Upload app.py

app.py

@@ -21,11 +21,8 @@ os.environ['OPENAI_API_KEY']  = "gl-U2FsdGVkX1+0bNWD6YsVLZUYsn0m1WfLxUzrP0xUFbtW
 os.environ["OPENAI_BASE_URL"] =  "https://aibe.mygreatlearning.com/openai/v1" # e.g. "https://aibe.mygreatlearning.com/openai/v1";
 
 model_name = 'gpt-4o-mini' # e.g. 'gpt-3.5-turbo'
-# llm_client = OpenAI()
-# 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?")
 
 # Define the embedding model and the vectorstore
 embedding_model = SentenceTransformerEmbeddings(model_name='thenlper/gte-large')
@@ -121,13 +118,6 @@ def llm_query(user_input,company):
         # Call the chat model with the message
         response = llm(prompt)
         
-        # response = llm_client.chat.completions.create(
-        #     model=model_name,
-        #     messages=prompt,
-        #     temperature=0
-        # )
-
-        #llm_response = response.choices[0].message.content.strip()
         llm_response = response.content.strip()
 
     except Exception as e:
@@ -137,9 +127,7 @@ def llm_query(user_input,company):
     print(llm_response)
 
     # While the prediction is made, log both the inputs and outputs to a local log file
-    # While writing to the log file, ensure that the commit scheduler is locked to avoid parallel
-    # access
-
+    # While writing to the log file, ensure that the commit scheduler is locked to avoid parallel access
     with scheduler.lock:
         with log_file.open("a") as f:
             f.write(json.dumps(
@@ -159,7 +147,7 @@ company = gr.Radio(label='Company:', choices=["aws", "google", "IBM", "Meta", "m
 
 # 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.", theme=gr.themes.Soft())
+demo = gr.Interface(fn=llm_query, inputs=[textbox, company], outputs="text", title="FY23 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.", theme=gr.themes.Soft())
 
 demo.queue()
-demo.launch()
+demo.launch()