MicroFish/backend/app
Ubuntu dfabab5343 feat(graph): expand ontology to 20 types, pass attributes to Graphiti, add retry
- ontology_generator: increase entity limit to 20 (18 specific + 2 fallback),
  edge types to 20 (12-20 requested); bump max_tokens to 8192
- ontology_generator: fallback type names (Person/Organization) now resolved
  via i18n so Catalan gets Persona/Organització
- locales: add ontologyFallback* keys to en/zh/es/ca
- graph_builder: pass entity/edge attributes to non-Zep set_ontology (were discarded)
- graphiti_backend: _make_model builds real Pydantic fields per attribute
- graphiti_backend: _build_extraction_instructions includes per-entity attribute
  hints so the LLM knows which fields to extract
- graphiti_backend: add_batch retries up to 3x on "node not found" race condition
  with exponential backoff (2s, 4s) before propagating the error

Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
2026-04-25 19:19:28 +00:00
..
api chore(i18n): replace all hardcoded Chinese strings with English in backend 2026-04-24 23:40:58 +00:00
graph feat(graph): expand ontology to 20 types, pass attributes to Graphiti, add retry 2026-04-25 19:19:28 +00:00
models chore(i18n): replace all hardcoded Chinese strings with English in backend 2026-04-24 23:40:58 +00:00
services feat(graph): expand ontology to 20 types, pass attributes to Graphiti, add retry 2026-04-25 19:19:28 +00:00
utils feat(llm): auto-configure Google AI Studio URL when LLM_PROVIDER=gemini 2026-04-25 13:13:11 +00:00
__init__.py chore(i18n): replace all hardcoded Chinese strings with English in backend 2026-04-24 23:40:58 +00:00
config.py feat(config): add GRAPH_BACKEND + NEO4J_* + LLM_PROVIDER config vars 2026-04-25 11:29:17 +00:00