Update app.py

app.py

@@ -69,39 +69,49 @@ class SerpClient:
 # ---------------------------
 # Safe file text extraction (Gradio returns FileData dict: {"name", "size", "path"})
 # ---------------------------
-def extract_text_from_gradio_file(filedata: Optional[dict]) -> str:
+def extract_text_from_gradio_file(filedata):
+    """
+    Supports BOTH:
+    1. HF Spaces dict:
+       {"name": "..", "path": "...", "size": ...}
+    2. HF NamedString:
+       filedata = NamedString("/tmp/.../file.txt")
+    """
     if not filedata:
         return ""
-    # filedata is a dict with 'name' and 'path' in Spaces
-    file_path = filedata.get("path") or filedata.get("tmp_path") or filedata.get("name")
-    if not file_path:
-        return ""
-    file_path = str(file_path)
+
+    # Case A: filedata is a dict
+    if isinstance(filedata, dict):
+        file_path = filedata.get("path") or filedata.get("name")
+        if not file_path:
+            return ""
+        file_path = str(file_path)
+
+    # Case B: filedata is NamedString (just a string)
+    else:
+        # Gradio NamedString gives direct file path
+        file_path = str(filedata)
+
+    lower = file_path.lower()
+
     try:
-        lower = file_path.lower()
         if lower.endswith(".txt"):
-            with open(file_path, "r", encoding="utf-8", errors="ignore") as f:
-                return f.read()
+            return open(file_path, "r", encoding="utf-8", errors="ignore").read()
+
         if lower.endswith(".pdf"):
-            try:
-                from pypdf import PdfReader
-                reader = PdfReader(file_path)
-                return "\n".join([p.extract_text() or "" for p in reader.pages])
-            except Exception:
-                # fallback: try binary read and decode
-                with open(file_path, "rb") as f:
-                    return f.read().decode("utf-8", errors="ignore")
+            from pypdf import PdfReader
+            reader = PdfReader(file_path)
+            return "\n".join([p.extract_text() or "" for p in reader.pages])
+
         if lower.endswith(".docx"):
-            try:
-                import docx
-                doc = docx.Document(file_path)
-                return "\n".join([p.text for p in doc.paragraphs])
-            except Exception:
-                with open(file_path, "rb") as f:
-                    return f.read().decode("utf-8", errors="ignore")
-        # Fallback: read bytes
+            import docx
+            doc = docx.Document(file_path)
+            return "\n".join([p.text for p in doc.paragraphs])
+
+        # fallback
         with open(file_path, "rb") as f:
             return f.read().decode("utf-8", errors="ignore")
+
     except Exception:
         return ""