Skip to content

Faiss

Faiss is a library for efficient similarity search and clustering of dense vectors. Unlike cloud vector stores, Faiss runs locally on your machine and saves data to your file system.

Faiss Node

Prerequisites

Faiss is available on the platform out of the box. No separate installation is required.

Setup

Inputs

Input Description
Document Connect any node from the Document Loader category.
Embeddings Connect any node from the Embeddings category.

Parameters

  • Base Path: The folder path where the index files (faiss.index and docstore.json) will be saved.
    • If left blank, data is stored in RAM and will be lost when the session ends.

Configuration and Ingestion

  1. Add a new Faiss node on the canvas.
  2. Enter a folder path in the Faiss node’s Base Path field.
  3. Connect your Document Loader and Embeddings nodes to the Faiss node.
  4. Click Upsert Vector Database to process your documents.

Verify

To verify your data has been upserted, navigate to the folder you specified in the Base Path field. You should see files faiss.index and docstore.json.

Resources