[BUG] Unable to change project id when using vertexai embedding configuartion.

[iam1492]

Description

In my crew.py source code, I want use custom embedder as google vertexai like bellow.
So I try to add configuration with my project_id to embedding_config dictionary.

embedding_config={
  "provider": "vertexai",
  "config": {
    "project_id": project_id,
    "model": "text-multilingual-embedding-002",
    "region": "us-central1",
    "api_key": access_token,
  }
}
return Crew(
  agents=self.agents,
  tasks=self.tasks,
  process=Process.sequential,
  verbose=True,
  knowledge_sources=[self.date_source],
  memory=True,
  embedder=embedding_config,
)

But unfortunately, In embedding_configurator.py in crewai.utilities package do not allow to change the project_id and region.
This make chromadb use default value.
project_id: str = "cloud-large-language-models",
region: str = "us-central1",
And of course, this default value is not my project id and api call not work as expected.

@staticmethod
    def _configure_vertexai(config, model_name):
        from chromadb.utils.embedding_functions.google_embedding_function import (
            GoogleVertexEmbeddingFunction,
        )

        return GoogleVertexEmbeddingFunction(
            model_name=model_name,
            api_key=config.get("api_key"),
        )

Steps to Reproduce

1. Using google vertex ai as a custom embedder.

Expected behavior

Can use vertex ai with my own project_id

Screenshots/Code snippets

embedding_config={
  "provider": "vertexai",
  "config": {
    "project_id": project_id,
    "model": "text-multilingual-embedding-002",
    "region": "us-central1",
    "api_key": access_token,
  }
}
return Crew(
  agents=self.agents,
  tasks=self.tasks,
  process=Process.sequential,
  verbose=True,
  knowledge_sources=[self.date_source],
  memory=True,
  embedder=embedding_config,
)

Operating System

Ubuntu 20.04

Python Version

3.10

crewAI Version

0.100.0

crewAI Tools Version

0.33.0

Virtual Environment

Venv

Evidence

[2025-01-31 08:49:25][ERROR]: Failed to upsert documents: Expected Embedings to be non-empty list or numpy array, got in upsert.
[2025-01-31 08:49:25][WARNING]: Failed to init knowledge: Expected Embedings to be non-empty list or numpy array, got in upsert.
ERROR:root:Error during short_term search: Expected Embedings to be non-empty list or numpy array, got in query.
ERROR:root:Error during entities search: Expected Embedings to be non-empty list or numpy array, got in query

Possible Solution

Make GoogleVertexEmbeddingFunction allow to set project_id and region as well.

Additional context

No