When the LLM returns ontology attributes as plain strings instead of
dicts, set_ontology() crashes with "TypeError: string indices must be
integers, not 'str'" at attr_def["name"].
Two-layer fix:
1. ontology_generator.py: normalize string attrs to {"name", "type",
"description"} dicts during validation, so downstream code always
receives well-formed structures.
2. graph_builder.py: add isinstance guard as a safety net in
set_ontology() for both entity and edge attribute loops.
Co-Authored-By: Octopus <liyuan851277048@icloud.com>
The language instruction was causing LLM to change entity/relation naming
conventions. Now explicitly enforce PascalCase/UPPER_SNAKE_CASE for technical
identifiers while only applying language preference to description fields.
- Updated `run.py` to conditionally print startup information only in the reloader process to avoid duplicate logs in debug mode.
- Modified `__init__.py` to log startup and completion messages based on the reloader process condition.
- Added warnings suppression in `graph_builder.py` for Pydantic v2 regarding Field usage.
- Revised `ontology_generator.py` to enforce strict design guidelines for entity types and relationships, ensuring compliance with new requirements.
- Improved logging behavior in `logger.py` to prevent log propagation to the root logger, avoiding duplicate outputs.
octo-patch
BaiFu
ghostubborn