Dominik Seemann 8af800a122 fix(graph): pass small_model to graphiti so non-openai backends don't 404 ... Graphiti's OpenAIClient routes "simpler" extraction prompts to ModelSize.small, falling back to a hard-coded `gpt-4.1-nano` when no small_model is configured. Against Qwen/Dashscope (and other OpenAI-SDK endpoints that don't host that model) this surfaces as a 404 mid-graph build, even when LLM_MODEL_NAME points at a working model. Add LLM_SMALL_MODEL_NAME (defaults to LLM_MODEL_NAME) and pass it through the Graphiti LLMConfig so the small slot is always populated with a model the configured endpoint actually serves. Closes #37		2026-05-11 13:12:21 +02:00
..
api	docs(i18n): translate chinese docstrings/comments in backend/api	2026-05-09 10:59:36 +00:00
models	docs(i18n): translate chinese docstrings/comments in backend/app/{models,utils} and partial services	2026-05-07 14:44:08 +00:00
services	fix(graph): pass small_model to graphiti so non-openai backends don't 404	2026-05-11 13:12:21 +02:00
utils	Merge branch 'main' into docs/i18n-7-translate-backend-comments	2026-05-09 10:40:10 +00:00
__init__.py	docs(i18n): translate chinese docstrings/comments in backend root, api init, simulation_ipc, simulation_manager, zep_entity_reader	2026-05-07 14:49:20 +00:00
config.py	fix(graph): pass small_model to graphiti so non-openai backends don't 404	2026-05-11 13:12:21 +02:00