Reference · Glossary

Qdrant

Last updated

An **open-source vector database** written in Rust, known for fast filtered search and built-in vector quantization to shrink memory use at scale. Available self-hosted or as a managed cloud.

#When to use

High-throughput search with heavy metadata filtering (e.g. "similar products, in stock, under $50"), or when you want quantization to cut hosting costs on large collections.

#When not to

A one-off prototype where the ops overhead of running/monitoring a service isn't worth it yet — start with an in-process store first.

#Example

from qdrant_client import QdrantClient
client = QdrantClient(url="http://localhost:6333")
client.upsert(
    collection_name="docs",
    points=[{"id": 1, "vector": [0.1, 0.2, 0.3], "payload": {"source": "faq.md"}}],
)
hits = client.query_points(collection_name="docs", query=[0.1, 0.2, 0.3], limit=3)