qdrant / qdrant_client

Python client for Qdrant vector search engine

Python Qdrant client library

Client library for the Qdrant vector search engine.

Library contains type definitions for all Qdrant API and allows to make both Sync and Async requests.

Pydantic is used for describing request models and httpx for handling http queries.

Client allows calls for all Qdrant API methods directly. It also provides some additional helper methods for frequently required operations, e.g. initial collection uploading.

Installation

pip install qdrant-client

Development

This project uses git hooks to run code formatters.

Install pre-commit with pip3 install pre-commit and set up hooks with pre-commit install.

pre-commit requires python>=3.8

Examples

Instance a client

from qdrant_client import QdrantClient

client = QdrantClient(host="localhost", port=6333)
# or
client = QdrantClient(url="http://localhost:6333")

Create a new collection

from qdrant_client.models import Distance, VectorParams

client.recreate_collection(
    collection_name="my_collection",
    vectors_config=VectorParams(size=100, distance=Distance.COSINE),
)

Get info about created collection

my_collection_info = client.get_collection("my_collection")
print(my_collection_info.dict())

Insert vectors into a collection

import numpy as np
from qdrant_client.models import PointStruct

vectors = np.random.rand(100, 100)
client.upsert(
    collection_name="my_collection",
    points=[
        PointStruct(
            id=idx,
            vector=vector.tolist(),
        )
        for idx, vector in enumerate(vectors)
    ]
)

Search for similar vectors

query_vector = np.random.rand(100)
hits = client.search(
    collection_name="my_collection",
    query_vector=query_vector,
    query_filter=None,  # Don't use any filters for now, search across all indexed points
    append_payload=True,  # Also return a stored payload for found points
    limit=5  # Return 5 closest points
)

Search for similar vectors with filtering condition

from qdrant_client.http.models import Filter, FieldCondition, Range

hits = client.search(
    collection_name="my_collection",
    query_vector=query_vector,
    query_filter=Filter(
        must=[  # These conditions are required for search results
            FieldCondition(
                key='rand_number',  # Condition based on values of `rand_number` field.
                range=Range(
                    gte=0.5  # Select only those results where `rand_number` >= 0.5
                )
            )
        ]
    ),
    append_payload=True,  # Also return a stored payload for found points
    limit=5  # Return 5 closest points
)

Check out full example code

gRPC

gRPC support in Qdrant client is under active development. Basic classes could be found here.

To enable (much faster) collection uploading with gRPC, use the following initialization:

from qdrant_client import QdrantClient

client = QdrantClient(host="localhost", grpc_port=6334, prefer_grpc=True)