mcpField
L
LanceDB

LanceDB

Local
github.com/vurtnecDatabases0Updated 83w ago
Repository

About LanceDB

LanceDB is a Node.js vector-search example for developers working with LanceDB and Ollama embeddings. It demonstrates a custom embedding function and similarity searches over stored documents.

Key features

  1. 01Connect to a LanceDB database
  2. 02Create embeddings with Ollama
  3. 03Run vector similarity searches on documents
  4. 04Display search results and similarity scores

Use cases

  1. 01Retrieve similar documents from LanceDB
  2. 02Test text embeddings generated by Ollama
  3. 03Inspect similarity scores for document results

MCP support

The project can be configured as an MCP service and connected through an MCP client's configuration.

#lancedb#vector-search#nodejs

Configuration

Local server config is the same for every client. Copy it into your client’s MCP config file.

No install method listed yet

We haven’t collected a package or remote endpoint for this server. Follow the instructions in the project README.

Repository

Tools

No tool list yet

Local servers expose tools only once running on your machine, and the maintainer has not provided a tool list.

Details

From the project README

LanceDB Node.js Vector Search

A Node.js implementation for vector search using LanceDB and Ollama's embedding model.

Overview

This project demonstrates how to:

  • Connect to a LanceDB database
  • Create custom embedding functions using Ollama
  • Perform vector similarity search against stored documents
  • Process and display search results

Prerequisites

  • Node.js (v14 or later)
  • Ollama running locally with the nomic-embed-text model
  • LanceDB storage location with read/write permissions

Installation

  1. Clone the repository
  2. Install dependencies:
pnpm install

Dependencies

  • @lancedb/lancedb: LanceDB client for Node.js
  • apache-arrow: For handling columnar data
  • node-fetch: For making API calls to Ollama

Usage

Run the vector search test script:

pnpm test-vector-search

Or directly execute:

node test-vector-search.js

Configuration

The script connects to:

  • LanceDB at the configured path
  • Ollama API at http://localhost:11434/api/embeddings

MCP Configuration

To integrate with Claude Desktop as an MCP service, add the following to your MCP configuration JSON:

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

Replace the paths with your actual installation paths:

  • /path/to/lancedb-node/dist/index.js - Path to the compiled index.js file
  • /path/to/your/lancedb/storage - Path to your LanceDB storage directory

Custom Embedding Function

The project includes a custom OllamaEmbeddingFunction that:

  • Sends text to the Ollama API
  • Receives embeddings with 768 dimensions
  • Formats them for use with LanceDB

Vector Search Example

The example searches for "how to define success criteria" in the "ai-rag" table, displaying results with their similarity scores.

License

MIT License

Contributing

Contributions are welcome! Please feel free to submit a Pull Request.

Comments

Markdown supported

New to MCP?

From what the protocol is to installing your first server, these answers cover most first questions.

An open protocol that defines how AI applications connect to external tools and data in a uniform way. Clients talk to the model; MCP servers provide tools, resources and prompt templates. They exchange standard messages, so one server can be reused by many clients.