Starter LLM Inference Call

app.py

@@ -1,4 +1,5 @@
 from langchain_community.utilities import SQLDatabase
+from langchain_community.chat_models import ChatHuggingFace
 from langchain_openai import ChatOpenAI
 from langchain_community.agent_toolkits import create_sql_agent
 import pandas as pd
@@ -55,13 +56,15 @@ The 'tickets' table contains Jira ticket data with columns:
 #llm = ChatOpenAI(model="gpt-4o-mini", temperature=0)
 
 #llm = InferenceClient(api_key=settings.HF_TOKEN)
-llm = HuggingFaceEndpoint(
+endpoint = HuggingFaceEndpoint(
     repo_id="meta-llama/Llama-3.1-8B-Instruct",
     huggingfacehub_api_token=os.environ["HF_TOKEN"],
     temperature=0.1,
     max_new_tokens=512
 )
 
+llm = ChatHuggingFace(llm=endpoint)
+
 agent = create_sql_agent(
     llm, 
     db=db,