@ragfoundry/adapter-vector-qdrant

🗄️ Qdrant vector store adapter. Store and search embeddings in Qdrant, self-hosted or Qdrant Cloud.

A VectorStore adapter for RAGFoundry — typed retrieval-augmented generation for TypeScript.

💡 New to RAGFoundry? This page is for adding one specific provider to an app you're already building. Starting a project from scratch is faster with the scaffolder — it asks a few questions and wires everything (including this adapter, if you pick it) for you:

npm create @ragfoundry my-app

→ @ragfoundry/create

📦 Install

npm install @ragfoundry/core @ragfoundry/adapter-vector-qdrant

🚀 Usage

Works with both import and require — this package ships both builds.

ESM:

import { createRAG } from "@ragfoundry/core"
import "@ragfoundry/adapter-vector-qdrant"

const rag = createRAG({
  vectorStore: {
    provider: "qdrant",
    url: process.env.QDRANT_URL ?? "http://localhost:6333",
    collectionName: "documents",
  },
  // ...the rest of your config
})

CommonJS:

const { createRAG } = require("@ragfoundry/core")
require("@ragfoundry/adapter-vector-qdrant")

const rag = createRAG({
  vectorStore: {
    provider: "qdrant",
    url: process.env.QDRANT_URL ?? "http://localhost:6333",
    collectionName: "documents",
  },
  // ...the rest of your config
})

⚠️ The import/require is what registers "qdrant" at runtime — remove it and createRAG throws Unknown adapter "qdrant", even though the provider name is still typed correctly. In TypeScript it's also what makes the vectorStore block above autocomplete and type-check.

⚙️ Options

| Option | Type | Required | Default | |---|---|---|---| | url | string | yes | — | | collectionName | string | yes | — | | apiKey | string | no | — |

Collection

Create it first, sized to your embedding model:

curl -X PUT "$QDRANT_URL/collections/documents" \
  -H 'content-type: application/json' \
  -d '{"vectors":{"size":768,"distance":"Cosine"}}'

Point ids

Qdrant accepts only unsigned integers or UUIDs as point ids, but chunk ids are readable strings like guide.md-3. The adapter hashes the logical id into a deterministic UUIDv5 and keeps the original in the payload, so re-ingesting a document overwrites its points instead of duplicating them — and queries still return the id you wrote. Ids Qdrant already accepts pass through untouched.

🔗 See also

• @ragfoundry/core — the pipelines, types, and every export explained
• @ragfoundry/create — npm create @ragfoundry, scaffold a whole project

📄 License

MIT