Update app.py

app.py

@@ -1,47 +1,56 @@
 import gradio as gr
 import pandas as pd
-from io import StringIO
-
-# Function to manipulate CSV based on instruction
-def manipulate_csv(file_path, instruction):
-    if file_path is None:
-        return "Please upload a CSV file", None
-
-    # Read the CSV file
-    original_df = pd.read_csv(file_path)
-    manipulated_df = original_df.copy()
-
-    # Process instruction (basic examples)
+from transformers import pipeline
+import io
+
+# Load the Hugging Face GPT-Neo model
+generator = pipeline('text-generation', model='EleutherAI/gpt-neo-2.7B')
+
+# Function to process CSV file and instruction using Hugging Face GPT-Neo
+def process_csv_with_huggingface(file, instruction):
+    # Read CSV from file
+    df = pd.read_csv(file.name)
+    
+    # Prepare the prompt for GPT-Neo to generate Python code
+    prompt = f"""
+You are an expert in Python and data manipulation using Pandas. You will be given a DataFrame and an instruction. 
+Interpret the instruction and generate Python code to manipulate the DataFrame accordingly.
+Only return the Python code.
+
+Instruction: {instruction}
+
+DataFrame:
+{df.head().to_dict()}
+"""
+    
+    # Request code generation from GPT-Neo
+    response = generator(prompt, max_length=200, num_return_sequences=1)
+
+    # Extract the generated Python code
+    generated_code = response[0]['generated_text'].strip()
+
+    # Execute the generated code
     try:
-        if "add column" in instruction.lower():
-            column_name = instruction.split("add column ")[1]
-            manipulated_df[column_name] = "New Data"
-        elif "filter rows" in instruction.lower():
-            column, value = instruction.split("filter rows ")[1].split("=")
-            manipulated_df = manipulated_df[manipulated_df[column.strip()] == value.strip()]
-        elif "drop column" in instruction.lower():
-            column_name = instruction.split("drop column ")[1]
-            manipulated_df = manipulated_df.drop(columns=[column_name.strip()])
-        else:
-            return "Instruction not recognized. Try: 'add column X', 'filter rows column=value', 'drop column X'", None
+        exec(generated_code, globals(), locals())
+        # After execution, the manipulated DataFrame is stored in 'df'
+        # Convert the DataFrame to CSV for download
+        output = io.StringIO()
+        df.to_csv(output, index=False)
+        output.seek(0)
+        return output.getvalue()
     except Exception as e:
-        return f"Error: {str(e)}", None
-
-    # Return dataframes as HTML tables
-    return original_df.to_html(index=False), manipulated_df.to_html(index=False)
-
+        return f"Error while processing: {str(e)}"
 
 # Gradio Interface
 with gr.Blocks() as demo:
-    gr.Markdown("# CSV Manipulation Tool")
-    file_input = gr.File(label="Upload CSV File", type="filepath")
-    instruction_input = gr.Textbox(label="Instruction (e.g., 'add column new_column')")
-    original_output = gr.HTML(label="Original CSV Data")
-    manipulated_output = gr.HTML(label="Manipulated CSV Data")
+    gr.Markdown("# LLM-Powered CSV Manipulation Tool")
+    file_input = gr.File(label="Upload CSV File", type="file")
+    instruction_input = gr.Textbox(label="Instruction (e.g., 'Add a new column Age with value 30')")
+    output_file = gr.File(label="Download Manipulated CSV")
     run_button = gr.Button("Apply Instruction")
 
     # Link inputs and outputs
-    run_button.click(manipulate_csv, inputs=[file_input, instruction_input], outputs=[original_output, manipulated_output])
+    run_button.click(process_csv_with_huggingface, inputs=[file_input, instruction_input], outputs=[output_file])
 
 # Launch Gradio Interface
 demo.launch()