Qdrant Python Client

1.17.0 verified Tue May 12 auth: no python install: verified quickstart: verified

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.

pip install qdrant-client

Common errors

error AttributeError: 'QdrantClient' object has no attribute 'search' ↓

cause The `search`, `recommend`, and `discover` methods were deprecated in `qdrant-client` 1.10 and completely removed in 1.14.0.

fix

Use the unified client.query_points() method instead, specifying query_vector and optional query_params (from qdrant_client.models).

error grpc._channel._MultiThreadedRendezvous: <_MultiThreadedRendezvous of RPC that terminated with status #14 and gRPC code 'UNAVAILABLE' ↓

cause The Qdrant client could not establish a connection with the Qdrant server, typically due to the server not running, incorrect host/port, or network/firewall issues.

fix

Verify that the Qdrant server is running and accessible from your client, ensuring the url (e.g., http://localhost:6333) and any API keys are correctly configured in QdrantClient.

error ImportError: cannot import name 'PointStruct' from 'qdrant_client.http.models' ↓

cause Model classes like `PointStruct`, `VectorParams`, and `CollectionConfig` are now directly available from `qdrant_client.models`, not from the internal `qdrant_client.http.models` path.

fix

Update the import statement to from qdrant_client.models import PointStruct (or the respective model class).

error KeyError: 'vector' ↓

cause When upserting points, each point must be a dictionary containing at least an 'id' and a 'vector' key, or be a `PointStruct` object; this error occurs if the 'vector' key is missing.

fix

Ensure each point is a dictionary like {'id': 1, 'vector': [0.1, 0.2, ...]} or a PointStruct object, e.g., PointStruct(id=1, vector=[0.1, 0.2, ...]).

Warnings

breaking client.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/

breaking client.upload_records() removed in 1.14.0. Raises AttributeError. ↓

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

breaking init_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.

breaking Pydantic <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.

gotcha Local 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').

gotcha collection.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.

gotcha AsyncQdrantClient 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.

Install

pip install 'qdrant-client[fastembed]'

Install compatibility verified last tested: 2026-05-12

python os / libc variant status wheel install import disk

3.10 alpine (musl) fastembed - - 2.24s 139.0M

3.10 alpine (musl) qdrant-client - - 4.51s 131.7M

3.10 slim (glibc) fastembed - - 5.92s 305M

3.10 slim (glibc) qdrant-client - - 2.88s 124M

3.11 alpine (musl) fastembed - - 3.15s 148.8M

3.11 alpine (musl) qdrant-client - - 5.65s 141.9M

3.11 slim (glibc) fastembed - - 6.03s 265M

3.11 slim (glibc) qdrant-client - - 3.92s 134M

3.12 alpine (musl) fastembed - - 3.08s 146.5M

3.12 alpine (musl) qdrant-client - - 4.60s 129.7M

3.12 slim (glibc) fastembed - - 6.16s 251M

3.12 slim (glibc) qdrant-client - - 3.79s 122M

3.13 alpine (musl) fastembed - - 3.38s 146.8M

3.13 alpine (musl) qdrant-client - - 4.32s 129.2M

3.13 slim (glibc) fastembed - - 6.03s 251M

3.13 slim (glibc) qdrant-client - - 3.76s 121M

3.9 alpine (musl) fastembed - - 2.14s 146.4M

3.9 alpine (musl) qdrant-client - - 3.90s 138.9M

3.9 slim (glibc) fastembed - - 4.65s 298M

3.9 slim (glibc) qdrant-client - - 3.01s 134M

Imports

query_points (unified search API)

wrong

results = client.search(collection_name='my_col', query_vector=[0.1, 0.2], limit=5)

correct

from qdrant_client import QdrantClient
from qdrant_client.models import Distance, VectorParams, PointStruct, QueryRequest
client = QdrantClient(':memory:')
results = client.query_points(collection_name='my_col', query=[0.1, 0.2], limit=5)

client.search(), client.recommend(), client.discover(), client.search_batch(), client.recommend_batch(), client.discovery_batch() all removed in 1.14.0. Raises AttributeError. Replace all with client.query_points() — the unified interface introduced in 1.10.

upload_points (replaces upload_records)

wrong

client.upload_records(collection_name='my_col', records=[...])

correct

client.upload_points(collection_name='my_col', points=[PointStruct(id=1, vector=[0.1, 0.2], payload={'text': 'hello'})])

upload_records() removed in 1.14.0. Replace with upload_points() using PointStruct objects.

Quickstart verified last tested: 2026-05-12

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)