Lancedb

A Node.js-based vector search project that uses the LanceDB database and Ollama embedding model to implement document similarity search functionality

Search tools Developer tools #Vector Search #Document Retrieval #Node Integration Local .JavaScript

rating : 2 points

downloads : 7.1K

update time : 2025-04-29

Open Site

What is LanceDB Vector Search?

This service enables semantic search capabilities by converting text into numerical vectors (embeddings) and performing efficient similarity searches. It's ideal for building AI-powered search features in applications.

How does it work?

The system uses Ollama's AI model to understand text meaning, LanceDB for fast vector storage/search, and provides simple Node.js APIs for integration.

When should I use this?

Perfect for implementing: document search, recommendation systems, question-answering bots, and any application needing'search by meaning' rather than exact keyword matching.

Key Features

Semantic Search

Understands search intent and meaning beyond literal keywords

Local AI Processing

Uses local Ollama models for privacy-preserving embeddings

Simple Integration

Node.js API makes it easy to add to existing applications

Advantages

No external API dependencies - runs completely locally

Maintains data privacy since processing happens on your infrastructure

Flexible enough to work with different AI models

Limitations

Requires local Ollama instance with sufficient computing resources

Initial setup has several moving parts to configure

Vector search performance depends on hardware capabilities

Getting Started

Install Requirements

Ensure you have Node.js v14+ installed and Ollama running locally with the nomic-embed-text model

Set Up the Project

Clone the repository and install dependencies

Run Sample Search

Execute the test script to verify everything works

Example Use Cases

Technical Documentation Search

Find relevant documentation sections even when using different terminology

Content Recommendation

Suggest related articles or products based on semantic similarity

Frequently Asked Questions

What hardware requirements does this have?

Can I use different embedding models?

How do I scale this for production?

Additional Resources

LanceDB Documentation

Official LanceDB documentation and API reference

Ollama Model Library

Browse available AI models for embedding generation

Vector Search Explained

Beginner's guide to semantic vector search concepts

🚀 LanceDB Node.js Vector Search

A sample project for vector search implemented in Node.js, integrating LanceDB and Ollama's embedding models.

🚀 Quick Start

This project demonstrates how to:

Connect to a LanceDB database.
Create a custom embedding function using Ollama.
Perform vector similarity searches to find stored documents.
Process and display search results.

✨ Features

Connect to LanceDB and execute vector similarity searches.
Use Ollama to create custom embedding functions.
Integrate with MCP services in Claude Desktop.

📦 Installation

Prerequisites

Node.js (v14 or higher).
A locally running Ollama service configured with the nomic-embed-text model.
Permissions to read from and write to the LanceDB storage location.

Steps

Clone the repository.
Install dependencies:

pnpm install

📚 Documentation

Dependencies

@lancedb/lancedb: A LanceDB client for connecting with Node.js.
apache-arrow: For handling columnar data.
node-fetch: For sending requests to the Ollama API.

Usage

Run the vector search test script:

pnpm test-vector-search

Or execute directly:

node test-vector-search.js

Configuration

The script connects to the following services:

LanceDB at the specified path.
Ollama API at http://localhost:11434/api/embeddings.

MCP Configuration

To use it as an MCP service in Claude Desktop, add the following to the MCP configuration JSON file:

{
  "mcpServers": {
    "lanceDB": {
      "command": "node",
      "args": [
        "/path/to/lancedb-node/dist/index.js",
        "--db-path",
        "/path/to/your/lancedb/storage"
      ]
    }
  }
}

Replace the following paths with the actual ones:

/path/to/lancedb-node/dist/index.js - The actual installation location of the Node.js service.
/path/to/your/lancedb/storage - The actual path of the LanceDB storage directory.

Custom Embedding Function

The project includes a custom OllamaEmbeddingFunction that is responsible for:

Sending text to the Ollama API for processing.
Receiving 768-dimensional embedding vectors.
Formatting the output to meet the requirements of LanceDB.

Vector Search Example

The example code demonstrates how to search for "how to define success criteria" in the "ai-rag" table and display the matching results and their similarity scores.