- System prompt is now optional — LLM only generates one when the task is ambiguous from the data alone (persona, domain, format constraints) - Sanitize system_prompt extraction (handle literal "null" string) - Show system prompt, user template, and assistant template in the advisor notification banner so user can see exactly what was generated - Templates displayed in monospace with labeled sections |
||
|---|---|---|
| .. | ||
| __init__.py | ||
| chat_templates.py | ||
| data_collators.py | ||
| dataset_utils.py | ||
| format_conversion.py | ||
| format_detection.py | ||
| llm_assist.py | ||
| model_mappings.py | ||
| vlm_processing.py | ||