Complete Qdrant Tutorial: Vector Database for AI Applications

Qdrant is a high-performance vector database designed for similarity search and AI applications. It provides efficient storage and retrieval of vector embeddings, making it ideal for building recommendation systems, semantic search, and RAG applications.

Why Qdrant?

• High performance: Rust-based engine for speed
• Rich filtering: Combine vector search with metadata filters
• Scalable: Distributed mode for large datasets
• Easy to use: REST and gRPC APIs
• Cloud native: Docker, Kubernetes ready

• Semantic search
• Recommendation systems
• RAG (Retrieval-Augmented Generation)
• Image similarity search
• Anomaly detection

Installation

# Python client
pip install qdrant-client

Run Qdrant with Docker
docker run -p 6333:6333 -p 6334:6334 \
    -v $(pwd)/qdrantstorage:/qdrant/storage:z \

    qdrant/qdrant

Verify
python -c "from qdrantclient import QdrantClient; print('Qdrant client ready')"

Quick Start

1. Connect to Qdrant

from qdrantclient import QdrantClient

Local instance
client = QdrantClient("localhost", port=6333)

In-memory (for testing)
client = QdrantClient(":memory:")

Qdrant Cloud
client = QdrantClient(
    url="https://xxx-xxx.us-east-1-0.aws.cloud.qdrant.io",
    apikey="your-api-key"
)

Check connection
print(client.getcollections())

from qdrantclient import QdrantClient
from qdrantclient.models import Distance, VectorParams


client = QdrantClient("localhost", port=6333)

Create collection
client.createcollection(
    collectionname="mycollection",
    vectorsconfig=VectorParams(size=384, distance=Distance.COSINE)

)

List collections
collections = client.getcollections()
print(collections)

3. Insert Vectors

from qdrantclient.models import PointStruct

Insert points
client.upsert(
    collectionname="mycollection",

    points=[
        PointStruct(
            id=1,
            vector=[0.1, 0.2, 0.3, ...],  # 384-dim vector
            payload={"title": "Document 1", "category": "tech"}
        ),
        PointStruct(
            id=2,
            vector=[0.4, 0.5, 0.6, ...],
            payload={"title": "Document 2", "category": "science"}
        )
    ]
)

# Search
results = client.search(
    collectionname="mycollection",

    queryvector=[0.1, 0.2, 0.3, ...],
    limit=5
)

for result in results:
    print(f"ID: {result.id}, Score: {result.score}")
    print(f"Payload: {result.payload}")

Working with Embeddings

1. Using Sentence Transformers

from qdrantclient import QdrantClient
from qdrantclient.models import Distance, VectorParams, PointStruct
from sentencetransformers import SentenceTransformer


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

Create collection
client.recreatecollection(
    collectionname="documents",

    vectorsconfig=VectorParams(size=384, distance=Distance.COSINE)
)

Prepare documents
documents = [
    {"id": 1, "text": "Machine learning is fascinating", "category": "tech"},
    {"id": 2, "text": "Natural language processing", "category": "tech"},
    {"id": 3, "text": "Cooking recipes for beginners", "category": "food"},
]

Generate embeddings and insert
points = []
for doc in documents:
    embedding = model.encode(doc["text"]).tolist()
    points.append(PointStruct(
        id=doc["id"],
        vector=embedding,
        payload={"text": doc["text"], "category": doc["category"]}
    ))

client.upsert(collectionname="documents", points=points)


Search
query = "AI and deep learning"