Update app.py

app.py

@@ -33,7 +33,7 @@ def process_resumes(filepaths, candidate_id: str, additional_notes: str = ""):
             raw_bytes = f.read()
         filetype = detect_filetype(filename, raw_bytes)
 
-        # 1) テキスト抽出：画像/PDFはOpenAI Vision OCR、docx/txtは生文面＋OpenAI整形
+        # 1) テキスト抽出
         if filetype in {"pdf", "image"}:
             text = extract_text_with_openai(raw_bytes, filename=filename, filetype=filetype)
         else:
@@ -42,7 +42,7 @@ def process_resumes(filepaths, candidate_id: str, additional_notes: str = ""):
 
         raw_texts.append({"filename": filename, "text": text})
 
-        # 2) OpenAIでセクション構造化 → ルール正規化
+        # 2) 構造化 → 3) 正規化
         structured = structure_with_openai(text)
         normalized = normalize_resume({
             "work_experience": structured.get("work_experience_raw", ""),
@@ -57,10 +57,10 @@ def process_resumes(filepaths, candidate_id: str, additional_notes: str = ""):
             "normalized": normalized,
         })
 
-    # 3) 統合（複数ファイル→1候補者）
+    # 4) 統合
     merged = merge_normalized_records([r["normalized"] for r in partial_records])
 
-    # 4) スキル抽出（辞書/正規表現）
+    # 5) スキル抽出
     merged_text = "\n\n".join([r["text"] for r in partial_records])
     skills = extract_skills(merged_text, {
         "work_experience": merged.get("raw_sections", {}).get("work_experience", ""),
@@ -69,17 +69,17 @@ def process_resumes(filepaths, candidate_id: str, additional_notes: str = ""):
         "skills": ", ".join(merged.get("skills", [])),
     })
 
-    # 5) 匿名化
+    # 6) 匿名化
     anonymized_text, anon_map = anonymize_text(merged_text)
     anon_pdf_bytes = render_anonymized_pdf(anonymized_text)
 
-    # 6) 品質スコア
+    # 7) 品質スコア
     score = compute_quality_score(merged_text, merged)
 
-    # 7) 要約（300/100/1文）
+    # 8) 要約
     summaries = summarize_with_openai(merged_text)
 
-    # 8) 構造化出力
+    # 9) 構造化出力
     result_json = {
         "candidate_id": candidate_id or hashlib.sha256(merged_text.encode("utf-8")).hexdigest()[:16],
         "files": [os.path.basename(p) for p in filepaths],
@@ -91,7 +91,7 @@ def process_resumes(filepaths, candidate_id: str, additional_notes: str = ""):
         "notes": additional_notes,
     }
 
-    # 9) HF Datasets 保存
+    # 10) HF Datasets 保存
     dataset_repo = os.environ.get("DATASET_REPO")
     commit_info = None
     if dataset_repo:
@@ -107,14 +107,15 @@ def process_resumes(filepaths, candidate_id: str, additional_notes: str = ""):
 
     anon_pdf = (result_json["candidate_id"] + ".anon.pdf", anon_pdf_bytes)
 
+    # 重要：gradioのAPIスキーマ生成バグ回避のため、dictはすべて文字列で返す
     return (
-        json.dumps(result_json, ensure_ascii=False, indent=2),
-        json.dumps(skills, ensure_ascii=False, indent=2),      # ← Code出力に合わせて文字列化
-        json.dumps(score, ensure_ascii=False, indent=2),
+        json.dumps(result_json, ensure_ascii=False, indent=2),  # out_json -> Code(str)
+        json.dumps(skills, ensure_ascii=False, indent=2),       # out_skills -> Code(str)
+        json.dumps(score, ensure_ascii=False, indent=2),        # out_score -> Code(str)
         summaries["300chars"],
         summaries["100chars"],
         summaries["onesent"],
-        anon_pdf,
+        anon_pdf,                                               # File(tuple)
         json.dumps(commit_info or {"status": "skipped (DATASET_REPO not set)"}, ensure_ascii=False, indent=2),
     )
 
@@ -127,7 +128,7 @@ with gr.Blocks(title=APP_TITLE) as demo:
             label="レジュメ類 (PDF/画像/Word/テキスト) 複数可",
             file_count="multiple",
             file_types=[".pdf", ".png", ".jpg", ".jpeg", ".tiff", ".bmp", ".docx", ".txt"],
-            type="filepath",  # ← ここが重要（'file' は不可）
+            type="filepath",  # ← 'file' は 4.44 系で非推奨/不可
         )
         candidate_id = gr.Textbox(label="候補者ID（任意。未入力なら自動生成）")
     notes = gr.Textbox(label="補足メモ（任意）", lines=3)
@@ -138,10 +139,10 @@ with gr.Blocks(title=APP_TITLE) as demo:
         out_json = gr.Code(label="統合出力 (JSON)")
 
     with gr.Tab("抽出スキル"):
-        out_skills = gr.Code(label="スキル一覧 (JSON)")  # ← gr.JSON は型推論で落ちやすいので Code に
+        out_skills = gr.Code(label="スキル一覧 (JSON)")  # ← gr.JSON をやめる
 
     with gr.Tab("品質スコア"):
-        out_score = gr.Code(label="品質評価")
+        out_score = gr.Code(label="品質評価 (JSON)")
 
     with gr.Tab("要約 (300/100/1文)"):
         out_sum_300 = gr.Textbox(label="300字要約")
@@ -160,6 +161,6 @@ with gr.Blocks(title=APP_TITLE) as demo:
         outputs=[out_json, out_skills, out_score, out_sum_300, out_sum_100, out_sum_1, out_pdf, out_commit],
     )
 
-
 if __name__ == "__main__":
-    demo.launch()
+    # ローカル不可環境に対応
+    demo.launch(share=True, server_name="0.0.0.0")