FAISS is a library for efficient similarity search and clustering of dense vectors. It is designed to work with large-scale datasets and provides a high-performance search engine for vector data. FAISS is optimized for memory usage and search speed, making it an excellent choice for production environments.

​
Usage

import os
from mem0 import Memory

os.environ["OPENAI_API_KEY"] = "sk-xx"

config = {
    "vector_store": {
        "provider": "faiss",
        "config": {
            "collection_name": "test",
            "path": "/tmp/faiss_memories",
            "distance_strategy": "euclidean"
        }
    }
}

m = Memory.from_config(config)
messages = [
    {"role": "user", "content": "I'm planning to watch a movie tonight. Any recommendations?"},
    {"role": "assistant", "content": "How about a thriller movies? They can be quite engaging."},
    {"role": "user", "content": "I'm not a big fan of thriller movies but I love sci-fi movies."},
    {"role": "assistant", "content": "Got it! I'll avoid thriller recommendations and suggest sci-fi movies in the future."}
]
m.add(messages, user_id="alice", metadata={"category": "movies"})

​
Installation

To use FAISS in your mem0 project, you need to install the appropriate FAISS package for your environment:

# For CPU version
pip install faiss-cpu

# For GPU version (requires CUDA)
pip install faiss-gpu

​
Config

Here are the parameters available for configuring FAISS:

ParameterDescriptionDefault Value
collection_nameThe name of the collectionmem0
pathPath to store FAISS index and metadata/tmp/faiss/<collection_name>
distance_strategyDistance metric strategy to use (options: ‘euclidean’, ‘inner_product’, ‘cosine’)euclidean
normalize_L2Whether to normalize L2 vectors (only applicable for euclidean distance)False

​
Performance Considerations

FAISS offers several advantages for vector search:

  1. Efficiency: FAISS is optimized for memory usage and speed, making it suitable for large-scale applications.
  2. Offline Support: FAISS works entirely locally, with no need for external servers or API calls.
  3. Storage Options: Vectors can be stored in-memory for maximum speed or persisted to disk.
  4. Multiple Index Types: FAISS supports different index types optimized for various use cases (though mem0 currently uses the basic flat index).

​
Distance Strategies

FAISS in mem0 supports three distance strategies:

  • euclidean: L2 distance, suitable for most embedding models
  • inner_product: Dot product similarity, useful for some specialized embeddings
  • cosine: Cosine similarity, best for comparing semantic similarity regardless of vector magnitude

When using cosine or inner_product with normalized vectors, you may want to set normalize_L2=True for better results.