How to Set Up a Vector Database with Qdrant

How to Set Up a Vector Database with Qdrant

Qdrant is an open-source vector similarity search engine designed for storing and querying high-dimensional embedding vectors. It is essential for building semantic search, recommendation systems, and retrieval-augmented generation (RAG) pipelines on your Breeze.

Prerequisites

• A Breeze instance with at least 2 GB of RAM
• Docker installed (recommended) or Rust toolchain for building from source
• Basic familiarity with REST APIs

Installing Qdrant with Docker

The simplest way to get Qdrant running on your Breeze is with Docker:

docker pull qdrant/qdrant
docker run -d --name qdrant \
  -p 6333:6333 -p 6334:6334 \
  -v /data/qdrant:/qdrant/storage \
  qdrant/qdrant

Port 6333 serves the REST API and port 6334 serves the gRPC API. The data is persisted to /data/qdrant on your Breeze.

Installing Without Docker

If you prefer running natively, download the pre-built binary:

wget https://github.com/qdrant/qdrant/releases/latest/download/qdrant-x86_64-unknown-linux-musl.tar.gz
tar xzf qdrant-x86_64-unknown-linux-musl.tar.gz
./qdrant

Creating a Collection

Collections in Qdrant store vectors with associated metadata (payloads). Create one using the REST API:

curl -X PUT http://localhost:6333/collections/documents \
  -H "Content-Type: application/json" \
  -d '{
    "vectors": {
      "size": 384,
      "distance": "Cosine"
    }
  }'

The vector size should match your embedding model’s output dimension. For example, all-MiniLM-L6-v2 produces 384-dimensional vectors.

Inserting Vectors

Upsert points (vectors with payloads) into your collection:

curl -X PUT http://localhost:6333/collections/documents/points \
  -H "Content-Type: application/json" \
  -d '{
    "points": [
      {"id": 1, "vector": [0.1, 0.2, ...], "payload": {"title": "Getting Started", "category": "tutorial"}},
      {"id": 2, "vector": [0.3, 0.4, ...], "payload": {"title": "Advanced Usage", "category": "guide"}}
    ]
  }'

Searching for Similar Vectors

Query the collection to find the most similar vectors:

curl -X POST http://localhost:6333/collections/documents/points/search \
  -H "Content-Type: application/json" \
  -d '{
    "vector": [0.1, 0.2, ...],
    "limit": 5,
    "with_payload": true
  }'

Qdrant returns the top matches ranked by similarity score, along with their payloads.

Using the Python Client

For programmatic access from your application, install the Python client:

pip install qdrant-client sentence-transformers

from qdrant_client import QdrantClient
from sentence_transformers import SentenceTransformer

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

query_vector = encoder.encode("How do I deploy my application?").tolist()
results = client.search(collection_name="documents", query_vector=query_vector, limit=5)
for r in results:
    print(r.payload["title"], r.score)

Enabling API Key Authentication

Protect your Qdrant instance by setting an API key in the configuration file or via environment variable:

docker run -d --name qdrant \
  -p 6333:6333 \
  -e QDRANT__SERVICE__API_KEY=your-secret-key \
  qdrant/qdrant

With this configuration, all requests to your Qdrant instance on your Breeze must include the api-key header.