Qdrant API on YDB

Drop‑in Qdrant REST API with single‑phase top‑k search using YDB vector index (auto‑built).

Getting started

Configure in Roo Code/Kilo Code

Request flow: IDE/Agent → ydb-qdrant (Node.js) → YDB vectors + index

Options

Self‑host: http://localhost:8080
Public demo: http://ydb-qdrant.tech:8080 (shared)

Docs

Configure self‑hosted

Clone and install: npm install
Set env: YDB_ENDPOINT, YDB_DATABASE
Auth via env: YDB_SERVICE_ACCOUNT_KEY_FILE_CREDENTIALS | YDB_METADATA_CREDENTIALS | YDB_ACCESS_TOKEN_CREDENTIALS | YDB_ANONYMOUS_CREDENTIALS
Run: npm run dev (dev) or npm start (prod)
Point client to http://localhost:8080

Details: GitHub README

Purpose

Use as a Qdrant base URL for IDE agents or apps; vectors persist in YDB.

Key features

Qdrant‑compatible endpoints
Single‑phase top‑k using YDB vector index (auto‑built); table‑scan fallback
Per‑tenant isolation
Self‑host or demo

Quick example

curl -X PUT http://localhost:8080/collections/mycol \
  -H 'Content-Type: application/json' \
  -d '{"vectors":{"size":384,"distance":"Cosine","data_type":"float"}}'

curl -X POST http://localhost:8080/collections/mycol/points/upsert \
  -H 'Content-Type: application/json' \
  -d '{"points":[{"id":"1","vector":[0.1,0.2,...384 vals...]}]}'

curl -X POST http://localhost:8080/collections/mycol/points/search \
  -H 'Content-Type: application/json' \
  -d '{"vector":[0.1,0.2,...],"limit":5,"with_payload":true}'

Health: GET /health → {"status":"ok"}