qdrant-client
Client library for the Qdrant vector search engine
Decision gist · record as of 2026-08-14
Yes. qdrant-client is actively maintained, has no known vulnerabilities, minimal install friction, and permissive licensing. Install it if you need to integrate vector search into a Python application—whether for prototyping locally or connecting to a production Qdrant deployment.AI-flagged interpretation of the facts on this page — verify before relying
Before you install
- Requires Python 3.10 or later.
- Low install friction with a pure Python wheel and minimal dependencies.
- Active maintenance with a recent release (10 days old) and steady repository activity.
License · maintenance · safety
Apache-2.0 (permissive) — Apache-2.0 permissive license allows free use, modification, and distribution in commercial and private projects with minimal restrictions.
last release 2026-08-04 (10 days) · last repo commit 2026-08-12 · 1,343 stars
0 known vulnerabilities (OSV.dev, 2026-08-14) · 22,371,363 downloads/mo, #975 on PyPI
Alternatives
Verify before relying
pip install qdrant-client
from qdrant_client import QdrantClient
client = QdrantClient(":memory:")
client.create_collection(
collection_name="my_collection",
vectors_config={"size": 100, "distance": "COSINE"}
)- Performance characteristics and latency benchmarks for local vs. remote modes
- Scalability limits for in-memory collections and disk-persisted storage
- Compatibility and integration details with specific embedding models beyond FastEmbed
What it is and what it does
qdrant-client is a Python SDK for the Qdrant vector search engine that lets you build semantic search and similarity matching into applications. It provides type-hinted APIs for all Qdrant operations—creating collections, upserting vectors, querying with filters—and works in three modes: local in-memory (for development and testing), local persistent (storing to disk), or remote (connecting to a Qdrant server or cloud instance). The library supports both synchronous and asynchronous calls, REST and gRPC transports, and includes helper methods for common workflows like batch uploads.
The package depends on grpcio, httpx, numpy, protobuf, pydantic, portalocker, and urllib3, keeping the dependency footprint lean. It's actively maintained, supports Python 3.10 through 3.14, and includes optional inference capabilities via FastEmbed for on-device embedding generation. Local mode is particularly useful for prototyping in notebooks or CI/CD pipelines without running a separate server.
Use it for
- Build semantic search into a web app by connecting to a Qdrant Cloud instance with an API key
- Prototype vector search workflows locally in Jupyter or Colab, then migrate to a production server without code changes
- Run integration tests in CI/CD pipelines using in-memory collections without external dependencies
- Upsert and query document embeddings with metadata filtering for retrieval-augmented generation (RAG) applications
- Perform similarity search on image or text embeddings stored in a persistent local database
Worth the install?
AI-flagged interpretation of the facts on this page. Verify before relying on it.
Yes.
qdrant-client is actively maintained, has no known vulnerabilities, minimal install friction, and permissive licensing. Install it if you need to integrate vector search into a Python application—whether for prototyping locally or connecting to a production Qdrant deployment.
Install
qdrant-client on PyPI
Before you install
Low install friction with a pure Python wheel and minimal dependencies. Active maintenance with a recent release (10 days old) and steady repository activity.
Requires Python 3.10 or later.
License in practice
Apache-2.0 permissive license allows free use, modification, and distribution in commercial and private projects with minimal restrictions.
Quickstart
pip install qdrant-client
from qdrant_client import QdrantClient
client = QdrantClient(":memory:")
client.create_collection(
collection_name="my_collection",
vectors_config={"size": 100, "distance": "COSINE"}
)Verify before relying
- Performance characteristics and latency benchmarks for local vs. remote modes
- Scalability limits for in-memory collections and disk-persisted storage
- Compatibility and integration details with specific embedding models beyond FastEmbed
Package facts
| License | Apache-2.0 permissive |
| Python support | Supports the current Python release >=3.10 |
| Install friction | Low. Pure-Python wheel |
| Runtime dependencies | 7 packagesgrpciohttpxnumpyportalockerprotobufpydanticurllib3 |
| Maintenance | Actively maintained 10 days since the last release |
| Last repo commit | |
| First released | |
| Downloads | 22,371,363 / month, #975 on PyPI 30-day window, as of 2026-08-14 |
| Known vulnerabilities | None known OSV.dev, checked 2026-08-14 |
| Classifiers | License :: OSI Approved :: Apache Software LicenseProgramming Language :: Python :: 3Programming Language :: Python :: 3.10Programming Language :: Python :: 3.11Programming Language :: Python :: 3.12Programming Language :: Python :: 3.13Programming Language :: Python :: 3.14 |
Evidence: qdrant_client-1.19.0-py3-none-any.whl
Tags
Let your AI agent find packages like this
Example. Real query, live index.
You found this page by searching. An agent finds it by wishing: SkillFed indexes 14,416 PyPI packages by what they can do, searchable in plain language.
wish › “qdrant python sdk”
- qdrant-clientPython client library for Qdrant vector search engine, supporting…
- opentelemetry-instrumentation-qdrantAdds distributed tracing to Qdrant vector database client calls,…
- langchain-qdrantConnects LangChain applications to Qdrant vector database for…
Give your agent the search over MCP, or paste the wish link into any chat.
More Database packages
psycopg2-binary is a PostgreSQL database adapter for Python that implements the DB API 2.0 specification, enabling Python applications to connect to and query PostgreSQL databases with thread-safe concurrent operations.
Python client library for connecting to and executing commands against Redis key-value stores, supporting both synchronous and asynchronous operations.
Install it if your application needs to interact with Redis; the only prerequisite is a running Redis server instance.
YDB Python SDK is the official client library for connecting to and querying YDB databases from Python applications.
Install it if you need to connect Python applications to YDB databases.
Connects Python applications to Snowflake data warehouses using the DB API 2.0 specification, enabling SQL queries, data transfers, and warehouse operations.
sqlparse tokenizes SQL text into a tree of statements, clauses, and expressions, and provides functions to split scripts, format queries, and inspect parsed tokens without validating dialect or syntax.
Install it if you need to manipulate, format, or analyze SQL text programmatically.
Provides base adapter protocols and shared functionality that database adapters use to integrate with dbt-core, handling connections, dialect translation, relation caching, and core interface management.
See also apache-airflow-providers-qdrant · llama-index-vector-stores-qdrant · opentelemetry-instrumentation-qdrant · langchain-qdrant · mcp-server-qdrant · upstash-vector · pinecone · langchain-mongodb · astrapy · redisvl