Update app.py

app.py

@@ -117,61 +117,37 @@ class AuditAgent:
         except Exception as e:
             return f"Error processing query: {str(e)}"
 
-    def process_documents(self, file):
+    def process_documents(self, file_path, file_name):
         """Process uploaded documents and create a vector store."""
-        if not file:
+        if not file_path or not file_name:
             return "Please upload a file"
             
         try:
             documents = []
             
-            # Create temporary directory
-            temp_dir = tempfile.mkdtemp()
-            temp_path = os.path.join(temp_dir, file.name)
-            
-            # Save uploaded file
-            with open(temp_path, 'wb') as f:
-                f.write(file.read())
-            
             # Get file extension and check it's supported
-            file_ext = os.path.splitext(file.name.lower())[1]
+            file_ext = os.path.splitext(file_name.lower())[1]
             supported_exts = ['.pdf', '.docx', '.pptx', '.xlsx', '.xls']
             
             if file_ext not in supported_exts:
-                # Clean up temp files before returning
-                if os.path.exists(temp_path):
-                    os.remove(temp_path)
-                if os.path.exists(temp_dir):
-                    os.rmdir(temp_dir)
                 return f"Unsupported file type: {file_ext}. Please upload one of: {', '.join(supported_exts)}"
             
             # Select appropriate loader
             try:
                 if file_ext == '.pdf':
-                    loader = PyPDFLoader(temp_path)
+                    loader = PyPDFLoader(file_path)
                 elif file_ext == '.docx':
-                    loader = Docx2txtLoader(temp_path)
+                    loader = Docx2txtLoader(file_path)
                 elif file_ext == '.pptx':
-                    loader = UnstructuredPowerPointLoader(temp_path)
+                    loader = UnstructuredPowerPointLoader(file_path)
                 elif file_ext in ['.xlsx', '.xls']:
-                    loader = UnstructuredExcelLoader(temp_path)
+                    loader = UnstructuredExcelLoader(file_path)
                 
                 # Load and process document
                 documents.extend(loader.load())
             except Exception as e:
-                # Clean up temp files
-                if os.path.exists(temp_path):
-                    os.remove(temp_path)
-                if os.path.exists(temp_dir):
-                    os.rmdir(temp_dir)
                 return f"Error loading document content: {str(e)}"
             
-            # Cleanup temp files
-            if os.path.exists(temp_path):
-                os.remove(temp_path)
-            if os.path.exists(temp_dir):
-                os.rmdir(temp_dir)
-            
             # Split documents
             if not documents:
                 return "No content could be extracted from the document."
@@ -190,7 +166,7 @@ class AuditAgent:
             embeddings = OpenAIEmbeddings(openai_api_key=api_keys["openai_key"])
             self.document_store = FAISS.from_documents(splits, embeddings)
             
-            return f"Document '{file.name}' processed successfully with {len(splits)} text chunks."
+            return f"Document '{file_name}' processed successfully with {len(splits)} text chunks."
         except Exception as e:
             return f"Error processing document: {str(e)}"
 
@@ -278,11 +254,11 @@ def create_interface():
         
         with gr.Row():
             with gr.Column(scale=1):
-                # Updated file component with clearer instructions
+                # Updated file upload component - using file type instead of binary
                 file_upload = gr.File(
                     label="Upload Audit Documents",
                     file_types=["pdf", "docx", "pptx", "xlsx", "xls"],
-                    type="binary"
+                    type="filepath"  # Changed from "binary" to "filepath"
                 )
                 gr.Markdown("Supported formats: PDF, DOCX, PPTX, XLSX, XLS")
         
@@ -395,30 +371,33 @@ def create_interface():
                 error_msg = f"Error solving problem: {str(e)}"
                 return error_msg, error_msg
 
-        # Handle file upload with improved validation
-        def handle_file_upload(file, model_name):
-            if file is None:
+        # Updated file upload handler for filepath type
+        def handle_file_upload(file_path, model_name):
+            if file_path is None:
                 return "No file uploaded. Please upload a file."
                 
-            # Check file extension
-            file_ext = os.path.splitext(file.name.lower())[1] if file.name else ""
-            supported_exts = ['.pdf', '.docx', '.pptx', '.xlsx', '.xls']
-            
-            if file_ext not in supported_exts:
-                return f"Invalid file type: {file_ext}. Please upload a file with one of these extensions: {', '.join(supported_exts)}"
-                
-            status = f"Processing document with {model_name}..."
-            
-            # Get or initialize agent
-            agent, init_status = get_or_initialize_agent(model_name)
-            
-            # If initialization failed
-            if agent is None:
-                return init_status
-            
-            # Process the document
             try:
-                result = agent.process_documents(file)
+                # Extract the filename from the path
+                file_name = os.path.basename(file_path)
+                
+                # Check file extension
+                file_ext = os.path.splitext(file_name.lower())[1]
+                supported_exts = ['.pdf', '.docx', '.pptx', '.xlsx', '.xls']
+                
+                if file_ext not in supported_exts:
+                    return f"Invalid file type: {file_ext}. Please upload a file with one of these extensions: {', '.join(supported_exts)}"
+                    
+                status = f"Processing document with {model_name}..."
+                
+                # Get or initialize agent
+                agent, init_status = get_or_initialize_agent(model_name)
+                
+                # If initialization failed
+                if agent is None:
+                    return init_status
+                
+                # Process the document
+                result = agent.process_documents(file_path, file_name)
                 return result
             except Exception as e:
                 return f"Error processing document: {str(e)}"