Qdrant Vector Database Reference

Overview

Qdrant is a high-performance vector database written in Rust, designed for production RAG (Retrieval-Augmented Generation) and semantic search workloads. It supports hybrid search combining vector similarity with metadata filtering, horizontal scaling through sharding and replication, and on-premise deployment for full data control.

When to Use Qdrant

• Building production RAG systems requiring low latency
• Need hybrid search (vectors + metadata filtering)
• Require horizontal scaling with sharding/replication
• Want on-premise deployment with full data control
• Need multi-vector storage per record (dense + sparse)
• Building real-time recommendation systems

Getting Started

Prerequisites

• Python 3.x installed
• pip installed
• Docker installed (for local development)
• Qdrant server running (Docker or cloud)
• qdrant-client library installed
• sentence-transformers library (for RAG example)
• LangChain or LlamaIndex (for framework integrations)

Installation and Basic Usage

Install the Python client and run Qdrant locally with Docker:

# Python client
pip install qdrant-client

# Docker (recommended for development)
docker run -p 6333:6333 -p 6334:6334 qdrant/qdrant

# Docker with persistent storage
docker run -p 6333:6333 -p 6334:6334 \
    -v $(pwd)/qdrant_storage:/qdrant/storage \
    qdrant/qdrant

The Docker command shown is for development; production requires persistent storage volume. Port 6333 is for REST API, port 6334 for gRPC.

Connect to Qdrant, create a collection, insert vectors with payload, and search:

from qdrant_client import QdrantClient
from qdrant_client.models import Distance, VectorParams, PointStruct

# Connect to Qdrant
client = QdrantClient(host="localhost", port=6333)

# Create collection
client.create_collection(
    collection_name="documents",
    vectors_config=VectorParams(size=384, distance=Distance.COSINE)
)

# Insert vectors with payload
client.upsert(
    collection_name="documents",
    points=[
        PointStruct(
            id=1,
            vector=[0.1, 0.2, ...],  # 384-dim vector
            payload={"title": "Doc 1", "category": "tech"}
        ),
        PointStruct(
            id=2,
            vector=[0.3, 0.4, ...],
            payload={"title": "Doc 2", "category": "science"}
        )
    ]
)

# Search with filtering (query_points is the current API; client.search is removed in qdrant-client 1.14+)
response = client.query_points(
    collection_name="documents",
    query=[0.15, 0.25, ...],
    query_filter={
        "must": [{"key": "category", "match": {"value": "tech"}}]
    },
    limit=10
)

for point in response.points:
    print(f"ID: {point.id}, Score: {point.score}, Payload: {point.payload}")

client.search is removed in qdrant-client 1.14+; use query_points instead. query_points returns a QueryResponse; access results via .points.

Data Model

Points

A point is the fundamental unit of data, consisting of an ID, one or more vectors, and a payload:

from qdrant_client.models import PointStruct

# Point = ID + Vector(s) + Payload
point = PointStruct(
    id=123,                              # Integer or UUID string
    vector=[0.1, 0.2, 0.3, ...],        # Dense vector
    payload={                            # Arbitrary JSON metadata
        "title": "Document title",
        "category": "tech",
        "timestamp": 1699900000,
        "tags": ["python", "ml"]
    }
)

# Batch upsert (recommended)
client.upsert(
    collection_name="documents",
    points=[point1, point2, point3],
    wait=True  # Wait for indexing
)

Collection Configuration

Vector Parameters

Create a collection with vector size and distance metric:

from qdrant_client.models import VectorParams, Distance, HnswConfigDiff

# Create with HNSW configuration
client.create_collection(
    collection_name="documents",
    vectors_config=VectorParams(
        size=384,                        # Vector dimensions
        distance=Distance.COSINE         # COSINE, EUCLID, DOT, MANHATTAN
    ),
    hnsw_config=HnswConfigDiff(
        m=16,                            # Connections per node (default 16)
        ef_construct=100,                # Build-time accuracy (default 100)
        full_scan_threshold=10000        # Switch to brute force below this
    ),
    on_disk_payload=True                 # Store payload on disk
)

# Collection info
info = client.get_collection("documents")
print(f"Points: {info.points_count}, Vectors: {info.vectors_count}")

Supported distance metrics: COSINE, EUCLID, DOT, MANHATTAN. The on_disk_payload parameter stores payload on disk instead of RAM, recommended for large payloads.

Search Operations

Simple Search

# Simple nearest neighbor search (returns a QueryResponse; use .points)
response = client.query_points(
    collection_name="documents",
    query=[0.1, 0.2, ...],
    limit=10,
    with_payload=True,
    with_vectors=False  # Don't return vectors (faster)
)
results = response.points

Filtered Search

Use Filter, FieldCondition, MatchValue, and Range objects for complex filtering:

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

# Complex filtering
response = client.query_points(
    collection_name="documents",
    query=query_embedding,
    query_filter=Filter(
        must=[
            FieldCondition(key="category", match=MatchValue(value="tech")),
            FieldCondition(key="timestamp", range=Range(gte=1699000000))
        ],
        must_not=[
            FieldCondition(key="status", match=MatchValue(value="archived"))
        ]
    ),
    limit=10
).points

# Shorthand filter syntax
response = client.query_points(
    collection_name="documents",
    query=query_embedding,
    query_filter={
        "must": [
            {"key": "category", "match": {"value": "tech"}},
            {"key": "price", "range": {"gte": 10, "lte": 100}}
        ]
    },
    limit=10
).points

Batch Search

search_batch is replaced by query_batch_points. Send multiple queries in one request:

from qdrant_client.models import QueryRequest

# Multiple queries in one request (search_batch is replaced by query_batch_points)
responses = client.query_batch_points(
    collection_name="documents",
    requests=[
        QueryRequest(query=[0.1, ...], limit=5),
        QueryRequest(query=[0.2, ...], limit=5, filter={"must": [...]}),
        QueryRequest(query=[0.3, ...], limit=10)
    ]
)
# Each element is a QueryResponse; use .points
for resp in responses:
    for point in resp.points:
        print(point.id, point.score)

query_batch_points returns a list of QueryResponse objects.

RAG Integration

With sentence-transformers

from sentence_transformers import SentenceTransformer
from qdrant_client import QdrantClient
from qdrant_client.models import VectorParams, Distance, PointStruct

# Initialize
encoder = SentenceTransformer("all-MiniLM-L6-v2")
client = QdrantClient(host="localhost", port=6333)

# Create collection
client.create_collection(
    collection_name="knowledge_base",
    vectors_config=VectorParams(size=384, distance=Distance.COSINE)
)

# Index documents
documents = [
    {"id": 1, "text": "Python is a programming language", "source": "wiki"},
    {"id": 2, "text": "Machine learning uses algorithms", "source": "textbook"},
]

points = [
    PointStruct(
        id=doc["id"],
        vector=encoder.encode(doc["text"]).tolist(),
        payload={"text": doc["text"], "source": doc["source"]}
    )
    for doc in documents
]
client.upsert(collection_name="knowledge_base", points=points)

# RAG retrieval
def retrieve(query: str, top_k: int = 5) -> list[dict]:
    query_vector = encoder.encode(query).tolist()
    response = client.query_points(
        collection_name="knowledge_base",
        query=query_vector,
        limit=top_k
    )
    return [{"text": r.payload["text"], "score": r.score} for r in response.points]

# Use in RAG pipeline
context = retrieve("What is Python?")
prompt = f"Context: {context}\n\nQuestion: What is Python?"

With LangChain

from langchain_community.vectorstores import Qdrant
from langchain_community.embeddings import HuggingFaceEmbeddings

embeddings = HuggingFaceEmbeddings(model_name="all-MiniLM-L6-v2")
vectorstore = Qdrant.from_documents(documents, embeddings, url="http://localhost:6333", collection_name="docs")
retriever = vectorstore.as_retriever(search_kwargs={"k": 5})

With LlamaIndex

from llama_index.vector_stores.qdrant import QdrantVectorStore
from llama_index.core import VectorStoreIndex, StorageContext

vector_store = QdrantVectorStore(client=client, collection_name="llama_docs")
storage_context = StorageContext.from_defaults(vector_store=vector_store)
index = VectorStoreIndex.from_documents(documents, storage_context=storage_context)
query_engine = index.as_query_engine()

Advanced Features

Multi-Vector Support (Named Vectors)

Create a collection with multiple named vectors, insert points with a dictionary of embeddings, and search a specific vector using the using parameter:

from qdrant_client.models import VectorParams, Distance

# Collection with multiple vector types
client.create_collection(
    collection_name="hybrid_search",
    vectors_config={
        "dense": VectorParams(size=384, distance=Distance.COSINE),
        "sparse": VectorParams(size=30000, distance=Distance.DOT)
    }
)

# Insert with named vectors
client.upsert(
    collection_name="hybrid_search",
    points=[
        PointStruct(
            id=1,
            vector={
                "dense": dense_embedding,
                "sparse": sparse_embedding
            },
            payload={"text": "document text"}
        )
    ]
)

# Search specific named vector (pass the vector name via `using`)
response = client.query_points(
    collection_name="hybrid_search",
    query=query_dense,
    using="dense",  # Specify which named vector to search
    limit=10
)
results = response.points

Sparse Vectors

Create a collection with sparse vector configuration, insert SparseVector objects, and search:

from qdrant_client.models import SparseVectorParams, SparseIndexParams, SparseVector

# Collection with sparse vectors
client.create_collection(
    collection_name="sparse_search",
    vectors_config={},
    sparse_vectors_config={"text": SparseVectorParams(index=SparseIndexParams(on_disk=False))}
)

# Insert sparse vector
client.upsert(
    collection_name="sparse_search",
    points=[PointStruct(id=1, vector={"text": SparseVector(indices=[1, 5, 100], values=[0.5, 0.8, 0.2])}, payload={"text": "document"})]
)

Quantization

Enable scalar quantization for memory efficiency (recommended for collections over 1 million vectors):

from qdrant_client.models import ScalarQuantization, ScalarQuantizationConfig, ScalarType

# Scalar quantization (4x memory reduction)
client.create_collection(
    collection_name="quantized",
    vectors_config=VectorParams(size=384, distance=Distance.COSINE),
    quantization_config=ScalarQuantization(
        scalar=ScalarQuantizationConfig(
            type=ScalarType.INT8,
            quantile=0.99,        # Clip outliers
            always_ram=True      # Keep quantized in RAM
        )
    )
)

# Search with rescoring
response = client.query_points(
    collection_name="quantized",
    query=query,
    search_params={"quantization": {"rescore": True}},  # Rescore top results
    limit=10
)
results = response.points

Payload Indexing

Create payload indexes for faster filtered searches:

from qdrant_client.models import PayloadSchemaType

# Create payload index for faster filtering
client.create_payload_index(
    collection_name="documents",
    field_name="category",
    field_schema=PayloadSchemaType.KEYWORD
)

client.create_payload_index(
    collection_name="documents",
    field_name="timestamp",
    field_schema=PayloadSchemaType.INTEGER
)

# Index types: KEYWORD, INTEGER, FLOAT, GEO, TEXT (full-text), BOOL

Payload indexing is required for fast filtered searches.

Performance and Deployment

Performance Tuning

Adjust HNSW parameters for search speed or indexing speed:

# Optimize for search speed (higher recall)
client.update_collection(
    collection_name="documents",
    hnsw_config=HnswConfigDiff(ef_construct=200, m=32)
)

# Optimize for indexing speed (bulk loads)
client.update_collection(
    collection_name="documents",
    optimizer_config={"indexing_threshold": 20000}
)

Production Deployment

Connect to Qdrant Cloud:

from qdrant_client import QdrantClient

# Connect to Qdrant Cloud
client = QdrantClient(
    url="https://your-cluster.cloud.qdrant.io",
    api_key="your-api-key"
)

Failure Modes and Solutions

Slow search with filters

Create a payload index for the filtered fields:

# Create payload index for filtered fields
client.create_payload_index(
    collection_name="docs",
    field_name="category",
    field_schema=PayloadSchemaType.KEYWORD
)

Out of memory

Enable quantization and on-disk storage:

# Enable quantization and on-disk storage
client.create_collection(
    collection_name="large_collection",
    vectors_config=VectorParams(size=384, distance=Distance.COSINE),
    quantization_config=ScalarQuantization(...),
    on_disk_payload=True
)

Connection issues

Use timeout, retry, and prefer gRPC for better performance:

# Use timeout and retry
client = QdrantClient(
    host="localhost",
    port=6333,
    timeout=30,
    prefer_grpc=True  # gRPC for better performance
)

Additional Notes

• Reuse client instances for connection pooling.
• Sharding is recommended for collections over 10 million vectors.
• Version: 1.14.0+
• License: Apache 2.0