Update app.py

app.py

@@ -165,51 +165,52 @@ class FileProcessor:
         except Exception:
             return False
 
-    def process_file(self, file) -> List[Dict]:
-        """Process uploaded file with enhanced error handling"""
-        if not file:
+    def process_files(self, files) -> List[Dict]:
+        """Process multiple uploaded files and return a single JSON extraction"""
+        if not files:
             return []
 
-        dataset = []
+        combined_data = []
         try:
-            file_size = os.path.getsize(file.name)
-            if file_size > self.max_file_size:
-                logger.warning(f"File size ({file_size} bytes) exceeds maximum allowed size")
-                return [{"error": f"File size ({file_size} bytes) exceeds maximum allowed size of {self.max_file_size} bytes."}]
+            for file in files:
+                file_size = os.path.getsize(file.name)
+                if file_size > self.max_file_size:
+                    logger.warning(f"File size ({file_size} bytes) exceeds maximum allowed size")
+                    continue  # Skip this file
 
-            with tempfile.TemporaryDirectory() as temp_dir:
                 if zipfile.is_zipfile(file.name):
-                    dataset.extend(self._process_zip_file(file.name, temp_dir))
+                    combined_data.extend(self._process_zip_file(file.name))
                 else:
-                    dataset.extend(self._process_single_file(file))
+                    combined_data.extend(self._process_single_file(file))
 
         except Exception as e:
-            logger.error(f"Error processing file: {str(e)}")
+            logger.error(f"Error processing files: {str(e)}")
             return []
 
-        return dataset
+        return combined_data
 
-    def _process_zip_file(self, zip_path: str, temp_dir: str) -> List[Dict]:
+    def _process_zip_file(self, zip_path: str) -> List[Dict]:
         """Process ZIP file contents"""
         results = []
         with zipfile.ZipFile(zip_path, 'r') as zip_ref:
-            zip_ref.extractall(temp_dir)
-            for root, _, files in os.walk(temp_dir):
-                for filename in files:
-                    filepath = os.path.join(root, filename)
-                    if self.is_text_file(filepath):
-                        try:
-                            with open(filepath, 'r', encoding='utf-8', errors='ignore') as f:
-                                content = f.read()
-                            if content.strip():
-                                results.append({
-                                    "source": "file",
-                                    "filename": filename,
-                                    "content": content,
-                                    "timestamp": datetime.now().isoformat()
-                                })
-                        except Exception as e:
-                            logger.error(f"Error reading file {filename}: {str(e)}")
+            with tempfile.TemporaryDirectory() as temp_dir:
+                zip_ref.extractall(temp_dir)
+                for root, _, files in os.walk(temp_dir):
+                    for filename in files:
+                        filepath = os.path.join(root, filename)
+                        if self.is_text_file(filepath):
+                            try:
+                                with open(filepath, 'r', encoding='utf-8', errors='ignore') as f:
+                                    content = f.read()
+                                if content.strip():
+                                    results.append({
+                                        "source": "file",
+                                        "filename": filename,
+                                        "content": content,
+                                        "timestamp": datetime.now().isoformat()
+                                    })
+                            except Exception as e:
+                                logger.error(f"Error reading file {filename}: {str(e)}")
         return results
 
     def _process_single_file(self, file) -> List[Dict]:
@@ -279,8 +280,9 @@ def create_interface():
         
         with gr.Tab("File Input"):
             file_input = gr.File(
-                label="Upload text file or ZIP archive",
-                file_types=[".txt", ".zip", ".md", ".csv", ".json", ".xml"]
+                label="Upload text files or ZIP archives",
+                file_types=[".txt", ".zip", ".md", ".csv", ".json", ".xml"],
+                multiple=True  # Allow multiple file uploads
             )
 
         with gr.Tab("Text Input"):
@@ -311,7 +313,7 @@ def create_interface():
         # Initialize chatbot
         chatbot = Chatbot()
 
-        def process_all_inputs(urls, file, text):
+        def process_all_inputs(urls, files, text):
             """Process all input types with progress tracking"""
             try:
                 processor = URLProcessor()
@@ -336,8 +338,9 @@ def create_interface():
                                 })
                 
                 # Process files
-                if file:
-                    results.extend(file_processor.process_file(file))
+                if files:
+                    combined_data = file_processor.process_files(files)
+                    results.extend(combined_data)
         
                 # Process text input
                 if text:
@@ -395,7 +398,7 @@ def create_interface():
         gr.Markdown("""
         ### Usage Guidelines
         - **URL Processing**: Enter valid HTTP/HTTPS URLs
-        - **File Input**: Upload text files or ZIP archives
+        - **File Input**: Upload text files or ZIP archives (multiple files allowed)
         - **Text Input**: Direct text processing
         - **Chat**: Load your JSON data and ask questions about it
         - Advanced cleaning and validation included