New Feature: Add optional LiteLLM Docker Compose setup for local LLM gateway

[marazik]

Summary:
This adds a new feature, an optional LiteLLM Docker Compose setup for local LLM routing. It is Opt-in and doesn't change existing behavior.
PR1 - Docker compose (current PR)
PR2 - Integration code (will follow)
PR3 - Documentation

Details:
This PR introduces an optional Docker Compose setup for LiteLLM, enabling a local LLM gateway that can be used alongside the existing DeepWiki-Open stack.

It is fully opt-in and does not modify the default application runtime or existing Docker configuration.

Changes

• Added docker-compose-litellm.yml for standalone DeepWiki-Open + LiteLLM stack
• Added docker-compose-litellm.env for environment configuration
• Added Dockerfile-litellm for service containerization
• Added litellm-config.yml for runtime configuration

Note: Currently Dockerfile-litellm mirrors the existing Dockerfile to keep the setup consistent. It serves as an extension point for future modifications (e.g., optional removal of Ollama dependency).

---

Key Properties

• Fully isolated from existing DeepWiki-Open setup
• No changes to core application logic
• Can be enabled independently of main stack
• Supports local-first LLM routing via LiteLLM

---

Usage

ollama serve
docker compose -f docker-compose-litellm.yml up -d

---

Impact

• No impact on default system behavior
• Adds optional LLM abstraction layer for local development and testing
• Enables future integration of provider-agnostic LLM routing

---

Future Work

• Integration with DeepWiki-Open LLM client layer (PR2)
• Extended documentation and usage examples (PR3)

[gemini-code-assist]

Code Review

This pull request introduces a new Docker-based deployment configuration for DeepWiki using LiteLLM and Ollama, including a multi-stage Dockerfile, a Docker Compose setup, and LiteLLM configuration files. The review identifies several security risks involving hardcoded API keys and database passwords that should be moved to environment variables. Additionally, there are networking issues in the LiteLLM configuration regarding the Ollama API base, and the Dockerfile is missing several optimizations and dependencies found in the original version, such as build caching, memory limits, and CA certificates. Feedback also suggests avoiding pulling large LLM models during the build process to improve image portability and build reliability.