add the google sheet connection

app.py

@@ -2,6 +2,7 @@ import streamlit as st
 import pandas as pd
 import numpy as np
 import datetime
+import gspread
 import pickle
 import os
 import csv
@@ -42,12 +43,6 @@ def load_scraped_web_info():
     chunked_text = text_splitter.create_documents([doc for doc in tqdm(ait_web_documents)])
 
 
-    # st.markdown(f"Number of Documents: {len(ait_web_documents)}")
-    # st.markdown(f"Number of chunked texts: {len(chunked_text)}")
-
-
-
-
 @st.cache_resource
 def load_embedding_model():
     embedding_model = HuggingFaceInstructEmbeddings(model_name='hkunlp/instructor-base',
@@ -74,8 +69,6 @@ def load_llm_model():
                                         model_kwargs={ "max_length": 256, "temperature": 0,
                                                       "torch_dtype":torch.float32,
                                                     "repetition_penalty": 1.3})
-
-
     return llm
 
 
@@ -85,6 +78,45 @@ def load_retriever(llm, db):
 
     return qa_retriever
 
+def retrieve_document(query_input):
+    related_doc = vector_database.similarity_search(query_input)
+    return related_doc
+
+def retrieve_answer(query_input):
+    prompt_answer=  query_input + " " + "Try to elaborate as much as you can."
+    answer = qa_retriever.run(prompt_answer)
+    output = st.text_area(label="Retrieved documents", value=answer)
+    
+    st.markdown('---')
+    score = st.radio(label = 'please select the rating score for overall satifaction and helpfullness of the bot answer', options=[0, 1,2,3,4,5], horizontal=True,
+                     on_change=update_worksheet_qa, key='rating')
+
+    return answer
+    
+# def update_score():
+#     st.session_state.session_rating = st.session_state.rating
+
+
+def update_worksheet_qa():
+    st.session_state.session_rating = st.session_state.rating
+    #This if helps validate the initiated rating, if 0, then the google sheet would not be updated
+    if st.session_state.session_rating  == 0:
+        pass
+    else:
+        worksheet_qa.append_row([st.session_state.history[-1]['timestamp'].strftime(datetime_format), 
+                                st.session_state.history[-1]['question'],
+                                st.session_state.history[-1]['generated_answer'], 
+                                st.session_state.session_rating 
+                                ])
+        
+def update_worksheet_comment():
+    worksheet_comment.append_row([datetime.datetime.now().strftime(datetime_format),
+                                feedback_input])
+    success_message = st.success('Feedback successfully submitted, thank you', icon="✅",
+               )
+    time.sleep(3)
+    success_message.empty()
+
 #--------------
 
 
@@ -92,9 +124,14 @@ if "history" not in st.session_state:
     st.session_state.history = []
 if "session_rating" not in st.session_state:
     st.session_state.session_rating = 0
-    
-def update_score():
-    st.session_state.session_rating = st.session_state.rating
+
+
+service_account = gspread.service_account_from_dict(credential)
+workbook= service_account.open("aitGPT-qa-log")
+worksheet_qa = workbook.worksheet("Sheet1")
+worksheet_comment = workbook.worksheet("Sheet2")
+datetime_format= "%Y-%m-%d %H:%M:%S"
+
 
 
 load_scraped_web_info()
@@ -108,20 +145,7 @@ print("all load done")
 
 
 
-def retrieve_document(query_input):
-    related_doc = vector_database.similarity_search(query_input)
-    return related_doc
 
-def retrieve_answer(query_input):
-    prompt_answer=  query_input + " " + "Try to elaborate as much as you can."
-    answer = qa_retriever.run(prompt_answer)
-    output = st.text_area(label="Retrieved documents", value=answer)
-    
-    st.markdown('---')
-    score = st.radio(label = 'please select the overall satifaction and helpfullness of the bot answer', options=[1,2,3,4,5], horizontal=True,
-                     on_change=update_score, key='rating')
-
-    return answer
     
 
 
@@ -134,10 +158,13 @@ st.markdown("""
 st.write(' ⚠️ Please expect to wait **~ 10 - 20 seconds per question** as thi app is running on CPU against 3-billion-parameter LLM')
 
 st.markdown("---")
+st.write(" ")
+st.write("""
+         ### ❔ Ask a question
+         """)
 
-
-query_input = st.text_area(label= 'What would you like to know about AIT?')
-generate_button = st.button(label = 'Submit!')
+query_input = st.text_area(label= 'What would you like to know about AIT?' , key = 'my_text_input')
+generate_button = st.button(label = 'Ask question!')
 
 if generate_button:
     answer = retrieve_answer(query_input)
@@ -147,21 +174,36 @@ if generate_button:
         "rating":st.session_state.session_rating }
 
     st.session_state.history.append(log)
+    update_worksheet_qa()
 
 
+st.write(" ")
+st.write(" ")
 
-if st.session_state.session_rating == 0:
-    pass
-else:
-    with open('test_db', 'a') as csvfile:
-        writer = csv.writer(csvfile)
-        writer.writerow([st.session_state.history[-1]['timestamp'], st.session_state.history[-1]['question'],
-                            st.session_state.history[-1]['generated_answer'], st.session_state.session_rating ])
-        st.session_state.session_rating = 0
-
-test_df = pd.read_csv("test_db", index_col=0)
-test_df.sort_values(by = ['timestamp'],
-                    axis=0,
-                    ascending=False,
-                    inplace=True)
-st.dataframe(test_df)
+st.markdown("---")
+st.write("""
+         ### 💌 Your voice matters
+         """)
+
+feedback_input = st.text_area(label= 'please leave your feedback or any ideas to make this bot more knowledgeable and fun')
+feedback_button = st.button(label = 'Submit feedback!')
+
+if feedback_button:
+    update_worksheet_comment()
+
+
+# if st.session_state.session_rating == 0:
+#     pass
+# else:
+#     with open('test_db', 'a') as csvfile:
+#         writer = csv.writer(csvfile)
+#         writer.writerow([st.session_state.history[-1]['timestamp'], st.session_state.history[-1]['question'],
+#                             st.session_state.history[-1]['generated_answer'], st.session_state.session_rating ])
+#         st.session_state.session_rating = 0
+
+# test_df = pd.read_csv("test_db", index_col=0)
+# test_df.sort_values(by = ['timestamp'],
+#                     axis=0,
+#                     ascending=False,
+#                     inplace=True)
+# st.dataframe(test_df)