Update app.py

app.py

@@ -272,32 +272,55 @@ with col2:
             st.json(st.session_state.r)
 
         
-        
-        
+         
 
 with col3:
     col3.subheader("Copilot Concept")
 
     question = st.text_input("Ask a question to Copilot:")
 
-    toggle = st.toggle("Grounded", False)
 
+    grounded = st.selectbox('Would you like to ground the model?', ('Not Grounded', 'Text Analytics for Health', 'Just Text Input', 'Both'))
+
+    model = st.selectbox("Model", ["gpt-35-turbo", "gpt-4" ])
 
     ask = st.button("Ask")
-    if toggle:
+    if grounded != 'Not Grounded':
         if ask:
-            json_spec = JsonSpec(dict_=st.session_state.r, max_value_length=7000)
-            json_toolkit = JsonToolkit(spec=json_spec)
+            if grounded == 'Text Analytics for Health':
+                total_text = str(st.session_state.r_annotated)
+            else:
+                total_text = str(st.session_state.r) + dax_input
 
-            json_agent_executor = create_json_agent(
-                llm=AzureChatOpenAI(temperature=0, deployment_name="gpt-4"), toolkit=json_toolkit, verbose=True
+            print(total_text)
+    
+            from langchain.text_splitter import RecursiveCharacterTextSplitter
+
+            text_splitter = RecursiveCharacterTextSplitter(
+                # Set a really small chunk size, just to show.
+                chunk_size = 3000,
+                chunk_overlap  = 20,
+                length_function = len,
+                add_start_index = True,
+            )
+            texts = text_splitter.create_documents([total_text])
+            
+            from langchain.embeddings.openai import OpenAIEmbeddings
+            embeddings = OpenAIEmbeddings(
+                deployment="text-embedding-ada-002",
+                model="text-embedding-ada-002",
+                openai_api_base="https://eastus-openai-sean.openai.azure.com/",
+                openai_api_type="azure",
+                chunk_size=16,
             )
+            index = VectorstoreIndexCreator(embedding=embeddings).from_documents(texts)
 
-            st.write(json_agent_executor.run(question))
+            st.write(index.query(question, llm=AzureChatOpenAI(temperature=0, deployment_name=model)))
+            
 
     elif ask:
         response = openai.ChatCompletion.create(
-    engine="gpt-4",
+    engine=model,
     messages = [{"role":"system","content":"You are an AI assistant that helps people find information."}, {"role": "user", "content" : question}],
     temperature=0.7,
     max_tokens=800,