Update app.py

app.py

@@ -20,7 +20,6 @@ from langchain.indexes import VectorstoreIndexCreator
 
 
 os.environ["OPENAI_API_BASE"] = openai.api_type = "azure"
-os.environ["OPENAI_API_KEY"] = openai.api_key = "26d0aaa9d01340cca61da08b29c44069"
 os.environ["OPENAI_API_BASE"] = openai.api_base = "https://eastus-openai-sean.openai.azure.com/"
 os.environ["OPENAI_API_VERSION"] = openai.api_version = "2023-03-15-preview"
 
@@ -31,7 +30,7 @@ def analyze_healthcare_text(text):
     base_url = "https://ta4h-endpoint.cognitiveservices.azure.com/language/analyze-text/jobs"
     headers = {
         "Content-Type": "application/json",
-        "Ocp-Apim-Subscription-Key": "00667ce9381d46a3a279c4799dd698d0"
+        "Ocp-Apim-Subscription-Key": os.environ["ta4h-api-key"]
     }
 
     # Data to be sent in the initial POST request
@@ -148,11 +147,12 @@ def annotate_text_with_entities(original_text, entities_data):
         original_text = original_text[:start] + entity_html + original_text[end:]
     
     # Create a color key section
-    color_key_section = "<br><br><strong>Color Key:</strong><br>"
+    color_key_section = "<strong>Color Key:</strong><br>"
     for category, color in category_to_color.items():
         color_key_section += f'<span style="display: inline-block; background: {color}; width: 1em; height: 1em; margin-right: 0.5em; vertical-align: middle;"></span>{category}<br>'
     
-    original_text += color_key_section
+    
+    original_text = color_key_section + original_text
     
     return original_text, category_to_color
 
@@ -242,9 +242,9 @@ if 'colour_to_category' not in st.session_state:
     st.session_state.colour_to_category = 'value'
 
 with col1:
-    col1.subheader("DAX Express Input")
+    col1.subheader("Patient Note Input")
 
-    st.text("Enter your DAX Express output below:")
+    st.text("Enter your text input below:")
 
     dax_input = st.text_area("", height=500)
     analyze_btn = st.button("Analyze")
@@ -272,35 +272,28 @@ with col2:
         with st.expander("Show JSON"):
             st.json(st.session_state.r)
 
-        
-         
-
 with col3:
     col3.subheader("Copilot Concept")
-
     question = st.text_input("Ask a question to Copilot:")
-
-
     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 grounded != 'Not Grounded':
         if ask:
             if grounded == 'Text Analytics for Health':
-                total_text = str(st.session_state.r_annotated)
-            else:
+                total_text = str(st.session_state.r)
+            elif grounded == 'Just Text Input':
+                total_text = dax_input
+            elif grounded == 'Both':
                 total_text = str(st.session_state.r) + dax_input
-
-            print(total_text)
-    
+            
+            # 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,
+                chunk_size = 8000,
+                chunk_overlap  = 200,
                 length_function = len,
                 add_start_index = True,
             )
@@ -314,12 +307,13 @@ with col3:
                 openai_api_type="azure",
                 chunk_size=16,
             )
+            index = ""
             index = VectorstoreIndexCreator(embedding=embeddings).from_documents(texts)
 
             st.write(index.query(question, llm=AzureChatOpenAI(temperature=0, deployment_name=model)))
-            
 
     elif ask:
+        print("not grounded")
         response = openai.ChatCompletion.create(
     engine=model,
     messages = [{"role":"system","content":"You are an AI assistant that helps people find information."}, {"role": "user", "content" : question}],