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

# Infrastructure

> This section covers the infrastructure components that power Knowledge Stack and how you can configure them for your deployment.

* **[Database Prewarming](/infrastructure/database-prewarming)** -- How Knowledge Stack uses PostgreSQL cache prewarming to deliver fast query performance for document retrieval and vector search.

* **[Real-Time Notifications](/infrastructure/notifications)** -- WebSocket and Server-Sent Events (SSE) APIs for receiving real-time updates and streaming AI responses.

* **[Vector Search (Qdrant)](/infrastructure/qdrant)** -- How the vector search infrastructure works, including embedding pipelines, metadata filtering, and multi-tenant isolation.

* **[LLM Gateway (LiteLLM)](/infrastructure/litellm)** -- The LLM gateway that provides per-tenant cost tracking, budget enforcement, and model routing.

* **[CI/CD Pipeline](/infrastructure/cicd)** -- Automated build, test, and deployment pipelines for self-hosted Knowledge Stack installations.