Update app.py

app.py

@@ -30,7 +30,7 @@ def load_models():
     with st.spinner("Loading AI models... This may take a minute on first run."):
         models = {}
         # Load summarization model
-        models['summarizer'] = pipeline("summarization", model="sshleifer/distilbart-xsum-12-6")
+        models['summarizer'] = pipeline("summarization", model="microsoft/Phi-3.5-mini-instruct")
         
         # Load feature extraction model for similarity
         models['feature_extractor'] = pipeline("feature-extraction", model="bert-base-uncased")
@@ -58,13 +58,25 @@ def extract_text_from_file(file_obj):
             text = "\n".join(para.text for para in document.paragraphs if para.text.strip())
         except Exception as e:
             text = f"Error processing DOCX file: {e}"
-    elif ext == ".txt":
+    elif ext == ".doc":
         try:
-            text = file_obj.getvalue().decode("utf-8")
-        except Exception as e:
-            text = f"Error processing TXT file: {e}"
+            # For .doc files, we need to save to a temp file
+            with tempfile.NamedTemporaryFile(delete=False, suffix='.doc') as temp_file:
+                temp_file.write(file_obj.getvalue())
+                temp_path = temp_file.name
+        
+            # Use docx2txt which is generally faster
+            try:
+                text = docx2txt.process(temp_path)
+            except Exception:
+                text = "Could not process .doc file. Please convert to .docx format."
+        
+            # Clean up temp file
+            os.unlink(temp_path)
+         except Exception as e:
+            text = f"Error processing DOC file: {e}"
     else:
-        text = "Unsupported file type. Please upload a .docx or .txt file."
+        text = "Unsupported file type. Please upload a .docx or .doc file."
     return text
 
 #####################################