Update app.py

app.py

@@ -46,8 +46,11 @@ def process_dataset(file):
     cleaned_data = clean_data(data)
     
     # Step 2: Create chunks
-    cleaned_data['chunks'] = cleaned_data['text_column'].apply(chunk_text)
-    
+    if 'text_column' in cleaned_data.columns:
+        cleaned_data['chunks'] = cleaned_data['text_column'].apply(chunk_text)
+    else:
+        return "Error: 'text_column' not found in the dataset."
+
     # Step 3: Generate embeddings
     cleaned_data['embeddings'] = cleaned_data['chunks'].apply(lambda chunks: [generate_embeddings(chunk) for chunk in chunks])
     
@@ -63,8 +66,8 @@ def gradio_interface(file):
 # Gradio App
 ui = gr.Interface(
     fn=gradio_interface,
-    inputs=gr.inputs.File(label="Upload CSV Dataset"),
-    outputs=gr.outputs.Textbox(label="Processing Result"),
+    inputs=gr.File(label="Upload CSV Dataset"),
+    outputs=gr.Textbox(label="Processing Result"),
     title="Data Cleaning and Embedding Tool",
     description="Upload your dataset to clean, chunk, and generate embeddings using Llama LLM with Groq API. Perfect for deployment on Hugging Face.",
     theme="compact",