任务拆解,悠然自得,自动版本的ChatGPT,AutoGPT自动人工智能AI任务实践(Python3.10)

git clone https://github.com/Significant-Gravitas/Auto-GPT.git

cd Auto-GPT

pip3 install -r requirements.txt

cp .env.template .env

### OPENAI
# OPENAI_API_KEY - OpenAI API Key (Example: my-openai-api-key)
# TEMPERATURE - Sets temperature in OpenAI (Default: 0)
# USE_AZURE - Use Azure OpenAI or not (Default: False)
OPENAI_API_KEY=您的秘钥
TEMPERATURE=0
USE_AZURE=False

docker build -t autogpt .
docker run -it --env-file=./.env -v $PWD/auto_gpt_workspace:/app/auto_gpt_workspace autogpt

python3 -m autogpt --debug

➜  Auto-GPT git:(master) python -m autogpt --debug       
Warning: The file 'AutoGpt.json' does not exist. Local memory would not be saved to a file.
Debug Mode:  ENABLED
Welcome to Auto-GPT!  Enter the name of your AI and its role below. Entering nothing will load defaults.
Name your AI:  For example, 'Entrepreneur-GPT'
AI Name:

AI Name: v3u.cn
v3u.cn here!  I am at your service.
Describe your AI's role:  For example, 'an AI designed to autonomously develop and run businesses with the sole goal of increasing your net worth.'
v3u.cn is:

v3u.cn is: Analyze the contents of this article,the url is https://v3u.cn/a_id_303,and write the result to goal.txt

Enter up to 5 goals for your AI:  For example: Increase net worth, Grow Twitter Account, Develop and manage multiple businesses autonomously'
Enter nothing to load defaults, enter nothing when finished.
Goal 1: 
Using memory of type:  LocalCache

Goal 1: 
Using memory of type:  LocalCache
Using Browser:  chrome
  Token limit: 4000
  Memory Stats: (0, (0, 1536))
  Token limit: 4000
  Send Token Count: 936
  Tokens remaining for response: 3064
  ------------ CONTEXT SENT TO AI ---------------
  System: The current time and date is Mon Apr 17 20:29:37 2023
  
  System: This reminds you of these events from your past:



  
  User: Determine which next command to use, and respond using the format specified above:
  
  ----------- END OF CONTEXT ----------------
Creating chat completion with model gpt-3.5-turbo, temperature 0.0, max_tokens 3064
The JSON object is valid.
 THOUGHTS:  Let's start by browsing the article at https://v3u.cn/a_id_303 to get a better understanding of its contents.
REASONING:  Browsing the article will allow us to analyze its contents and determine the appropriate next steps.
PLAN: 
-  Browse the article
-  Analyze its contents
-  Determine the appropriate next steps
CRITICISM:  None
NEXT ACTION:  COMMAND = browse_website ARGUMENTS = {'url': 'https://v3u.cn/a_id_303', 'question': 'analyze the contents of the article'}
Enter 'y' to authorise command, 'y -N' to run N continuous commands, 'n' to exit program, or enter feedback for ...
Input:y
-=-=-=-=-=-=-= COMMAND AUTHORISED BY USER -=-=-=-=-=-=-= 
[WDM] - Downloading: 100%|████████████████████████████████████████████| 8.04M/8.04M [00:03<00:00, 2.42MB/s]
Text length: 6977 characters
Adding chunk 1 / 1 to memory
Summarizing chunk 1 / 1
Creating chat completion with model gpt-3.5-turbo, temperature 0.0, max_tokens 300
SYSTEM:  Command browse_website returned: Error: This model's maximum context length is 4097 tokens. However, you requested 4339 tokens (4039 in the messages, 300 in the completion). Please reduce the length of the messages or completion.
  Token limit: 4000
  Memory Stats: (2, (2, 1536))
  Token limit: 4000
  Send Token Count: 1472
  Tokens remaining for response: 2528
  ------------ CONTEXT SENT TO AI ---------------
  System: The current time and date is Mon Apr 17 20:30:19 2023
  
  System: This reminds you of these events from your past:
['Assistant Reply: {\n    "thoughts": {\n        "text": "Let\'s start by browsing the article at https://v3u.cn/a_id_303 to get a better understanding of its contents.",\n        "reasoning": "Browsing the article will allow us to analyze its contents and determine the appropriate next steps.",\n        "plan": "- Browse the article\\n- Analyze its contents\\n- Determine the appropriate next steps",\n        "criticism": "None",\n        "speak": "I suggest we start by browsing the article at the given URL to analyze its contents and determine the appropriate next steps."\n    },\n    "command": {\n        "name": "browse_website",\n        "args": {\n            "url": "https://v3u.cn/a_id_303",\n            "question": "analyze the contents of the article"\n        }\n    }\n} \nResult: Command browse_website returned: Error: This model\'s maximum context length is 4097 tokens. However, you requested 4339 tokens (4039 in the messages, 300 in the completion). Please reduce the length of the messages or completion. \nHuman Feedback: GENERATE NEXT COMMAND JSON ']


  
  User: Determine which next command to use, and respond using the format specified above:
  
  Assistant: {
    "thoughts": {
        "text": "Let's start by browsing the article at https://v3u.cn/a_id_303 to get a better understanding of its contents.",
        "reasoning": "Browsing the article will allow us to analyze its contents and determine the appropriate next steps.",
        "plan": "- Browse the article\n- Analyze its contents\n- Determine the appropriate next steps",
        "criticism": "None",
        "speak": "I suggest we start by browsing the article at the given URL to analyze its contents and determine the appropriate next steps."
    },
    "command": {
        "name": "browse_website",
        "args": {
            "url": "https://v3u.cn/a_id_303",
            "question": "analyze the contents of the article"
        }
    }
}
  
  
  User: Determine which next command to use, and respond using the format specified above:
  
  ----------- END OF CONTEXT ----------------
Creating chat completion with model gpt-3.5-turbo, temperature 0.0, max_tokens 2528

这篇文章主要阐释了苹果Mac电脑可以完成机器学习和深度学习任务，并且通过深度学习框架Tensorflow的安装和运行进行了佐证，同时也对Tensorflow的CPU和GPU的两种模型训练模式进行了深度对比和测试。