Embbeder insist in calling OpenAI

CrewAI Community Support
1

Hi there,
I am trying now with an embeeded using ollama.
I have Llama 3.1 and nomic-text for embedder

This is what I add to my PDFtoll

tool = PDFSearchTool(
    config=dict(
        llm=dict(
            provider="ollama",# or google, openai, anthropic, llama2, ...
            config=dict(
                model="llama3.1",
                temperature=0.0001,
                base_url='http://127.0.0.1:11434',),),
        embedder=dict(
            provider="ollama",# or openai, ollama, ...
            config=dict(
                model="nomic-embed-text:latest",
                base_url='http://127.0.0.1:11434',
                # title="Embeddings",
            ),
        ),
    )
)

I looked that no other LLM is called, specially OpenAI.

I keep having these toke problem from OpenAI, but I don’t want to use it. I have an account but I want to stay local for the moment.

  return self._retry_request(
  File "/home/ru/Documents/personal_agents/.venv/lib/python3.10/site-packages/openai/_base_client.py", line 1092, in _retry_request
    return self._request(
  File "/home/ru/Documents/personal_agents/.venv/lib/python3.10/site-packages/openai/_base_client.py", line 1058, in _request
    raise self._make_status_error_from_response(err.response) from None
openai.RateLimitError: Error code: 429 - {'error': {'message': 'You exceeded your current quota, please check your plan and billing details. For more information on this error, read the docs: https://platform.openai.com/docs/guides/error-codes/api-errors.', 'type': 'insufficient_quota', 'param': None, 'code': 'insufficient_quota'}}`

can anyone help me? Thanks to all

2

My mistake, found the issue. It’s the memory embedding.
Many thanks

3

Hi I am trying to use text embedding other than ada02. can you please help me? I specified the model in DirectorySearchTool but it is not working

4

Hi there Shusanket,

Can you show the code?
As I have seen, the tools like more the absolute paths and not relative ones.

Let me know

5

policiesRagtool = DirectorySearchTool(
config=dict(
llm=dict(
provider=“openai”, # Options include ollama, google, anthropic, llama2, and more
config=dict(
model=“gpt-4o”,
# Additional configurations here
),
),
embedder=dict(
provider=“openai”, # or openai, ollama, …
config=dict(
model=“text-embedding-3-small”,
# task_type=“retrieval_document”,
# title=“Embeddings”,
),
),
),
directory = dir
) here is the code, thank you

6

What’s not working? What error do you get?

7

“”“WARNING:chromadb.segment.impl.vector.local_persistent_hnsw:Number of requested results 3 is greater than number of elements in index 1, updating n_results = 1"”" and it is not retrieving any info from the directory

8

Screenshot 2024-10-18 at 9.59.23 AM
Screenshot 2024-10-18 at 9.59.23 AM1588×103 6.27 KB

now even while using the default text embedder it is not generating any text embedding. the process gets finished at 0.
here is the code;
policiesRagtool = DirectorySearchTool(directory=dir)