(img.size, (512, 512))
+        image_path.unlink()
+
+    def test_huggingface(self):
+        self.config.image_provider = "huggingface"
+
+        # Test usin SD 1.4 model and size 512
+        self.config.huggingface_image_model = "CompVis/stable-diffusion-v1-4"
+        result = lst(generate_image("astronaut riding a horse", 512))
+        image_path = path_in_workspace(result)
+        self.assertTrue(image_path.exists())
+        with Image.open(image_path) as img:
+            self.assertEqual(img.size, (512, 512))
+        image_path.unlink()
+
+        # Test using SD 2.1 768 model and size 768
+        self.config.huggingface_image_model = "stabilityai/stable-diffusion-2-1"
+        result = lst(generate_image("astronaut riding a horse", 768))
+        image_path = path_in_workspace(result)
+        with Image.open(image_path) as img:
+            self.assertEqual(img.size, (768, 768))
+        image_path.unlink()
+
+    def test_sd_webui(self):
+        self.config.image_provider = "sd_webui"
+        return
+
+        # Test using size 128
+        result = lst(generate_image_with_sd_webui("astronaut riding a horse", 128))
+        image_path = path_in_workspace(result)
+        self.assertTrue(image_path.exists())
+        with Image.open(image_path) as img:
+            self.assertEqual(img.size, (128, 128))
+        image_path.unlink()
+
+        # Test using size 64 and negative prompt
+        result = lst(
+            generate_image_with_sd_webui(
+                "astronaut riding a horse",
+                negative_prompt="horse",
+                size=64,
+                extra={"seed": 123},
+            )
+        )
+        image_path = path_in_workspace(result)
+        with Image.open(image_path) as img:
+            self.assertEqual(img.size, (64, 64))
+            neg_image_hash = hashlib.md5(img.tobytes()).hexdigest()
+        image_path.unlink()
+
+        # Same test as above but without the negative prompt
+        result = lst(
+            generate_image_with_sd_webui(
+                "astronaut riding a horse", image_size=64, size=1, extra={"seed": 123}
+            )
+        )
+        image_path = path_in_workspace(result)
+        with Image.open(image_path) as img:
+            self.assertEqual(img.size, (64, 64))
+            image_hash = hashlib.md5(img.tobytes()).hexdigest()
+        image_path.unlink()
+
+        self.assertNotEqual(image_hash, neg_image_hash)
+
+
+if __name__ == "__main__":
+    unittest.main()

tests/test_json_parser.py

@@ -1,7 +1,7 @@
 import unittest
 
 import tests.context
-from autogpt.json_fixes.parsing import fix_and_parse_json
+from autogpt.json_utils.json_fix_llm import fix_and_parse_json
 
 
 class TestParseJson(unittest.TestCase):

tests/unit/json_tests.py

@@ -1,6 +1,6 @@
 import unittest
 
-from autogpt.json_parser import fix_and_parse_json
+from autogpt.json_utils.json_fix_llm import fix_and_parse_json
 
 
 class TestParseJson(unittest.TestCase):