Skip to Content
ReferenceRAGTurboPuffer

Turbopuffer Vector Store

The TurbopufferVector class provides vector search using Turbopuffer , a high-performance vector database optimized for RAG applications. Turbopuffer offers fast vector similarity search with advanced filtering capabilities and efficient storage management.

Constructor Options

apiKey:

string
The API key to authenticate with Turbopuffer

baseUrl?:

string
= https://api.turbopuffer.com
The base URL for the Turbopuffer API

connectTimeout?:

number
= 10000
The timeout to establish a connection, in ms. Only applicable in Node and Deno.

connectionIdleTimeout?:

number
= 60000
The socket idle timeout, in ms. Only applicable in Node and Deno.

warmConnections?:

number
= 0
The number of connections to open initially when creating a new client.

compression?:

boolean
= true
Whether to compress requests and accept compressed responses.

schemaConfigForIndex?:

function
A callback function that takes an index name and returns a config object for that index. This allows you to define explicit schemas per index.

Methods

createIndex()

indexName:

string
Name of the index to create

dimension:

number
Vector dimension (must match your embedding model)

metric?:

'cosine' | 'euclidean' | 'dotproduct'
= cosine
Distance metric for similarity search

upsert()

vectors:

number[][]
Array of embedding vectors

metadata?:

Record<string, any>[]
Metadata for each vector

ids?:

string[]
Optional vector IDs (auto-generated if not provided)

query()

indexName:

string
Name of the index to query

queryVector:

number[]
Query vector to find similar vectors

topK?:

number
= 10
Number of results to return

filter?:

Record<string, any>
Metadata filters for the query

includeVector?:

boolean
= false
Whether to include vectors in the results

listIndexes()

Returns an array of index names as strings.

describeIndex()

indexName:

string
Name of the index to describe

Returns:

interface IndexStats {
  dimension: number;
  count: number;
  metric: "cosine" | "euclidean" | "dotproduct";
}

deleteIndex()

indexName:

string
Name of the index to delete

Response Types

Query results are returned in this format:

interface QueryResult {
  id: string;
  score: number;
  metadata: Record<string, any>;
  vector?: number[]; // Only included if includeVector is true
}

Schema Configuration

The schemaConfigForIndex option allows you to define explicit schemas for different indexes:

schemaConfigForIndex: (indexName: string) => {
  // Mastra's default embedding model and index for memory messages:
  if (indexName === "memory_messages_384") {
    return {
      dimensions: 384,
      schema: {
        thread_id: {
          type: "string",
          filterable: true,
        },
      },
    };
  } else {
    throw new Error(`TODO: add schema for index: ${indexName}`);
  }
};

Error Handling

The store throws typed errors that can be caught:

try {
  await store.query({
    indexName: "index_name",
    queryVector: queryVector,
  });
} catch (error) {
  if (error instanceof VectorStoreError) {
    console.log(error.code); // 'connection_failed' | 'invalid_dimension' | etc
    console.log(error.details); // Additional error context
  }
}
QdrantVectorUpstashVector