Haystack serves as a comprehensive NLP framework, offering a modular methodology for constructing cutting-edge generative AI, QA, and semantic knowledge base search systems. A critical element in contemporary NLP systems is an efficient database for storing and retrieving extensive text data. Vector databases excel in this role, as they house vector representations of text and implement effective methods for swift retrieval. Thus, we are happy to announce the integration with Haystack - QdrantDocumentStore. This document store is unique, as it is maintained externally by the Qdrant team.

The new document store comes as a separate package and can be updated independently of Haystack:

pip install qdrant-haystack

QdrantDocumentStore supports all the configuration properties available in the Qdrant Python client. If you want to customize the default configuration of the collection used under the hood, you can provide that settings when you create an instance of the QdrantDocumentStore. For example, if you’d like to enable the Scalar Quantization, you’d make that in the following way:

from qdrant_haystack.document_stores import QdrantDocumentStore
from qdrant_client.http import models

document_store = QdrantDocumentStore(