scenario_name: sample-pdf-question-bank-online
mode: online
dataset: ../../datasets/raw/generated/sample-pdf-question-bank.csv
judge_model: qwen3.5-flash
embedding_model: text-embedding-v3
metrics:
- faithfulness
- answer_relevancy
- context_recall
- context_precision
output_dir: ../../outputs/online/sample-pdf-question-bank
runtime:
  batch_size: 2
  app_concurrency: 2
  metric_concurrency: 2
  max_samples: 45
app_adapter:
  type: python
  callable: apps.pdf_question_bank.adapter:run
  static_kwargs:
    source_chunks_path: ../../outputs/dataset-builds/sample-pdf-question-bank/latest/source_chunks.jsonl
    model: glm-5