The extraction pipeline accesses LLMs through a LiteLLM proxy that is OpenAI-compatible so that model routing is handled through a compatible proxy layer.

LLM access: Extraction pipeline uses a LiteLLM proxy (OpenAI-compatible) for model routing.

— PYRANA_PLATFORM_ARCHITECTURE_REFERENCE.md

uses a LiteLLM proxy

— PYRANA_PLATFORM_ARCHITECTURE_REFERENCE.md

OpenAI-compatible

— PYRANA_PLATFORM_ARCHITECTURE_REFERENCE.md

for model routing

— PYRANA_PLATFORM_ARCHITECTURE_REFERENCE.md