wangwei
75ae7927ad
- scenarios/siemens_build/siemens-pdf-build.yaml: dataset build for all 17 Siemens medical-imaging PDFs (aliyun_docmind parser, 10 questions/doc, failure_mode=skip, ~170 question total) - scenarios/offline/siemens-pdf-offline-smoke.yaml: offline evaluation using source chunks as contexts and ground_truth as answer (up to 30 samples) - scenarios/online/siemens-pdf-question-bank-online.yaml: online evaluation calling siemens_pdf_qa adapter, batch_size=4, up to 50 samples - apps/siemens_pdf_qa/adapter.py: Siemens-specific adapter with bilingual (zh/en) system prompt and strict evidence-grounding for CT domain - scripts/build_siemens_offline_smoke.py: helper to derive offline smoke CSV from completed dataset build artifacts (run after dataset build step) - docs/superpowers/specs/2026-06-15-siemens-scenario-design.md: design spec All three scenarios are automatically discovered by the web console. Co-Authored-By: Claude Sonnet 4 <noreply@anthropic.com>
18 lines
491 B
YAML
18 lines
491 B
YAML
job_name: siemens-pdf-question-bank
|
|
input:
|
|
path: ../../datasets/siemens-pdfs
|
|
glob: "*.pdf"
|
|
parser:
|
|
provider: aliyun_docmind
|
|
failure_mode: skip
|
|
generation:
|
|
output_type: online_question_bank
|
|
review_mode: draft_with_manual_review
|
|
max_questions_per_document: 10
|
|
max_source_chunks_per_question: 3
|
|
output:
|
|
dataset_path: ../../datasets/raw/generated/siemens-pdf-question-bank.csv
|
|
artifact_dir: ../../outputs/dataset-builds/siemens-pdf-question-bank
|
|
runtime:
|
|
max_documents: 17
|