wangwei a781ba1e4a config: set default judge_model=gpt-5, embedding_model=text-embedding-3-small ...

gpt-5.4/5.5/5.2/5.4-mini/5.4-nano are incompatible with RAGAS 0.4.3
because they require max_completion_tokens instead of max_tokens.
gpt-5 / gpt-4.1 support max_tokens and json_object mode required by RAGAS.

Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com>

2026-06-23 15:29:01 +08:00

..

adapters

first commit

2026-06-12 14:02:15 +08:00

advisor

fix(advisor): fix LLM API call, wire advice_markdown to webapp, update .env.example timeouts

2026-06-16 17:12:32 +08:00

config

feat: add metric_weights and doc_weights to Scenario schema and dataclass

2026-06-18 16:50:33 +08:00

dataset_builder

feat(dataset-builder): add retry logic and ASCII-safe logging for Siemens PDF pipeline

2026-06-15 23:06:33 +08:00

datasets

Add RAGAS evaluation web console (FastAPI + vanilla JS)

2026-06-15 15:53:57 +08:00

execution

feat: add weighted_score and sample_weight columns to score rows

2026-06-18 16:53:45 +08:00

metrics

feat: add metric/doc weight computation module (weights.py)

2026-06-18 16:47:47 +08:00

reporting

feat: use weighted metric means and add weighted_score row to summary.md

2026-06-18 16:59:56 +08:00

shared

feat: add metric_weights and doc_weights to Scenario schema and dataclass

2026-06-18 16:50:33 +08:00

__init__.py

first commit

2026-06-12 14:02:15 +08:00

compat.py

first commit

2026-06-12 14:02:15 +08:00

sample_rag_eval_dataset.csv

first commit

2026-06-12 14:02:15 +08:00

settings.py

config: set default judge_model=gpt-5, embedding_model=text-embedding-3-small

2026-06-23 15:29:01 +08:00