Update app.py

app.py

@@ -1,30 +1,41 @@
-import streamlit as st
+import gradio as gr
 from transformers import AutoModelForCausalLM, AutoTokenizer, pipeline
 
-# Load the model and tokenizer
+# Load a proper text-generation model
 model_name = "gpt2"  # Replace with your own trained model if available
 model = AutoModelForCausalLM.from_pretrained(model_name)
 tokenizer = AutoTokenizer.from_pretrained(model_name)
 
-# Create a text generation pipeline
+# Create a text-generation pipeline
 nlp_pipeline = pipeline("text-generation", model=model, tokenizer=tokenizer)
 
-# Streamlit UI
-st.title("🧠 AI Text Generator")
-st.markdown("Enter text and get AI-generated responses! Customize the input and see how the model responds.")
+# Function to generate response
+def generate_response(text):
+    try:
+        # Increase max_length for longer output
+        result = nlp_pipeline(text, max_length=200, do_sample=True)
+        return result[0]['generated_text']
+    except Exception as e:
+        return f"Error: {str(e)}"
 
-# Text input
-input_text = st.text_area("Enter Text", placeholder="Type something here...", height=120)
+# Create Gradio Interface using Blocks for flexible layout
+with gr.Blocks() as iface:
+    gr.Markdown("# AI Text Generator")
+    gr.Markdown("Enter text and get AI-generated responses! Customize the input and see how the model responds.")
+    
+    with gr.Row():
+        # Textbox for input
+        input_text = gr.Textbox(label="Enter Text", placeholder="Type something here...", lines=3, max_lines=5)
+        
+    with gr.Row():
+        # Output box
+        output_text = gr.Textbox(label="Generated Response", lines=6, max_lines=8)
+    
+    # Button to trigger the text generation
+    generate_btn = gr.Button("Generate Response")
+    
+    # Define button click action
+    generate_btn.click(generate_response, inputs=input_text, outputs=output_text)
 
-# Button click
-if st.button("Generate Response"):
-    if input_text.strip() == "":
-        st.warning("Please enter some text.")
-    else:
-        try:
-            with st.spinner("Generating response..."):
-                result = nlp_pipeline(input_text, max_length=200, do_sample=True)
-                generated_text = result[0]['generated_text']
-            st.text_area("Generated Response", value=generated_text, height=180)
-        except Exception as e:
-            st.error(f"Error: {str(e)}")
+# Launch Gradio UI (No need to specify theme and layout directly now)
+iface.launch(server_name="0.0.0.0", server_port=7860) i have created it with gradio now i want to convert it into streamlit