Update app.py

app.py

@@ -12,7 +12,7 @@ from folium.plugins import Fullscreen
 from geopy.geocoders import Nominatim
 from collections import OrderedDict
 from geopy.adapters import AioHTTPAdapter
-from huggingface_hub import InferenceClient
+from langchain_nvidia_ai_endpoints import ChatNVIDIA
 
 from examples import (
     description_sf,
@@ -24,8 +24,8 @@ from examples import (
     trip_examples
 )
 
-repo_id = "meta-llama/Meta-Llama-3.1-8B-Instruct"
-llm_client = InferenceClient(model=repo_id, timeout=180, token=os.getenv("hf_token"))
+repo_id = "meta/llama-3.1-405b-instruct"
+llm_client = ChatNVIDIA(model=repo_id)
 end_sequence = "I hope that helps!"
 
 def generate_key_points(text):
@@ -49,7 +49,7 @@ Now begin. You can make the descriptions a bit more verbose than in the examples
 
 Description: {text}
 Thought:"""
-    return llm_client.text_generation(prompt, max_new_tokens=2000, stream=True, stop_sequences=[end_sequence])
+    return llm_client.invoke(prompt).content
 
 
 def parse_llm_output(output):