Docs/release 0.175.0 docs (#3441)

* docs(install): note OpenAI SDK requirement openai>=1.13.3 for 0.175.0

* docs(cli): document device-code login and config reset guidance; renumber sections

* docs(flows): document conditional @start and resumable execution semantics

* docs(tasks): move max_retries to deprecation note under attributes table

* docs: provider-neutral RAG client config; entity memory batching; trigger payload note; tracing batch manager

* docs(cli): fix duplicate numbering (renumber Login/API Keys/Configuration sections)
This commit is contained in:
Tony Kipkemboi
2025-09-03 17:27:11 -04:00
committed by GitHub
parent d31ffdbb90
commit 49a5ae0e16
9 changed files with 131 additions and 4 deletions

View File

@@ -24,6 +24,41 @@ For file-based Knowledge Sources, make sure to place your files in a `knowledge`
Also, use relative paths from the `knowledge` directory when creating the source.
</Tip>
### Vector store (RAG) client configuration
CrewAI exposes a provider-neutral RAG client abstraction for vector stores. The default provider is ChromaDB, and Qdrant is supported as well. You can switch providers using configuration utilities.
Supported today:
- ChromaDB (default)
- Qdrant
```python Code
from crewai.rag.config.utils import set_rag_config, get_rag_client, clear_rag_config
# ChromaDB (default)
from crewai.rag.chromadb.config import ChromaDBConfig
set_rag_config(ChromaDBConfig())
chromadb_client = get_rag_client()
# Qdrant
from crewai.rag.qdrant.config import QdrantConfig
set_rag_config(QdrantConfig())
qdrant_client = get_rag_client()
# Example operations (same API for any provider)
client = qdrant_client # or chromadb_client
client.create_collection(collection_name="docs")
client.add_documents(
collection_name="docs",
documents=[{"id": "1", "content": "CrewAI enables collaborative AI agents."}],
)
results = client.search(collection_name="docs", query="collaborative agents", limit=3)
clear_rag_config() # optional reset
```
This RAG client is separate from Knowledges built-in storage. Use it when you need direct vector-store control or custom retrieval pipelines.
### Basic String Knowledge Example
```python Code