Update app.py and requirements.txt with PDF extraction support

app.py

@@ -29,14 +29,18 @@ dataset = load_dataset("dgmos/ericsson-manuals", split="train")
 # 4. PDF 텍스트 추출
 docs = []
 for item in dataset:
-    # 실제 필드명 확인 필요 (예: "file", "path")
-    pdf_path = item["file"]
+    # 실제 필드명 확인 필요 (예: "file", "path" 등)
+    pdf_path = item.get("file") or item.get("path") or None
+    if not pdf_path:
+        print(f"⚠️ PDF 경로가 없음: {item}")
+        continue
 
     try:
         with pdfplumber.open(pdf_path) as pdf:
             text = "
 ".join([page.extract_text() or "" for page in pdf.pages])
-            docs.append({"page_content": text})
+            if text.strip():
+                docs.append({"page_content": text})
     except Exception as e:
         print(f"PDF 처리 중 오류: {pdf_path} - {str(e)}")
         continue