Registry / vector-search / qdrant-client

qdrant-client

library1.19.0pypypi✓ verified 14d ago

Official Python client for the Qdrant vector search engine. Supports both remote server (gRPC or REST) and local in-memory/on-disk mode without a running server. All data operations use query_points() as the unified interface as of 1.10+. Prior search/recommend/discover methods removed in 1.14.0. Bundles FastEmbed for optional local embedding generation. Async support via AsyncQdrantClient.

vector-search database http-networking ai-ml llm-agents

pip install qdrant-client

github ↗package ↗homepage ↗

INSTALL

IMPORT

SIG · QDRANT-CLIENT

qdrant-client

vector-searchpythonv1.19.0

Install

11.7s avg

Import

4163ms

Disk

210MB

Pass rate

10/ 10

Env Coverage10 / 10

glibc

3.9–3.13

musl

3.9–3.13

Install & Compatibility

Where this runs

tested against v1.5.0 · pip install

no network on importno background threads

Install × environment matrix

Each cell = how many times install + import succeeded across repeated harness runs. Partial = flaky.
glibc = Debian/Ubuntu slim · musl = Alpine Linux

musl

py 3.10–3.910 runs

installs and imports cleanly · install 0.0s · import 3.719s · 139.6MB

glibc

py 3.10–3.910 runs

installs and imports cleanly · install 11.7s · import 4.606s · 298MB

210MB installed

● package 210MB

Code

Verified usage

Verified import paths — ran on the pinned version, not inferred.

QdrantClient

✓ from qdrant_client import QdrantClient

✗ from qdrant_client import QdrantClient

AsyncQdrantClient

✓ from qdrant_client import AsyncQdrantClient

✗ from qdrant_client import AsyncQdrantClient

models

✓ from qdrant_client import models

✗ from qdrant_client.models import Distance, VectorParams, PointStruct, QueryRequest

query_points() is the unified search interface in 1.10+. upload_points() replaces the removed upload_records().

from qdrant_client import QdrantClient from qdrant_client.models import Distance, VectorParams, PointStruct # In-memory (no server needed) client = QdrantClient(':memory:') # Persistent local mode # client = QdrantClient(path='/path/to/db') # Remote server # client = QdrantClient(url='http://localhost:6333') client.create_collection( collection_name='my_docs', vectors_config=VectorParams(size=4, distance=Distance.COSINE), ) client.upload_points( collection_name='my_docs', points=[ PointStruct(id=1, vector=[0.1, 0.2, 0.3, 0.4], payload={'text': 'hello'}), PointStruct(id=2, vector=[0.5, 0.6, 0.7, 0.8], payload={'text': 'world'}), ], ) results = client.query_points( collection_name='my_docs', query=[0.1, 0.2, 0.3, 0.4], limit=2, ) print(results.points)

Debug

Known issues

breakingclient.search(), client.recommend(), client.discover(), client.search_batch(), client.recommend_batch(), client.discovery_batch() all removed in 1.14.0. Massive amount of tutorials, LangChain/LlamaIndex integrations, and LLM-generated code uses client.search(). Raises AttributeError on 1.14+.

fix

Replace all with client.query_points(). For batch: client.query_batch_points(). Migration guide: qdrant.tech/documentation/concepts/search/

affects: >= 1.14.0

breakingclient.upload_records() removed in 1.14.0. Raises AttributeError.

fix

Replace with client.upload_points() using PointStruct(id=..., vector=..., payload=...) objects.

affects: >= 1.14.0

breakinginit_from parameter in create_collection() removed in 1.14.0.

fix

Use client.update_collection_aliases() or migrate data manually if you were using init_from for collection cloning.

affects: >= 1.14.0

breakingPydantic <2.2.1 is not supported. Supported versions are v1.10.x and >=2.2.1. Intermediate Pydantic 2.0–2.2.0 raises validation errors.

fix

Pin pydantic to either >=1.10,<2.0 or >=2.2.1. Avoid 2.0.0–2.2.0.

affects: all recent

gotchaLocal in-memory mode (QdrantClient(':memory:')) does not persist. Data is lost when the process exits. QdrantClient(path='...') persists to disk but does not support concurrent multi-process access.

fix

For production or multi-process access, run a Qdrant server (Docker or binary) and connect via QdrantClient(url='http://localhost:6333').

affects: all

gotchacollection.query_points() offset parameter is no longer propagated into prefetches for nested queries. Pre-1.13 behavior silently passed offset into sub-queries; current behavior does not.

fix

Apply offset only at the top-level query_points() call, not in nested prefetch structures.

affects: >= 1.13.0

gotchaAsyncQdrantClient raw gRPC methods are not accessible from the sync QdrantClient as of 1.11. Mixing sync client with raw async gRPC calls raises AttributeError.

fix

Use AsyncQdrantClient for async gRPC operations. Do not attempt to access .grpc_* methods from the synchronous QdrantClient.

affects: >= 1.11.0

Upgrade

Version history

1.19.0latest on PyPI · released Aug 4, 2026

Audit

Dependencies

grpciorequiredRequired. Used for gRPC transport to remote Qdrant server. Also required for local mode.

httpxrequiredRequired. REST transport.

numpyrequiredRequired.

fastembedoptionalOptional. Only with fastembed extra. Adds ONNX-based local embedding generation (~200MB+ model downloads on first use).

Agent activity

159 hits · last 30 days

node

148

Amazon

OpenAI (training)

Resources

githubhttps://github.com/qdrant/qdrant-client ↗

packagehttps://pypi.org/project/qdrant-client/ ↗

homepagehttps://qdrant.tech ↗