Update app.py

app.py

@@ -14,8 +14,7 @@ import os
 
 df_chunks = pd.read_pickle('Chunks_Complete.pkl')
 
-placeHolderPersona1 = """
-##Mission
+placeHolderPersona1 = """##Mission
 Please create a highly targeted query for a semantic search engine. The query must represent the conversation to date. 
 ** You will be given the converstaion to date in the user prompt.
 ** If no converstaion provided then this is the first converstaion
@@ -49,8 +48,8 @@ def format_elapsed_time(time):
     # Format the elapsed time to two decimal places
     return "{:.2f}".format(time)
 
-def search_knowledgebase(query, k):
-    results = retriever(query, k)
+def search_knowledgebase(query):
+    results = retriever(query)
     return results
 
 def process_search_results(search_results):
@@ -109,7 +108,7 @@ def lookup_related_chunks(df_chunks, chunk_id):
     return df_chunks[(df_chunks['Title'] == title) & (df_chunks['PageNumber'].isin(page_range))]
 
 
-def search_and_reconstruct(query, df_chunks, k):
+def search_and_reconstruct(query, df_chunks):
     """
     Combines search, lookup of related chunks, and text reconstruction.
 
@@ -119,7 +118,7 @@ def search_and_reconstruct(query, df_chunks, k):
     :param top_k: Number of top search results to retrieve.
     :return: A list of dictionaries with document title, page number, and reconstructed text.
     """
-    search_results = search_knowledgebase(query, k)
+    search_results = search_knowledgebase(query)
     processed_results = process_search_results(search_results)
 
     reconstructed_results = []
@@ -131,14 +130,14 @@ def search_and_reconstruct(query, df_chunks, k):
 
         reconstructed_results.append({
             "Title": result['Title'],
-            "Score": result['score'],
+            "score": result['score'],
             "PageNumber": result['PageNumber'],
             "ReconstructedText": reconstructed_text
         })
 
     return reconstructed_results
 
-def call_chat_api(data: ChatRequestClient, k):
+def call_chat_api(data: ChatRequestClient):
     url = "https://agent-builder-api.greensea-b20be511.northeurope.azurecontainerapps.io/chat/"
     # Validate and convert the data to a dictionary
     validated_data = data.dict()
@@ -149,7 +148,7 @@ def call_chat_api(data: ChatRequestClient, k):
     if response.status_code == 200:
         body = response.json()
         query = body.get("content")
-        final_results = search_and_reconstruct(query, df_chunks, k)
+        final_results = search_and_reconstruct(query, df_chunks)
         return body, final_results # Return the JSON response if successful
     else:
         return "An error occured"  # Return the raw response text if not successful
@@ -171,8 +170,7 @@ persona1SystemMessage = st.sidebar.text_area("Query Designer System Message", va
 
 llm1 = st.sidebar.selectbox("Model Selection", ['GPT-4', 'GPT3.5'], key='persona1_size')
 temp1 = st.sidebar.slider("Temperature", min_value=0.0, max_value=1.0, step=0.1, value=0.6, key='persona1_temp')
-tokens1 = st.sidebar.slider("Tokens", min_value=1, max_value=4000, step=100, value=500, key='persona1_tokens')
-k = st.sidebar.slider("Returned Docs", min_value=1, max_value=10, step=1, value=3, key='k')
+tokens1 = st.sidebar.slider("Tokens", min_value=0, max_value=4000, step=100, value=500, key='persona1_tokens')
 
 st.sidebar.caption(f"Session ID: {genuuid()}")
 
@@ -225,7 +223,7 @@ else:
             temperature2=0.2
         )
 
-        response, retrival = call_chat_api(data, k)
+        response, retrival = call_chat_api(data)
         agent_message = response.get("content", "No response received from the agent.")
         elapsed_time = response.get("elapsed_time", 0)
         st.session_state.messages.append({"role": "assistant", "content": agent_message})
@@ -238,14 +236,13 @@ else:
                 st.markdown(message["content"])
 
         if response:
-            # st.chat_message("assistant").markdown(response.get("content", "No response"))
+            st.chat_message("assistant").markdown(response.get("content", "No response"))
             st.caption(f"##### Time taken: {format_elapsed_time(response.get('elapsed_time', 0))} seconds")
 
     with col2:
         for entry in retrival:
             with st.container():
                 st.write(f"**Title:** {entry['Title']}")
+                st.write(f"**Score** {entry['score']}")
                 st.write(f"**Page Number:** {entry['PageNumber']}")
-                st.text_area("Grounding Text", entry['ReconstructedText'], height=150)
-
-
+                st.write("Grounding Text", entry['ReconstructedText'], height=150)