Update app.py

app.py

@@ -35,12 +35,8 @@ severities = {
     "Best Practice": "Low"
 }
 
-# ---------- Load QnA Model (optimized) ----------
-qa_pipeline = pipeline(
-    "text2text-generation",
-    model="google/flan-t5-base",  # ✅ Smaller, faster model
-    device=-1  # ✅ Use CPU explicitly or 0 for GPU if available
-)
+# ---------- Load QnA Model (no fallback) ----------
+qa_pipeline = pipeline("text2text-generation", model="google/flan-t5-large")
 
 # ---------- Logging ----------
 def log_to_console(data, log_type):
@@ -181,7 +177,7 @@ Assistant:
 """
 
     try:
-        result = qa_pipeline(prompt, max_new_tokens=512, do_sample=False, temperature=0.1, top_k=50)  # ✅ Faster
+        result = qa_pipeline(prompt, max_new_tokens=1024, do_sample=False, temperature=0.1, top_k=50)
         output = result[0]["generated_text"].strip()
         if output.startswith("Assistant:"):
             output = output.replace("Assistant:", "").strip()
@@ -240,4 +236,4 @@ with gr.Blocks(theme=gr.themes.Soft()) as demo:
         clear_button.click(fn=clear_chat, inputs=None, outputs=[chatbot_output, query_input])
 
 if __name__ == "__main__":
-    demo.launch()
+    demo.launch()