langchain-qdrant

What it is and what it does

langchain-qdrant is a bridge between LangChain and Qdrant, a vector database designed for semantic search. It lets you store document embeddings in Qdrant and retrieve them through LangChain's standard vector store interface, enabling retrieval-augmented generation (RAG) and semantic search workflows. The package wraps Qdrant's Python client and integrates with LangChain's embedding and document abstractions.

Typically used to build applications that combine large language models with external knowledge: you embed documents, store them in Qdrant via this package, then query them semantically to augment LLM prompts. It depends on langchain-core for the vector store contract, pydantic for data validation, and qdrant-client to communicate with the Qdrant service.

Use it for:

• Build RAG systems that retrieve relevant documents from Qdrant to augment LLM responses
• Implement semantic search over a corpus of documents stored in Qdrant
• Create chatbots with long-term memory by storing conversation embeddings in Qdrant
• Filter and rerank search results using Qdrant's metadata and payload capabilities within LangChain workflows
• Prototype vector search applications without managing Qdrant client code directly

Worth the install?

AI-flagged interpretation of the facts on this page — verify before relying

Connects LangChain applications to Qdrant vector database for semantic search and retrieval-augmented generation workflows.

Yes, if you are building a LangChain application that needs vector search. Low install friction, active maintenance, no security issues, and permissive MIT license make it a straightforward choice. The only prerequisite is Python 3.10+ and access to a Qdrant instance.

Install

langchain-qdrant on PyPI

pip install langchain-qdrant

uv add langchain-qdrant

poetry add langchain-qdrant

Installing langchain-qdrant

Before you install

Low friction: pure Python wheel with three runtime dependencies (langchain-core, pydantic, qdrant-client). Actively maintained as of 2026-08-14 with no known vulnerabilities.

License in practice

MIT license permits commercial and private use with minimal restrictions—suitable for most projects.

Quickstart

pip install langchain-qdrant

from langchain_qdrant import QdrantVectorStore
from qdrant_client import QdrantClient

client = QdrantClient(":memory:")
vector_store = QdrantVectorStore.from_documents(
    documents, embeddings, client=client, collection_name="my_collection"
)

Requires Python 3.10 or later (supports up to <4.0.0). Qdrant server or in-memory instance must be available.

Verify before relying

• Whether this package handles vector dimension mismatches or type validation automatically
• Performance characteristics with large document collections (millions of embeddings)
• Supported Qdrant server versions and backward compatibility guarantees

Package facts

Evidence: langchain_qdrant-1.1.0-py3-none-any.whl

Tags

More Artificial Intelligence packages

Further reading