Redis is a fast in-memory data store that supports vector similarity search through the Redis Search module. It supports both cloud-hosted (Redis Cloud) and self-hosted deployments.
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:
uv pip install cognee-community-vector-adapter-redis
Configuration Docker (Local)
Redis Cloud
Redis with SSL
Run a local Redis instance with the Search module enabled: docker run -d --name redis -p 6379:6379 redis:8.0.2
Configure in Python: from cognee_community_vector_adapter_redis import register from cognee import config config.set_vector_db_config({ "vector_db_provider" : "redis" , "vector_db_url" : "redis://localhost:6379" , })
Or via environment variables: VECTOR_DB_PROVIDER = "redis" VECTOR_DB_URL = "redis://localhost:6379"
Get your connection URL from the Redis Cloud dashboard. Make sure to enable the Search module. from cognee_community_vector_adapter_redis import register from cognee import config config.set_vector_db_config({ "vector_db_provider" : "redis" , "vector_db_url" : "redis://user:password@your-redis-cloud-url:port" , })
Or via environment variables: VECTOR_DB_PROVIDER = "redis" VECTOR_DB_URL = "redis://user:password@your-redis-cloud-url:port"
For secure connections, use the rediss:// protocol: from cognee_community_vector_adapter_redis import register from cognee import config config.set_vector_db_config({ "vector_db_provider" : "redis" , "vector_db_url" : "rediss://localhost:6380" , })
Or via environment variables: VECTOR_DB_PROVIDER = "redis" VECTOR_DB_URL = "rediss://localhost:6380"
Important Notes
Import register from the adapter package before using Redis with Cognee. This registers the adapter with Cognee’s provider system.
Connection Errors : Ensure Redis is running and accessible at the specified URLSearch Module Missing : Make sure Redis has the Search module enabledEmbedding Dimension Mismatch : Verify embedding engine dimensions match index configurationCollection Not Found : Always create collections before adding data points Resources 
