qdrant/qdrant-client

Python client for Qdrant vector search engine

What it solves

It provides a Python SDK for interacting with the Qdrant vector search engine, allowing developers to store, search, and manage high-dimensional vector embeddings used in AI applications.

How it works

The library acts as a bridge between Python applications and a Qdrant server (or a local instance). It supports both synchronous and asynchronous requests via REST and gRPC. It also includes a "Local mode" that allows users to run the engine without a separate server for prototyping and testing.

Who it’s for

Developers building AI-powered search, recommendation systems, or RAG (Retrieval-Augmented Generation) pipelines who need a programmatic way to manage vector data in Python.

Highlights

  • Local Mode: Run the vector database locally in-memory or on disk without needing a Docker container or server.
  • Inference API: Integrated support for creating embeddings locally via FastEmbed (CPU/GPU) or remotely via Qdrant Cloud.
  • _Async Support: Full asynchronous client (AsyncQdrantClient) for high-performance applications.
  • Flexible Connectivity: Supports REST and gRPC for communication with Qdrant servers or managed cloud clusters.

Related

  • Project
    qdrant/rust-client

    A native Rust client for Qdrant, enabling high-performance vector search and database management within Rust applications.

  • Project
    qdrant/qdrant

    A high-performance vector database and similarity search engine written in Rust, designed for storing and retrieving embeddings with advanced filtering and hybrid search capabilities.

  • Project
    pinecone-io/python-sdk

    A Python client for the Pinecone vector database used to create and manage indexes, upsert vectors, and perform similarity queries.

  • Project
    qdrant/qdrant-js

    A JavaScript/TypeScript SDK for the Qdrant vector search engine, providing REST and gRPC clients to manage and search vector data.

  • Project
    Stevenic/vectra

    A local, file-backed, in-memory vector database that supports metadata filtering, cosine similarity, and local or API-based embeddings.