search

mem0ai / mem0

The Memory layer for your AI apps
https://mem0.ai
Apache License 2.0
21.6k stars 1.97k forks source link

Error Code 400 - Invalid input Parameter for OpenAI Embeddings API #1743

Closed ketchalegend closed 2 weeks ago

ketchalegend commented 2 weeks ago

🐛 Describe the bug

I'm encountering a 400 Bad Request error when making a request to the OpenAI Embeddings API. The error message indicates that the input parameter is invalid. Below is the relevant part of the traceback and error message:

ERROR:root
adding memory: Error code: 400 - {'error': {'message': "'$.input' is invalid. Please check the API reference: https://platform.openai.com/docs/api-reference.", 'type': 'invalid_request_error', 'param': None, 'code': None}}
Traceback (most recent call last):
File "/Users/xxxxx/xxxx/xxxx/chat.py", line 73, in handle_query
self.memory.add(
File "/usr/local/lib/python3.12/site-packages/mem0/memory/main.py", line 159, in add
function_result = function_to_call(**function_args)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/usr/local/lib/python3.12/site-packages/mem0/memory/main.py", line 464, in _create_memory_tool
embeddings = self.embedding_model.embed(data)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/usr/local/lib/python3.12/site-packages/mem0/embeddings/openai.py", line 32, in embed
self.client.embeddings.create(input=[text], model=self.config.model)
File "/usr/local/lib/python3.12/site-packages/openai/resources/embeddings.py", line 114, in create
return self._post(
^^^^^^^^^^^
File "/usr/local/lib/python3.12/site-packages/openai/_base_client.py", line 1266, in post
return cast(ResponseT, self.request(cast_to, opts, stream=stream, stream_cls=stream_cls))
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/usr/local/lib/python3.12/site-packages/openai/_base_client.py", line 942, in request
return self._request(
^^^^^^^^^^^^^^
File "/usr/local/lib/python3.12/site-packages/openai/_base_client.py", line 1046, in _request
raise self._make_status_error_from_response(err.response) from None
openai.BadRequestError: Error code: 400 - {'error': {'message': "'$.input' is invalid. Please check the API reference: https://platform.openai.com/docs/api-reference.", 'type': 'invalid_request_error', 'param': None, 'code': None}}

This is what am doing in the code and am running this code: python3 chat.py "how old am i?" "you are a support agent" "you reply well" 1 

    def handle_query(self, system_prompt, query, user_id=None):
        """
        Handle a customer query and store the relevant information in memory.
        :param system_prompt: The system prompt to use for the AI.
        :param query: The customer query to handle.
        :param user_id: Optional user ID to associate with the memory.
        """
        try:
            previous_memories = self.search_memories(query, user_id)

            prompt = query
            if previous_memories:
                prompt = f"User input: {query}\nPrevious memories: {previous_memories}"

            # Start a chat completion request to the AI
            response = self.client.chat.completions.create(
                model="gpt-4o-mini",
                messages=[
                    {"role": "system", "content": system_prompt},
                    {"role": "user", "content": prompt},
                ],
            )

            # Attempt to store the query in memory
            try:
                self.memory.add(
                    query, user_id=user_id, metadata={"app_id": self.app_id}
                )
            except Exception as mem_error:
                logging.error(f"Error adding memory: {str(mem_error)}", exc_info=True)
                # Continue execution even if memory storage fails

            return response.choices[0].message.content
        except Exception as e:
            logging.error(f"Error in handle_query: {str(e)}", exc_info=True)
            return (
                "I'm sorry, but I encountered an error while processing your request."
            )

I modified the model to gpt-4o now i get the error message that i should modify my prompt

ERROR:root:Error adding memory: Error code: 400 - {'error': {'message': "Failed to call a function. Please adjust your prompt. See 'failed_generation' for more details.", 'type': 'invalid_request_error', 'code': 'tool_use_failed', 'failed_generation': '<tool-use>{"tool_calls": [{"id": "pending", "type": "function", "function": {"name": "add_memory"}, "parameters": {}}]}</tool-use>'}}
Traceback (most recent call last):
  File "/Users/emmanuelketchabepa/Herd/whatsocial/chat.py", line 75, in handle_query
    self.memory.add(
  File "/usr/local/lib/python3.12/site-packages/mem0/memory/main.py", line 136, in add
    response = self.llm.generate_response(messages=messages, tools=tools)
               ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "/usr/local/lib/python3.12/site-packages/mem0/llms/groq.py", line 89, in generate_response
    response = self.client.chat.completions.create(**params)
               ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "/usr/local/lib/python3.12/site-packages/groq/resources/chat/completions.py", line 289, in create
    return self._post(
           ^^^^^^^^^^^
  File "/usr/local/lib/python3.12/site-packages/groq/_base_client.py", line 1225, in post
    return cast(ResponseT, self.request(cast_to, opts, stream=stream, stream_cls=stream_cls))
                           ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "/usr/local/lib/python3.12/site-packages/groq/_base_client.py", line 920, in request
    return self._request(
           ^^^^^^^^^^^^^^
  File "/usr/local/lib/python3.12/site-packages/groq/_base_client.py", line 1018, in _request
    raise self._make_status_error_from_response(err.response) from None
groq.BadRequestError: Error code: 400 - {'error': {'message': "Failed to call a function. Please adjust your prompt. See 'failed_generation' for more details.", 'type': 'invalid_request_error', 'code': 'tool_use_failed', 'failed_generation': '<tool-use>{"tool_calls": [{"id": "pending", "type": "function", "function": {"name": "add_memory"}, "parameters": {}}]}</tool-use>'}}
I can't determine your exact age from this interaction. However, if you have a specific question or need assistance with something else, feel free to ask!
ketchalegend commented 2 weeks ago

I had to change the model and it worked. maybe its something to add to your documentation.