Skip to main content
Turbopuffer is a high-performance vector database designed for fast similarity search at scale.
Cognee can use Turbopuffer as a vector store backend through this community-maintained adapter.

​
Installation

This adapter is a separate package from core Cognee. Before installing, complete the Cognee installation and ensure your environment is configured with LLM and embedding providers. After that, install the adapter package: 
pip install cognee-community-vector-adapter-turbopuffer

​
Configuration

  1. Create an account at turbopuffer.com
  2. Get your API key from the dashboard
Set the following environment variables in your .env file: 
TURBOPUFFER_API_KEY="your_api_key"
VECTOR_DATASET_DATABASE_HANDLER="turbopuffer"
# Optional: defaults to gcp-us-central1
# TURBOPUFFER_REGION="gcp-us-central1"
Then register the adapter in your code: 
from cognee_community_vector_adapter_turbopuffer import register
See available regions for supported TURBOPUFFER_REGION values.

​
Important Notes

Ensure EMBEDDING_DIMENSIONS matches your embedding model. See Embedding Providers for configuration.Changing dimensions requires recreating collections or running prune.prune_system().

​
Resources

Turbopuffer Docs

Official documentation

Adapter Source

GitHub repository

Vector Stores

Official vector providers

Community Overview

All community integrations

Setup Overview

Configuration guide