Lorenze/tools drop litellm (#3710)

* completely drop litellm and correctly pass config for qdrant

* feat: add support for additional embedding models in EmbeddingService

- Expanded the list of supported embedding models to include Google Vertex, Hugging Face, Jina, Ollama, OpenAI, Roboflow, Watson X, custom embeddings, Sentence Transformers, Text2Vec, OpenClip, and Instructor.
- This enhancement improves the versatility of the EmbeddingService by allowing integration with a wider range of embedding providers.

* fix: update collection parameter handling in CrewAIRagAdapter

- Changed the condition for setting vectors_config in the CrewAIRagAdapter to check for QdrantConfig instance instead of using hasattr. This improves type safety and ensures proper configuration handling for Qdrant integration.

lib/crewai/src/crewai/rag/qdrant/config.py

@@ -4,6 +4,7 @@ from dataclasses import field
 from typing import Literal, cast
 
 from pydantic.dataclasses import dataclass as pyd_dataclass
+from qdrant_client.models import VectorParams
 
 from crewai.rag.config.base import BaseRagConfig
 from crewai.rag.qdrant.constants import DEFAULT_EMBEDDING_MODEL, DEFAULT_STORAGE_PATH
@@ -53,3 +54,4 @@ class QdrantConfig(BaseRagConfig):
     embedding_function: QdrantEmbeddingFunctionWrapper = field(
         default_factory=_default_embedding_function
     )
+    vectors_config: VectorParams | None = field(default=None)

lib/crewai/src/crewai/rag/qdrant/utils.py

@@ -4,8 +4,8 @@ import asyncio
 from typing import TypeGuard
 from uuid import uuid4
 
-from qdrant_client import AsyncQdrantClient  # type: ignore[import-not-found]
 from qdrant_client import (
+    AsyncQdrantClient,  # type: ignore[import-not-found]
     QdrantClient as SyncQdrantClient,  # type: ignore[import-not-found]
 )
 from qdrant_client.models import (  # type: ignore[import-not-found]