Download files_process.py from Datycs/MCG-Assist-Question-Answering: direct link, hf CLI and curl.
- Browser
- Download file 4.3 kB
-
https://huggingface.co/spaces/Datycs/MCG-Assist-Question-Answering/resolve/main/files_process.py
- Command line
-
hf download hf://spaces/Datycs/MCG-Assist-Question-Answering/files_process.py
-
curl -L -o files_process.py https://huggingface.co/spaces/Datycs/MCG-Assist-Question-Answering/resolve/main/files_process.py
4.3 kB
| # files_process.py | |
| import os | |
| from typing import List, Dict | |
| import gradio as gr | |
| import pandas as pd | |
| from agents import QuestionExtractionEngine, AnsweringEngine | |
| # ---- Gradio handlers ---- | |
| def extract_questions_handler(guideline_pdf, surgery_type, suggestions): | |
| """ | |
| Returns (questions_list, questions_dataframe) | |
| """ | |
| if guideline_pdf is None: | |
| raise gr.Error("Please upload a surgical guideline PDF (e.g., Knee Arthroplasty guideline).") | |
| pdf_path = guideline_pdf.name if hasattr(guideline_pdf, "name") else str(guideline_pdf) | |
| q_engine = QuestionExtractionEngine(pdf_path, surgery_type or "Procedure", user_suggestions=suggestions or "") | |
| questions: List[str] = q_engine.run() | |
| if not questions: | |
| raise gr.Error("I couldn't extract any questions. Try adding suggestions or another guideline PDF.") | |
| df = pd.DataFrame({"#": list(range(1, len(questions) + 1)), "Question": questions}) | |
| return questions, df | |
| def answer_questions_handler(patient_pdf, questions_state): | |
| """ | |
| Returns a DataFrame: Question | Answer | Rationale | |
| """ | |
| if patient_pdf is None: | |
| raise gr.Error("Please upload a patient chart PDF.") | |
| if not questions_state: | |
| raise gr.Error("No questions available. Extract questions first.") | |
| pdf_path = patient_pdf.name if hasattr(patient_pdf, "name") else str(patient_pdf) | |
| a_engine = AnsweringEngine(pdf_path) | |
| rows = [] | |
| for q in questions_state: | |
| res: Dict[str, Dict[str, str]] = a_engine.answer_one(q) | |
| ans = res.get(q, {}) | |
| rows.append({ | |
| "Question": q, | |
| "Answer": ans.get("answer", "Not Found"), | |
| "Rationale": ans.get("rationale", "—") | |
| }) | |
| df = pd.DataFrame(rows, columns=["Question", "Answer", "Rationale"]) | |
| return df | |
| with gr.Blocks(title="Guideline → Questions → Chart Answers", theme="soft") as demo: | |
| gr.Markdown("# 🏥 Guideline Q&A (Yes/No) — with Iterative Feedback") | |
| with gr.Tabs(): | |
| with gr.Tab("1) Extract Questions"): | |
| with gr.Row(): | |
| guideline_pdf = gr.File(label="Upload Guideline PDF (e.g., Knee_Arthroplasty.pdf)", file_count="single") | |
| surgery_type = gr.Textbox(label="Surgery Type", value="Knee Arthroplasty") | |
| suggestions = gr.Textbox( | |
| label="Suggestions (optional)", | |
| placeholder="E.g., 'Focus on contraindications and pre-op lab thresholds; keep questions short.'" | |
| ) | |
| extract_btn = gr.Button("Extract Yes/No Questions", variant="primary") | |
| questions_state = gr.State([]) # list[str] | |
| questions_df = gr.Dataframe(headers=["#", "Question"], interactive=False, wrap=True) | |
| gr.Markdown("If the questions need refinement, update 'Suggestions' and click the button again.") | |
| def _extract_and_store(g_pdf, s_type, sugg): | |
| q_list, df = extract_questions_handler(g_pdf, s_type, sugg) | |
| return q_list, df | |
| extract_btn.click( | |
| fn=_extract_and_store, | |
| inputs=[guideline_pdf, surgery_type, suggestions], | |
| outputs=[questions_state, questions_df], | |
| ) | |
| with gr.Tab("2) Answer from Patient Chart"): | |
| patient_pdf = gr.File(label="Upload Patient Chart PDF (e.g., JAY_MORGAN.pdf)", file_count="single") | |
| answer_btn = gr.Button("Answer All Questions", variant="primary") | |
| answers_df = gr.Dataframe(headers=["Question", "Answer", "Rationale"], interactive=False, wrap=True) | |
| answer_btn.click( | |
| fn=answer_questions_handler, | |
| inputs=[patient_pdf, questions_state], | |
| outputs=answers_df, | |
| ) | |
| gr.Markdown( | |
| "### Notes\n" | |
| "- Embeddings are cached under `./embeddings/<PDF-name>/` to avoid recomputation.\n" | |
| "- Set your OpenAI key: `export OPENAI_API_KEY=...` before running.\n" | |
| "- If a PDF is scanned/image-only, text extraction may be poor (consider OCR pre-processing).\n" | |
| ) | |
| if __name__ == "__main__": | |
| # Optional: set server params via env (Arch-friendly) | |
| # os.environ.setdefault("GRADIO_SERVER_NAME", "0.0.0.0") | |
| # os.environ.setdefault("GRADIO_SERVER_PORT", "7860") | |
| demo.launch() |