Update app.py

app.py

@@ -213,10 +213,25 @@ async def extract_text_from_file(file: UploadFile):
     try:
         file_content = await file.read()
         if not file_content:
+            logger.error("Uploaded file is empty.")
             raise ValueError("Uploaded file is empty.")
 
+        # Check file size (e.g., limit to 10MB)
+        if len(file_content) > 10 * 1024 * 1024:  # 10MB
+            logger.error("File size exceeds the limit (10MB).")
+            raise ValueError("File size exceeds the limit (10MB).")
+
+        # Check file type
+        if not file.filename.lower().endswith((".pdf", ".docx", ".txt")):
+            logger.error(f"Unsupported file format: {file.filename}")
+            raise ValueError("Unsupported file format. Please upload a PDF, DOCX, or TXT file.")
+
         if file.filename.endswith(".pdf"):
             try:
+                # Log the first few bytes of the file for debugging
+                logger.info(f"First 100 bytes of the file: {file_content[:100]}")
+
+                # Attempt to open the PDF
                 doc = fitz.open(stream=file_content, filetype="pdf")
                 text = ""
                 for page in doc:
@@ -239,8 +254,6 @@ async def extract_text_from_file(file: UploadFile):
             except Exception as e:
                 logger.error(f"Error reading TXT file: {e}")
                 raise ValueError("Failed to read TXT file. It might be corrupted or not a valid TXT.")
-        else:
-            raise ValueError("Unsupported file format. Please upload a PDF, DOCX, or TXT file.")
     except Exception as e:
         logger.error(f"Error extracting text from file: {e}")
         raise HTTPException(status_code=400, detail=str(e))