Update app.py

app.py

@@ -1,27 +1,30 @@
-import streamlit as st
+import gradio as gr
 from transformers import T5Tokenizer, T5ForConditionalGeneration
 
-@st.cache_resource
-def load_model():
-    tokenizer = T5Tokenizer.from_pretrained("Salesforce/codet5-base")
-    model = T5ForConditionalGeneration.from_pretrained("Salesforce/codet5-base")
-    return tokenizer, model
+# Load CodeT5 model and tokenizer
+tokenizer = T5Tokenizer.from_pretrained("Salesforce/codet5-base")
+model = T5ForConditionalGeneration.from_pretrained("Salesforce/codet5-base")
 
-tokenizer, model = load_model()
+# Function to explain code
+def explain_code(code_snippet):
+    if not code_snippet.strip():
+        return "❗ Please enter some code."
+    
+    input_text = f"summarize: {code_snippet.strip()}"
+    input_ids = tokenizer.encode(input_text, return_tensors="pt", truncation=True, max_length=512)
+    outputs = model.generate(input_ids, max_length=150, num_beams=4, early_stopping=True)
+    explanation = tokenizer.decode(outputs[0], skip_special_tokens=True)
+    
+    return explanation
 
-st.title("🧠 Code Explainer (CodeT5)")
-st.markdown("Paste code and get an explanation using the CodeT5 model from Hugging Face.")
+# Gradio Interface
+demo = gr.Interface(
+    fn=explain_code,
+    inputs=gr.Textbox(lines=15, label="Paste your code here"),
+    outputs=gr.Textbox(label="Explanation"),
+    title="🧠 Code Explainer using Hugging Face",
+    description="This tool uses Salesforce's CodeT5 to convert your code into a human-readable explanation. Works on CPU!",
+    theme="default"
+)
 
-code_input = st.text_area("Paste your code here:", height=200)
-
-if st.button("Explain Code"):
-    if code_input.strip() == "":
-        st.warning("Please paste some code first.")
-    else:
-        with st.spinner("Generating explanation..."):
-            input_text = f"summarize: {code_input.strip()}"
-            input_ids = tokenizer.encode(input_text, return_tensors="pt", truncation=True, max_length=512)
-            outputs = model.generate(input_ids, max_length=150, num_beams=4, early_stopping=True)
-            summary = tokenizer.decode(outputs[0], skip_special_tokens=True)
-            st.success("Explanation:")
-            st.write(summary)
+demo.launch()