Skip to content

Commit

Permalink
Update Qdrant integration for Haystack 2.x (#87)
Browse files Browse the repository at this point in the history
  • Loading branch information
silvanocerza authored Dec 20, 2023
1 parent 6a552be commit e48966e
Showing 1 changed file with 24 additions and 9 deletions.
33 changes: 24 additions & 9 deletions integrations/qdrant-document-store.md
Original file line number Diff line number Diff line change
Expand Up @@ -3,15 +3,17 @@ layout: integration
name: Qdrant Document Store
description: Use the Qdrant vector database with Haystack
authors:
- name: Qdrant
socials:
github: qdrant
twitter: qdrant_engine
- name: Qdrant
socials:
github: qdrant
twitter: qdrant_engine
pypi: https://pypi.org/project/qdrant-haystack/
repo: https://github.com/qdrant/qdrant-haystack
repo: https://github.com/deepset-ai/haystack-core-integrations/tree/main/integrations/qdrant
type: Document Store
report_issue: https://github.com/qdrant/qdrant-haystack/issues
report_issue: https://github.com/deepset-ai/haystack-core-integrations/issues
logo: /logos/qdrant.png
version: Haystack 2.0
toc: true
---

An integration of [Qdrant](https://qdrant.tech) vector database with [Haystack](https://haystack.deepset.ai/)
Expand All @@ -33,6 +35,19 @@ pip install qdrant-haystack
poetry add qdrant-haystack
```

## Installation (1.x)

Latest versions of `qdrant-haystack` are compatible only with Haystack 2.x.
If you're using Haystack 1.x you need to specify the version explicitly.

```bash
pip install "qdrant-haystack<2.0.0"
```

```bash
poetry add "qdrant-haystack<2.0.0"
```

## Usage

Once installed, you can already start using `QdrantDocumentStore` as any other store that supports
Expand All @@ -55,9 +70,9 @@ official [Python Qdrant client](https://github.com/qdrant/qdrant_client).

### Using local in-memory / disk-persisted mode

Qdrant Python client, from version 1.1.1, supports local in-memory/disk-persisted mode. That's
Qdrant Python client, from version 1.1.1, supports local in-memory/disk-persisted mode. That's
a good choice for any test scenarios and quick experiments in which you do not plan to store
lots of vectors. In such a case spinning a Docker container might be even not required.
lots of vectors. In such a case spinning a Docker container might be even not required.

The local mode was also implemented in `qdrant-haystack` integration.

Expand Down Expand Up @@ -115,4 +130,4 @@ document_store = QdrantDocumentStore(
)
```

There is no difference in terms of functionality between local instances and cloud clusters.
There is no difference in terms of functionality between local instances and cloud clusters.

0 comments on commit e48966e

Please sign in to comment.