mirror of
https://github.com/crewAIInc/crewAI.git
synced 2026-01-10 00:28:31 +00:00
ecd16486c1
- Implement FAISSSearchTool for vector similarity search - Add comprehensive unit tests - Update documentation with usage examples - Add FAISS dependency Closes #2118 Co-Authored-By: Joe Moura <joao@crewai.com>
59 lines
1.3 KiB
Plaintext
59 lines
1.3 KiB
Plaintext
# FAISS Search Tool
|
|
|
|
The FAISS Search Tool enables efficient vector similarity search using Facebook AI Similarity Search (FAISS).
|
|
|
|
## Usage
|
|
|
|
```python
|
|
from crewai import Agent
|
|
from crewai.tools import FAISSSearchTool
|
|
|
|
# Initialize tool
|
|
search_tool = FAISSSearchTool(
|
|
index_type="L2", # or "IP" for inner product
|
|
dimension=384, # Match your embedder's dimension
|
|
embedder_config={
|
|
"provider": "fastembed",
|
|
"model": "BAAI/bge-small-en-v1.5"
|
|
}
|
|
)
|
|
|
|
# Add documents
|
|
search_tool.add_texts([
|
|
"Document 1 content",
|
|
"Document 2 content",
|
|
# ...
|
|
])
|
|
|
|
# Create agent with tool
|
|
agent = Agent(
|
|
role="researcher",
|
|
goal="Find relevant information",
|
|
tools=[search_tool]
|
|
)
|
|
```
|
|
|
|
## Configuration
|
|
|
|
| Parameter | Type | Description |
|
|
|-----------|------|-------------|
|
|
| index_type | str | FAISS index type ("L2" or "IP") |
|
|
| dimension | int | Embedding dimension |
|
|
| embedder_config | dict | Embedder configuration |
|
|
|
|
## Parameters
|
|
|
|
### index_type
|
|
- `"L2"`: Euclidean distance (default)
|
|
- `"IP"`: Inner product similarity
|
|
|
|
### dimension
|
|
Default is 384, which matches the BAAI/bge-small-en-v1.5 model. Adjust this to match your chosen embedder model's output dimension.
|
|
|
|
### embedder_config
|
|
Configuration for the embedding model. Supports all CrewAI embedder providers:
|
|
- fastembed (default)
|
|
- openai
|
|
- google
|
|
- ollama
|