search

sahbic / profile-gpt

An AI-driven tool to analyze your profile and gain insights into how ChatGPT interprets your personality.
MIT License
180 stars 12 forks source link

I want my credit back. InvalidRequestError: This model's maximum context length is 8192 tokens. However, your messages resulted in 24140 tokens. Please reduce the length of the messages. #6

Open baditaflorin opened 1 year ago

baditaflorin commented 1 year ago 
1/4 The user profile analysis is ready ✅

2/4 The personality test is ready ✅

3/4 The future prediction is ready ✅

InvalidRequestError: This model's maximum context length is 8192 tokens. However, your messages resulted in 24140 tokens. Please reduce the length of the messages.
Traceback:
File "/Users/florin/Documents/GITHUB_PROJECTS/profile-gpt/venv/lib/python3.11/site-packages/streamlit/runtime/scriptrunner/script_runner.py", line 565, in _run_script
    exec(code, module.__dict__)
File "/Users/florin/Documents/GITHUB_PROJECTS/profile-gpt/dashboard.py", line 98, in <module>
    website_data, urls = commands.stalk_user(user_name)
                         ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/Users/florin/Documents/GITHUB_PROJECTS/profile-gpt/utils/commands.py", line 50, in stalk_user
    website_data.append(browse_website(url, f"Extract information about the user {user_name} in a paragraph of 3 sentences."))
                        ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/Users/florin/Documents/GITHUB_PROJECTS/profile-gpt/utils/commands.py", line 32, in browse_website
    summary = get_text_summary(url, question)
              ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/Users/florin/Documents/GITHUB_PROJECTS/profile-gpt/utils/commands.py", line 27, in get_text_summary
    summary = summarize_text(text, question)
              ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/Users/florin/Documents/GITHUB_PROJECTS/profile-gpt/utils/browse.py", line 150, in summarize_text
    summary = create_chat_completion(
              ^^^^^^^^^^^^^^^^^^^^^^^
File "/Users/florin/Documents/GITHUB_PROJECTS/profile-gpt/utils/llm_utils.py", line 14, in create_chat_completion
    response = openai.ChatCompletion.create(
               ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/Users/florin/Documents/GITHUB_PROJECTS/profile-gpt/venv/lib/python3.11/site-packages/openai/api_resources/chat_completion.py", line 25, in create
    return super().create(*args, **kwargs)
           ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/Users/florin/Documents/GITHUB_PROJECTS/profile-gpt/venv/lib/python3.11/site-packages/openai/api_resources/abstract/engine_api_resource.py", line 153, in create
    response, _, api_key = requestor.request(
                           ^^^^^^^^^^^^^^^^^^
File "/Users/florin/Documents/GITHUB_PROJECTS/profile-gpt/venv/lib/python3.11/site-packages/openai/api_requestor.py", line 226, in request
    resp, got_stream = self._interpret_response(result, stream)
                       ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/Users/florin/Documents/GITHUB_PROJECTS/profile-gpt/venv/lib/python3.11/site-packages/openai/api_requestor.py", line 620, in _interpret_response
    self._interpret_response_line(
File "/Users/florin/Documents/GITHUB_PROJECTS/profile-gpt/venv/lib/python3.11/site-packages/openai/api_requestor.py", line 683, in _interpret_response_line
    raise self.handle_error_response(
baditaflorin commented 1 year ago

Can I see at least what I got for the first 3? No. Also to be able to get it to this I changed from GPT3.5-turbo to GPT4