Update app.py

app.py

@@ -4,6 +4,9 @@ import requests
 import inspect
 import pandas as pd
 
+import torch
+from transformers import pipeline
+
 # (Keep Constants as is)
 # --- Constants ---
 DEFAULT_API_URL = "https://agents-course-unit4-scoring.hf.space"
@@ -12,16 +15,31 @@ DEFAULT_API_URL = "https://agents-course-unit4-scoring.hf.space"
 # ----- THIS IS WERE YOU CAN BUILD WHAT YOU WANT ------
 class BasicAgent:
     def __init__(self):
-        print("BasicAgent initialized.")
+        print("🔄 Loading HF LLM pipeline...")
+        self.llm = pipeline(
+            "text-generation",
+            model="mistralai/Mistral-7B-Instruct-v0.2",
+            tokenizer="mistralai/Mistral-7B-Instruct-v0.2",
+            max_new_tokens=200,
+            temperature=0,
+            device=0 if torch.cuda.is_available() else -1  # Use GPU if available
+        )
+        print("✅ LLM Loaded.")
+
     def __call__(self, question: str) -> str:
-        print(f"Agent received question: {question}")
+        print(f"🤖 Agent received question: {question}")
+
+        # Format as instruction
+        prompt = f"[INST] {question} [/INST]"
         
-        # Simple hardcoded logic
-        if "capital of France" in question.lower():
-            return "Paris"
-        elif "2 + 2" in question:
-            return "4"
-        else:
+        try:
+            output = self.llm(prompt)[0]["generated_text"]
+            # Strip original prompt from output
+            answer = output.replace(prompt, "").strip()
+            print(f"✅ Answer: {answer}")
+            return answer
+        except Exception as e:
+            print(f"❌ Error: {e}")
             return "I don't know"
 
 def run_and_submit_all( profile: gr.OAuthProfile | None):