Upload app.py

app.py

@@ -22,7 +22,6 @@ llm_client = OpenAI()
 # Define the embedding model and the vectorstore
 embedding_model = SentenceTransformerEmbeddings(model_name='thenlper/gte-large')
 
-# Load the persisted vectorDB
 vectorstore_persisted = Chroma(
     collection_name='10k_reports',
     persist_directory='10k_reports_db',
@@ -117,7 +116,7 @@ def llm_query(user_input,company):
             temperature=0
         )
 
-        prediction = response.choices[0].message.content.strip()
+        llm_response = response.choices[0].message.content.strip()
 
     except Exception as e:
         
@@ -135,16 +134,16 @@ def llm_query(user_input,company):
                 {
                     'user_input': user_input,
                     'retrieved_context': context_for_query,
-                    'model_response': prediction
+                    'model_response': llm_response
                 }
             ))
             f.write("\n")
 
-    return prediction
+    return llm_response
 
 # Set-up the Gradio UI
-company = gr.Radio(Label='Company:', choices=["aws", "google", "ibm", "meta", "microsoft"]) # 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"]) # Create a radio button for company selection
+textbox = gr.Textbox(label='Question:') # Create a textbox for user input
 
 # Create Gradio interface
 # For the inputs parameter of Interface provide [textbox,company] with outputs parameter of Interface provide prediction