Qdrant plugin

The Qdrant plugin provides Genkit indexer and retriever implementations in JS and Go that use the Qdrant.

Installation

npm i genkitx-qdrant

Configuration

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

import { qdrant } from 'genkitx-qdrant';

const ai = genkit({
  plugins: [
    qdrant([
      {
        embedder: googleAI.embedder('text-embedding-004'),
        collectionName: 'collectionName',
        clientParams: {
          url: 'http://localhost:6333',
        },
      },
    ]),
  ],
});

You'll need to specify a collection name, the embedding model you want to use and the Qdrant client parameters. In addition, there are a few optional parameters:

• embedderOptions: Additional options to pass options to the embedder:

  embedderOptions: { taskType: 'RETRIEVAL_DOCUMENT' },

• contentPayloadKey: Name of the payload filed with the document content. Defaults to "content".

  contentPayloadKey: 'content';

• metadataPayloadKey: Name of the payload filed with the document metadata. Defaults to "metadata".

  metadataPayloadKey: 'metadata';

• dataTypePayloadKey: Name of the payload filed with the document datatype. Defaults to "_content_type".

  dataTypePayloadKey: '_datatype';

• collectionCreateOptions: Additional options when creating the Qdrant collection.

Usage

Import retriever and indexer references like so:

import { qdrantIndexerRef, qdrantRetrieverRef } from 'genkitx-qdrant';

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

// To export an indexer:
export const qdrantIndexer = qdrantIndexerRef('collectionName', 'displayName');

// To export a retriever:
export const qdrantRetriever = qdrantRetrieverRef(
  'collectionName',
  'displayName',
);

You can refer to Retrieval-augmented generation for a general discussion on indexers and retrievers.