Update app.py

app.py

@@ -12,6 +12,7 @@ from langgraph.prebuilt import ToolNode, tools_condition
 from langchain_core.messages import AnyMessage, SystemMessage, HumanMessage
 from langchain_groq import ChatGroq
 from langchain_huggingface import HuggingFaceEndpoint, ChatHuggingFace
+from langchain_ollama import ChatOllama
 
 # (Keep Constants as is)
 # --- Constants ---
@@ -31,13 +32,23 @@ HF_TOKEN = os.getenv("HF_TOKEN")
 #        huggingfacehub_api_token=HF_TOKEN,
 #        provider='auto'
 #)
-llm = HuggingFaceEndpoint(
-    repo_id="mistralai/Mistral-7B-Instruct-v0.2",
-    huggingfacehub_api_token=HF_TOKEN,
-    provider="auto"
-)
 
-chat = ChatHuggingFace(llm=llm, verbose=True)
+checkpoint = "meta-llama/Llama-3.2-3B-Instruct"
+tokenizer = AutoTokenizer.from_pretrained(checkpoint)
+model = AutoModelForCausalLM.from_pretrained(checkpoint, token=HF_TOKEN)
+
+#messages = [{"role": "user", "content": "Hello."}]
+#input_text=tokenizer.apply_chat_template(messages, tokenize=False)
+#print(input_text)
+#inputs = tokenizer.encode(input_text, return_tensors="pt").to(device)
+#outputs = model.generate(inputs, max_new_tokens=50, temperature=0.2, top_p=0.9, do_sample=True)
+#print(tokenizer.decode(outputs[0]))
+
+pipe = pipeline('text-generation', model=model, tokenizer=tokenizer, max_length=2048)
+hf = HuggingFacePipeline(pipeline=pipe)
+
+#chat = ChatHuggingFace(llm=llm, verbose=True)
+chat = ChatOllama(llm=llm)
 
 tools = []
 chat_with_tools = chat.bind_tools(tools)