llama-index-vector-stores-qdrant

What it is and what it does

This package provides a LlamaIndex integration layer for Qdrant, a vector database designed for similarity search and retrieval-augmented generation (RAG). It acts as a bridge between LlamaIndex's document processing and embedding pipeline and Qdrant's vector storage and query engine, allowing you to persist embeddings and perform semantic searches efficiently.

The package wraps Qdrant's gRPC client (via qdrant-client) and exposes it through LlamaIndex's standard vector store interface. You use it to store document embeddings in Qdrant and retrieve semantically similar results during inference, typically as part of a larger RAG system. It requires Python 3.10+, depends on llama-index-core for the integration framework, and handles the gRPC communication with Qdrant transparently.

Use it for:

• Store embeddings from LlamaIndex document processing into Qdrant for persistent semantic search across documents
• Build RAG pipelines where LlamaIndex retrieves relevant context from Qdrant before passing it to an LLM
• Perform similarity search on embeddings without managing Qdrant client code directly in your application
• Scale embedding storage across multiple documents while maintaining LlamaIndex's high-level API
• Integrate Qdrant as a backend for LlamaIndex-based chatbots or question-answering systems

Worth the install?

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

Integrates Qdrant vector database with LlamaIndex for storing and retrieving embeddings in RAG and semantic search applications.

Yes, if you are already using LlamaIndex and need a vector store backend. Low install friction, active maintenance, MIT license, and no known vulnerabilities make it a straightforward choice. Verify that Qdrant server setup aligns with your deployment model before committing.

Install

llama-index-vector-stores-qdrant on PyPI

pip install llama-index-vector-stores-qdrant

uv add llama-index-vector-stores-qdrant

poetry add llama-index-vector-stores-qdrant

Installing llama-index-vector-stores-qdrant

Before you install

Low install friction with a pure-Python wheel. Active maintenance as of 2026-08-13, released 1 day ago. Depends on grpcio, llama-index-core, and qdrant-client.

License in practice

MIT license permits commercial and private use with minimal restrictions, making it suitable for most production deployments.

Quickstart

pip install llama-index-vector-stores-qdrant

from llama_index.vector_stores.qdrant import QdrantVectorStore
from qdrant_client import QdrantClient

client = QdrantClient(":memory:")
vector_store = QdrantVectorStore(client=client, collection_name="my_collection")

Requires Python 3.10 or later (and below 3.14). Qdrant server or in-memory instance must be available or configured.

Verify before relying

• Whether Qdrant server setup or configuration is required before this integration can be used
• Performance characteristics and scalability limits for large embedding datasets
• Compatibility matrix with specific versions of llama-index-core and qdrant-client

Package facts

Evidence: llama_index_vector_stores_qdrant-0.10.3-py3-none-any.whl

Tags

More Artificial Intelligence packages

Further reading