Chroma plugin

The Chroma plugin provides indexer and retriever implementatons that use the Chroma vector database in client/server mode.


npm i --save genkitx-chromadb


To use this plugin, specify it when you call configureGenkit():

import { chroma } from 'genkitx-chromadb';

export default configureGenkit({
  plugins: [
        collectionName: 'bob_collection',
        embedder: textEmbeddingGecko,
  // ...

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

  • clientParams: If you're not running your Chroma server on the same machine as your Genkit flow, you need to specify auth options, or you're otherwise not running a default Chroma server configuration, you can specify a Chroma ChromaClientParams object to pass to the Chroma client:

    clientParams: {
      path: "",
  • embedderOptions: Use this parameter to pass options to the embedder:

    embedderOptions: { taskType: 'RETRIEVAL_DOCUMENT' },


Import retriever and indexer references like so:

import { chromaRetrieverRef } from 'genkitx-chromadb';
import { chromaIndexerRef } from 'genkitx-chromadb';

Then, pass the references to retrieve() and index():

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

// To specify an index:
export const bobFactsRetriever = chromaRetrieverRef({
  collectionName: 'bob-facts',
docs = await retrieve({ retriever: bobFactsRetriever, query });
// To use the index you configured when you loaded the plugin:
await index({ indexer: chromaIndexerRef, documents });

// To specify an index:
export const bobFactsIndexer = chromaIndexerRef({
  collectionName: 'bob-facts',
await index({ indexer: bobFactsIndexer, documents });

See the Retrieval-augmented generation page for a general discussion on indexers and retrievers.