Upload app.py

app.py

@@ -25,7 +25,7 @@ model_name = 'gpt-4o-mini' # e.g. 'gpt-3.5-turbo'
 # Initialize the ChatOpenAI model
 llm = ChatOpenAI(model_name=model_name, temperature=0)  # Set temperature to 0 for deterministic output
 # Create a HumanMessage
-user_message = HumanMessage(content="What's the weather like today?")
+#user_message = HumanMessage(content="What's the weather like today?")
 
 # Define the embedding model and the vectorstore
 embedding_model = SentenceTransformerEmbeddings(model_name='thenlper/gte-large')
@@ -127,7 +127,8 @@ def llm_query(user_input,company):
         #     temperature=0
         # )
 
-        llm_response = response.choices[0].message.content.strip()
+        #llm_response = response.choices[0].message.content.strip()
+        llm_response = response.content.strip()
 
     except Exception as e:
         
@@ -153,12 +154,12 @@ def llm_query(user_input,company):
     return llm_response
 
 # Set-up the Gradio UI
-company = gr.Radio(label='Company:', choices=["aws", "google", "ibm", "meta", "microsoft"], value="aws") # Create a radio button for company selection
 textbox = gr.Textbox(label='Question:') # Create a textbox for user input
+company = gr.Radio(label='Company:', choices=["aws", "google", "ibm", "meta", "microsoft"], value="aws") # Create a radio button for company selection
 
 # Create Gradio interface
 # For the inputs parameter of Interface provide [textbox,company] with outputs parameter of Interface provide prediction
 demo = gr.Interface(fn=llm_query, inputs=[textbox, company], outputs="text", title="Financial Analyst Assistant", description="Ask questions about the financial performance of AWS, Google, IBM, Meta, and Microsoft based on their 10-K reports.\n\nPlease enter a question below.")
 
 demo.queue()
-demo.launch()
+demo.launch()