Enterprise Components

Portkey’s Enterprise Components provide the core infrastructure needed for production deployments. Each component handles a specific function - analytics, logging, or caching - with multiple implementation options to match your requirements.

​

Analytics Store

Portkey leverages Clickhouse as the primary Analytics Store for the Control Panel, offering powerful capabilities for handling large-scale analytical workloads.

​

Log Store

Portkey provides flexible options for storing and managing logs in your enterprise deployment. Choose from various storage solutions including MongoDB for document-based storage, AWS S3 for cloud-native object storage, or Wasabi for cost-effective cloud storage. Each option offers different benefits in terms of scalability, cost, and integration capabilities.

​

Cache Store

Portkey supports robust caching solutions to optimize performance and reduce latency in your enterprise deployment. Choose between Redis for in-memory caching or AWS ElastiCache for a fully managed caching service.

​

Semantic Cache Store

Portkey supports semantic caching capabilities that allow for intelligent caching based on the semantic meaning of requests rather than exact matches. For this functionality, Portkey requires a vector database to efficiently store and retrieve embeddings. Both Milvus and Pinecone are supported vector databases for Portkey’s semantic cache implementation.

• You need a Milvus deployment with a collection configured with 1536 dimensions

• Pinecone can be configured with a Pinecone index of 1536 dimensions to store the embeddings

This specific dimension size is required as Portkey uses OpenAI’s text-embedding-small model to create embeddings