Qdrant Has a Free API — Vector Search for AI Applications

#qdrant #vectordb #ai #api

Qdrant is an open-source vector database built for AI. It powers semantic search, recommendation systems, and RAG applications with a simple REST API.

What Is Qdrant?

Qdrant stores and searches high-dimensional vectors with metadata filtering. It is designed for production AI workloads.

Free tier (Qdrant Cloud):

1GB storage
1 cluster
No credit card

Quick Start

docker run -p 6333:6333 qdrant/qdrant

REST API

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

# Insert vectors
curl -X PUT http://localhost:6333/collections/my_docs/points \
  -d '{"points":[{"id":1,"vector":[0.1,0.2,0.3,...],"payload":{"title":"AI Guide","category":"tutorial"}}]}'

# Search
curl -X POST http://localhost:6333/collections/my_docs/points/search \
  -d '{"vector":[0.1,0.2,0.3,...],"limit":5,"filter":{"must":[{"key":"category","match":{"value":"tutorial"}}]}}'

Python SDK

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

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

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

client.upsert("docs", points=[
    PointStruct(id=1, vector=[0.1]*384, payload={"title": "AI Guide"})
])

results = client.search("docs", query_vector=[0.1]*384, limit=5)