// $ npm install turbopuffer import { Turbopuffer } from "@turbopuffer/turbopuffer"; const tpuf = new Turbopuffer({ // API tokens are created in the dashboard https://turbopuffer.com/dashboard apiKey: process.env.TURBOPUFFER_API_KEY, // Pick the right region https://turbopuffer.com/docs/regions baseUrl: "https://gcp-us-central1.turbopuffer.com", }); const ns = tpuf.namespace(`namespace-a-ts-${Date.now()}`); // Upsert documents with vectors and attributes await ns.upsert({ vectors: [ { id: 1, vector: await openaiOrRandVector("walrus narwhal"), attributes: { name: "foo", public: 1, text: "walrus narwhal", }, }, { id: 2, vector: await openaiOrRandVector("elephant walrus rhino"), attributes: { name: "foo", public: 0, text: "elephant walrus rhino", }, }, ], distance_metric: "cosine_distance", schema: { text: { // Configure FTS/BM25, other attributes have inferred types (name: str, public: int) type: "string", // More schema & FTS options https://turbopuffer.com/docs/schema full_text_search: true, }, }, }); // Query nearest neighbors with filter let results = await ns.query({ vector: await openaiOrRandVector("walrus narwhal"), top_k: 10, distance_metric: "cosine_distance", filters: [ "And", [ ["name", "Eq", "foo"], ["public", "Eq", 1], ], ], include_attributes: ["name"], include_vectors: false, }); console.log(results); // [{ id: 1, attributes: { name: 'foo' }, dist: 0.009067952632904053 }] // Full-text search on an attribute // If you want to combine FTS and vector search, see https://turbopuffer.com/docs/hybrid-search results = await ns.query({ top_k: 10, distance_metric: "cosine_distance", filters: ["name", "Eq", "foo"], rank_by: ["text", "BM25", "quick walrus"], }); console.log(results); // [{ id: 1, attributes: { name: 'foo' }, dist: 0.19 }] // [{ id: 2, attributes: { name: 'foo' }, dist: 0.168 }] // Vectors can be updated by passing new data for an existing ID await ns.upsert({ vectors: [ { id: 1, vector: await openaiOrRandVector("foo"), attributes: { name: "foo", public: 1, }, }, { id: 2, vector: await openaiOrRandVector("foo"), attributes: { name: "foo", public: 1, }, }, { id: 3, vector: await openaiOrRandVector("foo"), attributes: { name: "foo", public: 1, }, }, ], distance_metric: "cosine_distance", }); // Vectors are deleted by ID await ns.delete({ ids: [1, 3] }); // Create an embedding with OpenAI, could be {Cohere, Voyage, Mixed Bread, ...} // Requires OPENAI_API_KEY to be set (https://platform.openai.com/settings/organization/api-keys) async function openaiOrRandVector(text: string): Promise<number[]> { if (!process.env.OPENAI_API_KEY) { console.log("OPENAI_API_KEY not set, using random vectors"); return [Math.random(), Math.random()]; } try { const { OpenAI } = await import("openai"); return ( await new OpenAI().embeddings.create({ model: "text-embedding-3-small", input: text, }) ).data[0].embedding; } catch { console.log( "OpenAI package not installed, using random vectors (`npm install openai`)", ); return [Math.random(), Math.random()]; } }

Navigation

Quickstart Guide