faiss

Name: faiss
Author: facebook

by facebook

GPU-accelerated billion-scale vector similarity search and clustering

39.5K★dl/month

N/A (library)params

Source Run it on your own data, free

Identifiers

Model ID

facebook/faiss

Feature URI

mixpeek://vector_index@v1/facebook_faiss_v1

Overview

FAISS is Meta's library for efficient similarity search and clustering of dense vectors. It supports multiple index types (IVF, PQ, HNSW, flat), product quantization for compression, and optimized GPU kernels that handle billion-scale datasets.

On Mixpeek, FAISS powers the vector search infrastructure behind retriever stages, enabling sub-millisecond approximate nearest neighbor queries over large embedding collections.

Architecture

C++ library with Python bindings. Supports flat (exact), IVF (inverted file), PQ (product quantization), HNSW (graph-based), and composite indexes. GPU batched search with CUDA kernels for billion-scale workloads.

Mixpeek SDK Integration

// No extractor parameter takes a Hugging Face model id (checked against
// GET /v1/discovery/extractors, which returns 13), so faiss runs
// on your side and the output is upserted through POST
// /v1/namespaces/{namespace_id}/documents/upsert. On Enterprise the other
// path is to upload the weights instead: POST /v1/namespaces/{id}/models
// accepts the huggingface format and a custom plugin loads them.
const res = await fetch(
  "https://api.mixpeek.com/v1/namespaces/ns_your_namespace/documents/upsert",
  {
    method: "POST",
    headers: {
      Authorization: "Bearer API_KEY",
      "Content-Type": "application/json",
    },
    body: JSON.stringify({
      collection_id: "col_your_collection",
      documents: [
        {
          document_id: "asset-00412",
          // The vector name has to match a vector index on the collection.
          vectors: { "image-embedding": yourVector },
          payload: { source_key: "archive/2026/asset-00412" },
        },
      ],
    }),
  },
);

// Managed alternative, if this exact model is not the requirement:
// image_extractor@v1 runs google/siglip-base-patch16-224
// (768-d) over a bucket, with no inference of your own.