Update app.py

app.py

@@ -1,26 +1,27 @@
 import streamlit as st
-from transformers import pipeline
+from transformers import T5Tokenizer, T5ForConditionalGeneration
 
-# Load the code explainer pipeline
 @st.cache_resource
 def load_model():
-    return pipeline("text2text-generation", model="philschmid/code-explainer", device=-1)
+    tokenizer = T5Tokenizer.from_pretrained("Salesforce/codet5-base")
+    model = T5ForConditionalGeneration.from_pretrained("Salesforce/codet5-base")
+    return tokenizer, model
 
-explainer = load_model()
+tokenizer, model = load_model()
 
-# Streamlit UI
-st.title("🧠 Code Explainer (Hugging Face)")
+st.title("🧠 Code Explainer (CodeT5)")
+st.markdown("Paste code and get an explanation using the CodeT5 model from Hugging Face.")
 
-st.markdown("Paste any code snippet below (Python, JavaScript, etc.) and get a plain-English explanation using a Hugging Face model.")
-
-code_input = st.text_area("📝 Paste your code here:", height=200)
+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 to explain.")
+        st.warning("Please paste some code first.")
     else:
-        with st.spinner("Explaining your code..."):
-            result = explainer(f"Explain this code: {code_input}")
-            explanation = result[0]['generated_text']
-            st.success("✅ Explanation:")
-            st.write(explanation)
+        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)