genkitx-milvus

Firebase Genkit <> Milvus Plugin

Milvus Community Plugin for Google Firebase Genkit

genkitx-milvus is a community plugin for using Milvus Vector Database with Firebase Genkit. Built by The Fire Company. 🔥

Installation

Install the plugin in your project with your favorite package manager:

• npm install genkitx-milvus
• yarn add genkitx-milvus
• pnpm add genkitx-milvus

Usage

Initialize

To use this plugin, specify it when you initialize Genkit:

import { genkit } from 'genkit';
import { milvus } from 'genkitx-milvus';

export default genkit({
  plugins: [
    milvus([
      {
        collectionName: 'collection_01',
        embedder: textEmbeddingGecko,
      },
    ]),
  ],
  // ...
});

You must specify a Milvus collection and the embedding model you want to use. In addition, there are three optional parameters:

• dbName: Specified database

• clientParams: If you're not running your Milvus server on the same machine as your Genkit flow, you need to specify auth options, or you're otherwise not running a default Milvus server configuration, you can specify Milvus client connection parameters: address and token.

  clientParams: {
    address: "",
    token: "",
  }
  

• embedderOptions: Use this parameter to pass options to the embedder:

  embedderOptions: { taskType: 'RETRIEVAL_DOCUMENT' },
  

Basic Examples

Import retriever and indexer references like so:

import { milvusRetrieverRef, milvusIndexerRef } from 'genkitx-milvus';

Then, use the references with ai.retrieve() and ai.index():

// To use the index you configured when you loaded the plugin:
let docs = await ai.retrieve({ retriever: milvusRetrieverRef, query });

// To specify an index:
export const customRetriever = milvusRetrieverRef({
  collectionName: 'collection_01',
});
docs = await ai.retrieve({ retriever: customRetriever, query });

// To use the index you configured when you loaded the plugin:
await ai.index({ indexer: milvusIndexerRef, documents });

// To specify an index:
export const customIndexer = milvusIndexerRef({
  collectionName: 'collection_01',
});
await ai.index({ indexer: customIndexer, documents });

Contributing

Want to contribute to the project? That's awesome! Head over to our Contribution Guidelines.

Need support?

[!NOTE]
This repository depends on Google's Firebase Genkit. For issues and questions related to Genkit, please refer to instructions available in Genkit's repository.

Reach out by opening a discussion on Github Discussions.

Credits

This plugin is proudly maintained by the team at The Fire Company. 🔥

License

This project is licensed under the Apache 2.0 License.