> ## Documentation Index
> Fetch the complete documentation index at: https://docs.portkey.ai/docs/llms.txt
> Use this file to discover all available pages before exploring further.

# Deployment Components

The Prisma AIRS AI Gateway's deployment 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

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

> **[Clickhouse](https://github.com/Portkey-AI/helm-chart/tree/main/helm/enterprise#analytics-store)**

> [!NOTE]
>
> The AI Gateway supports exporting your Clickhouse analytics data to OpenTelemetry (OTel) compatible collectors, allowing you to integrate the AI Gateway's analytics with your existing observability infrastructure.

***

## Log Store

The AI Gateway provides flexible options for storing and managing logs in your hybrid 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.

> **[MongoDB](https://docs.portkey.ai/docs/aigw/integrations/libraries/mongodb.md)**

> **[AWS S3](https://github.com/Portkey-AI/helm-chart/tree/main/helm/enterprise#log-storage)**

> **[Wasabi](https://github.com/Portkey-AI/helm-chart/tree/main/helm/enterprise#log-storage)**

### Log Object Path Format

Configure how log files are organized in your blob storage using the `LOG_STORE_FILE_PATH_FORMAT` environment variable.

| Value | Format | Example Path |
| - | - | - |
| `v1` (default) | Flat structure | `30/<organisation-id>/<log-id>.json` |
| `v2` | Time-hierarchical | `30/<organisation-id>/<workspace-slug>/<year>/<month>/<day>/<hour>/<log-id>.json` |

The `v2` format organizes logs by time hierarchy, making it easier to manage retention policies and query logs for specific time periods.

> [!NOTE]
>
> Changing `LOG_STORE_FILE_PATH_FORMAT` only affects newly written logs. Previously written logs retain their original path format and are not migrated.

***

## Cache Store

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

> **[Redis](https://github.com/Portkey-AI/helm-chart/tree/main/helm/enterprise#cache-store)**

> **[AWS ElastiCache](https://github.com/Portkey-AI/helm-chart/tree/main/helm/enterprise#cache-store)**

> **[Azure Cache for Redis](https://github.com/Portkey-AI/helm-chart/tree/main/helm/enterprise#cache-store)**

> **[GCP Memorystore](https://github.com/Portkey-AI/helm-chart/tree/main/helm/enterprise#cache-store)**

## Semantic Cache Store

Semantic caching stores embeddings in a vector database (**Milvus** or **Pinecone**) so similar prompts can reuse LLM responses. Embedding provider settings, vector store environment variables, and provider-specific setup (collection schema for Milvus, index naming and metric for Pinecone) are documented in **[Cache (Simple & Semantic)](https://docs.portkey.ai/docs/aigw/product/ai-gateway/cache-simple-and-semantic.md#set-up-semantic-caching-self-hosted)** under *Set up semantic caching (self-hosted)*.


## Related topics

- [Cache Behaviour](https://docs.portkey.ai/docs/aigw/self-hosting/cache-behavior.md)
- [EKS](https://docs.portkey.ai/docs/aigw/self-hosting/hybrid-deployments/aws/eks.md)
- [GCP](https://docs.portkey.ai/docs/aigw/self-hosting/hybrid-deployments/gcp.md)
- [OpenLIT](https://docs.portkey.ai/docs/aigw/integrations/tracing-providers/openlit.md)
- [Atlassian Remote MCP server](https://docs.portkey.ai/docs/aigw/integrations/mcp-servers/atlassian-mcp-server.md)


This documentation is built and hosted on [Mintlify](https://mintlify.com), a developer documentation platform.