The extraction pipeline accesses language models through a LiteLLM proxy that is OpenAI-compatible so that model routing is handled through a standardized interface.

Supporting contexts

Quoteverbatim

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

— PYRANA_PLATFORM_ARCHITECTURE_REFERENCE.md

Quoteverbatim

LiteLLM proxy

— PYRANA_PLATFORM_ARCHITECTURE_REFERENCE.md

Quoteverbatim

OpenAI-compatible

— PYRANA_PLATFORM_ARCHITECTURE_REFERENCE.md

Effective from: 7/16/2026, 11:29:15 PM