langchain/libs/partners/qdrant
Anush a653b209ba
qdrant: test new QdrantVectorStore (#24165)
## Description

This PR adds integration tests to follow up on #24164.

By default, the tests use an in-memory instance.

To run the full suite of tests, with both in-memory and Qdrant server:

```
$ docker run -p 6333:6333 qdrant/qdrant

$ make test

$ make integration_test
```

---------

Co-authored-by: Erick Friis <erick@langchain.dev>
2024-07-12 23:59:30 +00:00
..
langchain_qdrant langchain_qdrant: Added method "_asimilarity_search_with_relevance_scores" to Qdrant class (#23954) 2024-07-12 23:25:20 +00:00
scripts qdrant: init package (#21146) 2024-05-13 18:20:03 -07:00
tests qdrant: test new QdrantVectorStore (#24165) 2024-07-12 23:59:30 +00:00
.gitignore qdrant: init package (#21146) 2024-05-13 18:20:03 -07:00
LICENSE qdrant: init package (#21146) 2024-05-13 18:20:03 -07:00
Makefile qdrant: New sparse embeddings provider interface - PART 1 (#24015) 2024-07-11 17:07:25 -07:00
poetry.lock qdrant: new Qdrant implementation (#24164) 2024-07-12 04:52:02 +02:00
pyproject.toml qdrant: Bump patch version (#24168) 2024-07-12 14:48:50 -07:00
README.md qdrant: init package (#21146) 2024-05-13 18:20:03 -07:00

langchain-qdrant

This package contains the LangChain integration with Qdrant.

Installation

pip install -U langchain-qdrant

Usage

The Qdrant class exposes the connection to the Qdrant vector store.

from langchain_qdrant import Qdrant

embeddings = ... # use a LangChain Embeddings class

vectorstore = Qdrant.from_existing_collection(
    embeddings=embeddings,
    collection_name="<COLLECTION_NAME>",
    url="http://localhost:6333",
)