what is LanceDB?
LanceDB is a Node.js implementation for vector search that utilizes LanceDB and Ollama's embedding model to perform efficient similarity searches on stored documents.
how to use LanceDB?
To use LanceDB, clone the repository, install the dependencies, and run the vector search test script to perform searches against your LanceDB database.
key features of LanceDB?
- Connects to a LanceDB database for vector search
- Custom embedding functions using Ollama
- Performs vector similarity search and displays results
use cases of LanceDB?
- Searching for relevant documents based on vector similarity.
- Integrating with other applications as a microservice for document retrieval.
- Enhancing search capabilities in AI applications.
FAQ from LanceDB?
- What are the prerequisites for using LanceDB?
You need Node.js (v14 or later) and Ollama running locally with the
nomic-embed-text
model.
- How do I install LanceDB?
Clone the repository and run
pnpm install
to install the dependencies.
- Can I customize the embedding function?
Yes! The project includes a custom
OllamaEmbeddingFunction
that you can modify.
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
- Clone the repository
- Install dependencies:
pnpm install
Dependencies
@lancedb/lancedb
: LanceDB client for Node.jsapache-arrow
: For handling columnar datanode-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
Contributing
Contributions are welcome! Please feel free to submit a Pull Request.