Upload app.py with huggingface_hub

app.py

@@ -41,6 +41,12 @@ model_name = "gpt-4o-mini"
 api_key = os.getenv("OPENAI_API_KEY")
 endpoint = os.getenv("OPENAI_API_BASE")
 
+llm = ChatOpenAI(
+    openai_api_base=endpoint,  # Fill in the endpoint
+    openai_api_key=api_key,  # Fill in the API key
+    model="gpt-4o-mini",  # Fill in the deployment name (e.g., gpt-4o-mini)
+    streaming=False)
+
 # Define the location of the SQLite database
 db_loc = 'ecomm.db'
 
@@ -108,13 +114,6 @@ full_prompt = ChatPromptTemplate.from_messages(
     ]
 )
 
-#Initialize the ChatOpenAI model with the extracted configuration
-llm = ChatOpenAI(
-    openai_api_base=endpoint,
-    openai_api_key=api_key,
-    model="gpt-4o-mini",  # Fill in the deployment name (e.g., gpt-4o-mini)
-    streaming=False)
-
 
 # Create the SQL agent using the ChatOpenAI model, database, and prompt template
 sqlite_agent = create_sql_agent(
@@ -260,10 +259,10 @@ retriever = vector_store.as_retriever(
     search_kwargs={'k': 5}
 )
 
-client = OpenAI(
-    api_key=api_key,
-    base_url=endpoint
-)
+# client = OpenAI(
+#     api_key=api_key,
+#     base_url=endpoint
+# )
 
 @tool
 def rag(user_input: str) -> str:
@@ -290,7 +289,7 @@ def rag(user_input: str) -> str:
     }
     ]
     try:
-        response = client.chat.completions.create(
+        response = llm.chat.completions.create(
         model="gpt-4o-mini",
         messages=prompt
         )
@@ -550,15 +549,15 @@ def chatbot_interface():
     tools = [sql_tool,defer_to_human, rag, register_feedback, days_since]
 
 
-    chatbot = ChatOpenAI(
-    openai_api_base=endpoint,
-    openai_api_key=api_key,
-    model="gpt-4o-mini",
-    streaming=False, # Explicitly disabling streaming
-    temperature=0
-    )
+    # chatbot = ChatOpenAI(
+    # openai_api_base=endpoint,
+    # openai_api_key=api_key,
+    # model="gpt-4o-mini",
+    # streaming=False, # Explicitly disabling streaming
+    # temperature=0
+    # )
 
-    agent = create_tool_calling_agent(chatbot, tools, prompt)
+    agent = create_tool_calling_agent(llm, tools, prompt)
     agent_executor = AgentExecutor(agent=agent, tools=tools, verbose=True)
 
     # Display chat messages from history on app rerun