Update chatbot_rag.py

chatbot_rag.py

@@ -29,17 +29,19 @@ def build_qa():
 
     # 3. Load LLM (Phi-3 mini)
     print("🔹 Loading LLM...")
-    model_id = "declare-lab/flan-alpaca-large"
+    model_id = "meta-llama/Llama-3.2-1B-Instruct"   # or "meta-llama/Llama-3.1-1B-Instruct"
     tokenizer = AutoTokenizer.from_pretrained(model_id)
-    model = AutoModelForSeq2SeqLM.from_pretrained(model_id)
+    model = AutoModelForCausalLM.from_pretrained(model_id)
     
     pipe = pipeline(
-        "text2text-generation",   
+        "text-generation",
         model=model,
         tokenizer=tokenizer,
-        max_new_tokens=300,
-        do_sample=False,          
+        max_new_tokens=256,
+        temperature=0.7,
+        do_sample=True
     )
+    
     llm = HuggingFacePipeline(pipeline=pipe)
 
     # 4. Retriever