Qdrant: The Vector Database Built for Production RAG Pipelines

Qdrant combines HNSW indexing, hybrid search, and rich payload filtering in a Rust-native vector database that scales from Docker to multi-node Qdrant Cloud.

Mahmudul Haque Qudrati

CEO & ML Engineer

April 12, 2026

8 min read

// tags

#qdrant#vector-database#rag#embeddings#similarity-search

FIG. ART-26

8 min read

“

Qdrant: The Vector Database Built for Production RAG Pipelines

// reading plan

sections

366

words

min read

// Developer Tools

OpenAI Codex Issue #2847: Excluding Sensitive Files Still Unresolved – Workarounds and Risks

OpenAI Codex issue #2847 about excluding sensitive files from context is still unresolved. This post covers the problem, current workarounds, and why it's a critical missing feature for production use.

3 min read

// Developer Tools

Docker Setup

docker run -d   -p 6333:6333   -v $(pwd)/qdrant_storage:/qdrant/storage   qdrant/qdrant

The REST API is available at http://localhost:6333. The dashboard UI is at http://localhost:6333/dashboard.

Python SDK

pip install qdrant-client sentence-transformers

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

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

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

# Insert documents
texts = ["PagedAttention manages KV cache as pages.", "HNSW is a graph-based ANN index."]
vectors = encoder.encode(texts).tolist()

client.upsert(
    collection_name="docs",
    points=[
        PointStruct(id=i, vector=v, payload={"text": t, "source": "technical-docs"})
        for i, (v, t) in enumerate(zip(vectors, texts))
    ],
)

# Search with payload filter
query_vector = encoder.encode("how does memory management work in LLMs").tolist()
results = client.search(
    collection_name="docs",
    query_vector=query_vector,
    query_filter={"must": [{"key": "source", "match": {"value": "technical-docs"}}]},
    limit=3,
)
for r in results:
    print(r.score, r.payload["text"])

Hybrid Search (Dense + Sparse)

Qdrant supports named vectors - include both a dense embedding and a sparse BM25 vector per point:

from qdrant_client.models import NamedVector

client.search_batch(
    collection_name="docs",
    requests=[
        # dense semantic search
        NamedVector(name="dense", vector=dense_query),
        # sparse keyword search
        NamedVector(name="sparse", vector=sparse_query),
    ],
)

Combine results with Reciprocal Rank Fusion for best-of-both retrieval.

Distance Metrics

Metric	Use case
Cosine	Text embeddings (default)
Dot Product	When vectors are pre-normalized
Euclidean	Image embeddings

Qdrant Cloud

For production, Qdrant Cloud provides a managed cluster with automatic backups, horizontal scaling, and a free 1 GB tier. Switch by changing the client URL:

client = QdrantClient(
    url="https://your-cluster.qdrant.io",
    api_key="YOUR_API_KEY",
)

Full documentation at qdrant.tech.

Qdrant: The Vector Database Built for Production RAG Pipelines

Related Articles

OpenAI Codex Issue #2847: Excluding Sensitive Files Still Unresolved – Workarounds and Risks

Why Qdrant for Production RAG

Core Concepts

Docker Setup

Python SDK

Hybrid Search (Dense + Sparse)

Distance Metrics

Qdrant Cloud

The workspace your team
actually needs

AI & ML insights, weekly

Mahmudul Haque Qudrati

What Is Alibaba Banning Claude Code Over Backdoor Risks? A Practical Overview

Claude Code Sends 33k Tokens Before Reading the Prompt; OpenCode Sends 7k: A Practical Overview

Qdrant: The Vector Database Built for Production RAG Pipelines

Related Articles

OpenAI Codex Issue #2847: Excluding Sensitive Files Still Unresolved – Workarounds and Risks

Why Qdrant for Production RAG

Core Concepts

Docker Setup

Python SDK

Hybrid Search (Dense + Sparse)

Distance Metrics

Qdrant Cloud

The workspace your teamactually needs

AI & ML insights, weekly

Mahmudul Haque Qudrati

What Is Alibaba Banning Claude Code Over Backdoor Risks? A Practical Overview

Claude Code Sends 33k Tokens Before Reading the Prompt; OpenCode Sends 7k: A Practical Overview

The workspace your team
actually needs