Update app.py

app.py

@@ -11,7 +11,7 @@ import json
 
 os.environ["api_key"] == st.secrets["api_key"]
 
-#os.environ["OPENAI_API_KEY"] = api_key
+#os.environ["OPENAI_API_KEY"] = api_key 
 openai.api_key = os.getenv("api_key")
 
 os.environ["GSPREAD_CREDENTIALS"]=  st.secrets["GSPREAD_CREDENTIALS"]
@@ -62,7 +62,7 @@ if page == 'Review Analysis':
     sheet_url = st.text_input('Enter the URL of your Google Sheet')
 
     # Add this in the part of your Streamlit app where the user can select the model
-    models = ["gpt-3.5-turbo", "gpt-4"]
+    models = ["gpt-3.5-turbo", "gpt-4", "gpt-3.5-turbo-16k"]
     selected_model = st.selectbox("Choose a model:", models)
 
     user_char_limit = st.number_input("Enter character limit for chunk:", value=9000, step=500)
@@ -291,7 +291,7 @@ if page == 'Feature Benefits':
     # prompt = st.text_area("Edit the prompt:", value=default_prompt, height=200)
 
     # Add this in the part of your Streamlit app where the user can select the model
-    models = ["gpt-3.5-turbo", "gpt-4"]
+    models = ["gpt-3.5-turbo", "gpt-4", "gpt-3.5-turbo-16k"]
     selected_model = st.selectbox("Choose a model:", models)
     
     # Extract sheet ID from URL
@@ -494,7 +494,7 @@ if page == 'Identify Avatars':
     sheet = gc.open_by_key(sheet_id)
 
     # Add this in the part of your Streamlit app where the user can select the model
-    models = ["gpt-3.5-turbo", "gpt-4"]
+    models = ["gpt-3.5-turbo", "gpt-4", "gpt-3.5-turbo-16k"]
     selected_model = st.selectbox("Choose a model:", models)
     
 
@@ -647,7 +647,7 @@ if page == 'Tone of Voice Manual':
     sheet = gc.open_by_key(sheet_id)
 
     # Add this in the part of your Streamlit app where the user can select the model
-    models = ["gpt-3.5-turbo", "gpt-4"]
+    models = ["gpt-3.5-turbo", "gpt-4", "gpt-3.5-turbo-16k"]
     selected_model = st.selectbox("Choose a model:", models)
 
     # Add the prompt
@@ -776,7 +776,7 @@ if page == 'review summary':
     sheet_url = st.text_input('Enter the URL of your Google Sheet')
 
     # Add this in the part of your Streamlit app where the user can select the model
-    models = ["gpt-3.5-turbo", "gpt-4"]
+    models = ["gpt-3.5-turbo", "gpt-4", "gpt-3.5-turbo-16k"]
     selected_model = st.selectbox("Choose a model:", models)
 
      # Set default prompts
@@ -989,197 +989,263 @@ if page == 'review summary':
             st.error(f"An error occurred while writing to Google Sheets: {e}")
 
 
-if page == 'question_answers':
-    st.title('question answers')
+# if page == 'question_answers':
+#     st.title('question answers')
 
-    #gc = gspread.service_account(filename='arctic-rite-381810-e8bee8664772.json')
-    gc = gspread.service_account_from_dict(credentials_dict)
+#     #gc = gspread.service_account(filename='arctic-rite-381810-e8bee8664772.json')
+#     gc = gspread.service_account_from_dict(credentials_dict)
 
-    # Ask user for Google Sheet URL
-    sheet_url = st.text_input('Enter the URL of your Google Sheet')
+#     # Ask user for Google Sheet URL
+#     sheet_url = st.text_input('Enter the URL of your Google Sheet')
 
-    # Add this in the part of your Streamlit app where the user can select the model
-    models = ["gpt-3.5-turbo", "gpt-4"]
-    selected_model = st.selectbox("Choose a model:", models)
+#     # Add this in the part of your Streamlit app where the user can select the model
+#     models = ["gpt-3.5-turbo", "gpt-4"]
+#     selected_model = st.selectbox("Choose a model:", models)
 
-    # Extract sheet ID from URL
-    sheet_id = sheet_url.split('/')[5]
-    # Open the Google spreadsheet
-    sheet = gc.open_by_key(sheet_id)
+#     # Extract sheet ID from URL
+#     sheet_id = sheet_url.split('/')[5]
+#     # Open the Google spreadsheet
+#     sheet = gc.open_by_key(sheet_id)
 
-    # Select sheet named 'Listing'
-    worksheet = sheet.worksheet('Listing')
-    # Get all records of the data
-    df = get_as_dataframe(worksheet)
+#     # Select sheet named 'Listing'
+#     worksheet = sheet.worksheet('Listing')
+#     # Get all records of the data
+#     df = get_as_dataframe(worksheet)
 
-    # Convert DataFrame to strings
-    df_str = df.astype(str)
+#     # Convert DataFrame to strings
+#     df_str = df.astype(str)
 
-    title = df[df.eq('Title').any(axis=1)].iloc[0, 2]
-    bullets = [df[df.eq(f"Bullet #{i}").any(axis=1)].iloc[0, 2] for i in range(1, 6)]
+#     title = df[df.eq('Title').any(axis=1)].iloc[0, 2]
+#     bullets = [df[df.eq(f"Bullet #{i}").any(axis=1)].iloc[0, 2] for i in range(1, 6)]
 
-    backend_search_terms = df[df.astype(str).apply(lambda x: 'Backend Search Terms' in ' '.join(x), axis=1)].iloc[0, 2] if len(df[df.astype(str).apply(lambda x: 'Backend Search Terms' in ' '.join(x), axis=1)]) > 0 else None
+#     backend_search_terms = df[df.astype(str).apply(lambda x: 'Backend Search Terms' in ' '.join(x), axis=1)].iloc[0, 2] if len(df[df.astype(str).apply(lambda x: 'Backend Search Terms' in ' '.join(x), axis=1)]) > 0 else None
 
-    image_text_row = df[df.eq('Image Text').any(axis=1)]
-    image_text = list(image_text_row.dropna(axis=1).iloc[0, :])
+#     image_text_row = df[df.eq('Image Text').any(axis=1)]
+#     image_text = list(image_text_row.dropna(axis=1).iloc[0, :])
 
-    a_plus_desc_mask = df.astype(str).apply(lambda x: 'A+ Description' in ' '.join(x), axis=1)
-    if a_plus_desc_mask.any():
-        a_plus_desc_row = df[a_plus_desc_mask].index[0]
-        a_plus_desc = df.iloc[a_plus_desc_row:, :].fillna('').values.flatten()
-        a_plus_desc = ' '.join(a_plus_desc).strip()
-    else:
-        a_plus_desc = None
+#     a_plus_desc_mask = df.astype(str).apply(lambda x: 'A+ Description' in ' '.join(x), axis=1)
+#     if a_plus_desc_mask.any():
+#         a_plus_desc_row = df[a_plus_desc_mask].index[0]
+#         a_plus_desc = df.iloc[a_plus_desc_row:, :].fillna('').values.flatten()
+#         a_plus_desc = ' '.join(a_plus_desc).strip()
+#     else:
+#         a_plus_desc = None
 
-    legacy_desc = df[df.astype(str).apply(lambda x: 'Legacy Product Description' in ' '.join(x), axis=1)].iloc[0, 2] if len(df[df.astype(str).apply(lambda x: 'Legacy Product Description' in ' '.join(x), axis=1)]) > 0 else None
+#     legacy_desc = df[df.astype(str).apply(lambda x: 'Legacy Product Description' in ' '.join(x), axis=1)].iloc[0, 2] if len(df[df.astype(str).apply(lambda x: 'Legacy Product Description' in ' '.join(x), axis=1)]) > 0 else None
 
-    image_text_string = ' '.join(image_text)
+#     image_text_string = ' '.join(image_text)
 
-    bullet_str = ""
-    for i, bullet in enumerate(bullets, 1):
-        bullet_str += f"Bullet #{i}: {bullet}\n"
+#     bullet_str = ""
+#     for i, bullet in enumerate(bullets, 1):
+#         bullet_str += f"Bullet #{i}: {bullet}\n"
 
-    # Display default prompt to user
-    default_prompt = """Below is data of our products for amazon listing:
-    ------------------------------------
-    Title: {}\n 
-    bullet_str: {}\n
-    Legacy Product Description: {}\n
-    A+ Description: {}\n
-    Image_text: {}\n
-    backend_search_terms: {}\n
-    -------------------------------------    
+#     # Display default prompt to user
+#     default_prompt = """Below is data of our products for amazon listing:
+#     ------------------------------------
+#     Title: {}\n 
+#     bullet_str: {}\n
+#     Legacy Product Description: {}\n
+#     A+ Description: {}\n
+#     Image_text: {}\n
+#     backend_search_terms: {}\n
+#     -------------------------------------    
 
-    Please create question-answers pairs for amazon listing using this data. 
-    Please segregate them theme wise. themes names should not be features or benefits and create 1 or more questions answer pairs for each theme.
-    questions generated should be potential questions in customer mind before buying product.
-    please create at least 20 question-answers pairs.
-            """.format(title, bullet_str, legacy_desc, a_plus_desc, image_text_string, backend_search_terms)
+#     Please create question-answers pairs for amazon listing using this data. 
+#     Please segregate them theme wise. themes names should not be features or benefits and create 1 or more questions answer pairs for each theme.
+#     questions generated should be potential questions in customer mind before buying product.
+#     please create at least 20 question-answers pairs.
+#             """.format(title, bullet_str, legacy_desc, a_plus_desc, image_text_string, backend_search_terms)
 
-    prompt = st.text_area("Edit the prompt:", value=default_prompt, height=200)
+#     prompt = st.text_area("Edit the prompt:", value=default_prompt, height=200)
 
 
 
-    # If the user has input a URL, fetch the data from Google Sheets
-    if st.button('generate'):
+#     # If the user has input a URL, fetch the data from Google Sheets
+#     if st.button('generate'):
 
-        messages = [
-                    {"role": "system", "content": "You are helpful assistant"},
-                    {"role": "user", "content": prompt}
-                ]
+#         messages = [
+#                     {"role": "system", "content": "You are helpful assistant"},
+#                     {"role": "user", "content": prompt}
+#                 ]
 
         
 
-        model_response = get_chatgpt_response(messages, selected_model)
+#         model_response = get_chatgpt_response(messages, selected_model)
 
-        question_answers= model_response
+#         question_answers= model_response
 
-        st.session_state.question_answers = question_answers
+#         st.session_state.question_answers = question_answers
 
-        st.write(question_answers)
+#         st.write(question_answers)
 
-    def parse_qa(text):
-        try:
-            # Split the text into themes
-            themes = re.split(r'\nTheme: ', text)[1:]
+#     def parse_qa(text):
+#         try:
+#             # Split the text into themes
+#             themes = re.split(r'\nTheme: ', text)[1:]
             
-            output = []
-            for theme in themes:
-                theme_lines = theme.split('\n')
-                theme_name = theme_lines[0]
-                qa_pairs = theme_lines[1:]
+#             output = []
+#             for theme in themes:
+#                 theme_lines = theme.split('\n')
+#                 theme_name = theme_lines[0]
+#                 qa_pairs = theme_lines[1:]
                 
-                # Extract question and answer pairs
-                for qa in qa_pairs:
-                    if qa.startswith('Q'):
-                        question = qa.split(': ', 1)[1]
-                    elif qa.startswith('A'):
-                        answer = qa.split(': ', 1)[1]
-                        output.append((theme_name, question, answer))
-            return output, True
-        except Exception as e:
-            return text, False  # Return the full text and a flag indicating the parsing failed
+#                 # Extract question and answer pairs
+#                 for qa in qa_pairs:
+#                     if qa.startswith('Q'):
+#                         question = qa.split(': ', 1)[1]
+#                     elif qa.startswith('A'):
+#                         answer = qa.split(': ', 1)[1]
+#                         output.append((theme_name, question, answer))
+#             return output, True
+#         except Exception as e:
+#             return text, False  # Return the full text and a flag indicating the parsing failed
 
         
 
-    # # Create a button that will trigger writing to Google Sheets
-    # if st.button('Write output to sheet'):
+#     # # Create a button that will trigger writing to Google Sheets
+#     # if st.button('Write output to sheet'):
 
-    #     final_output= st.session_state.question_answers
+#     #     final_output= st.session_state.question_answers
 
-    #     st.write("Button clicked, processing data...")
+#     #     st.write("Button clicked, processing data...")
 
-    #     sheet_id = sheet_url.split('/')[5]  # Open the Google spreadsheet
-    #     sheet = gc.open_by_key(sheet_id)
+#     #     sheet_id = sheet_url.split('/')[5]  # Open the Google spreadsheet
+#     #     sheet = gc.open_by_key(sheet_id)
 
 
 
        
 
-    #     try:
-    #         # Check if the "tone_of_voice_manual" worksheet already exists
-    #         worksheet_output = None
-    #         for wks in sheet.worksheets():
-    #             if wks.title == 'question_answers':
-    #                 worksheet_output = wks
-    #                 break
+#     #     try:
+#     #         # Check if the "tone_of_voice_manual" worksheet already exists
+#     #         worksheet_output = None
+#     #         for wks in sheet.worksheets():
+#     #             if wks.title == 'question_answers':
+#     #                 worksheet_output = wks
+#     #                 break
 
-    #         # If the worksheet does not exist, create a new one
-    #         if worksheet_output is None:
-    #             worksheet_output = sheet.add_worksheet(title="question_answers", rows="100", cols="20")
+#     #         # If the worksheet does not exist, create a new one
+#     #         if worksheet_output is None:
+#     #             worksheet_output = sheet.add_worksheet(title="question_answers", rows="100", cols="20")
 
-    #         # Read the existing data from the worksheet
-    #         existing_data = get_as_dataframe(worksheet_output)
+#     #         # Read the existing data from the worksheet
+#     #         existing_data = get_as_dataframe(worksheet_output)
 
-    #         # Remove empty columns from the existing data
-    #         existing_data = existing_data.dropna(how='all', axis=1)
+#     #         # Remove empty columns from the existing data
+#     #         existing_data = existing_data.dropna(how='all', axis=1)
 
-    #         # Prepare a list to store the tone of voice manual data
-    #         question_answers_data = [final_output]
+#     #         # Prepare a list to store the tone of voice manual data
+#     #         question_answers_data = [final_output]
 
-    #         # Convert the list of tone of voice manual data into a DataFrame
-    #         new_data = pd.DataFrame(question_answers_data, columns=['question_answers'])
+#     #         # Convert the list of tone of voice manual data into a DataFrame
+#     #         new_data = pd.DataFrame(question_answers_data, columns=['question_answers'])
 
-    #         # Append the new data to the existing data
-    #         updated_data = pd.concat([existing_data, new_data], axis=1)
+#     #         # Append the new data to the existing data
+#     #         updated_data = pd.concat([existing_data, new_data], axis=1)
 
-    #         # Clear the worksheet before writing the updated data
-    #         worksheet_output.clear()
+#     #         # Clear the worksheet before writing the updated data
+#     #         worksheet_output.clear()
 
-    #         # Write the updated data to the "tone_of_voice_manual" worksheet
-    #         set_with_dataframe(worksheet_output, updated_data)
-    #         st.write("Data written successfully to Google Sheets.")
-    #     except Exception as e:
-    #         st.error(f"An error occurred while writing to Google Sheets: {e}")
+#     #         # Write the updated data to the "tone_of_voice_manual" worksheet
+#     #         set_with_dataframe(worksheet_output, updated_data)
+#     #         st.write("Data written successfully to Google Sheets.")
+#     #     except Exception as e:
+#     #         st.error(f"An error occurred while writing to Google Sheets: {e}")
 
-    if st.button('Write output to sheet'):
-        final_output, parsed_successfully = parse_qa(st.session_state.question_answers)
+#     if st.button('Write output to sheet'):
+#         final_output, parsed_successfully = parse_qa(st.session_state.question_answers)
 
-        st.write("Button clicked, processing data...")
+#         st.write("Button clicked, processing data...")
 
-        sheet_id = sheet_url.split('/')[5]  # Open the Google spreadsheet
-        sheet = gc.open_by_key(sheet_id)
+#         sheet_id = sheet_url.split('/')[5]  # Open the Google spreadsheet
+#         sheet = gc.open_by_key(sheet_id)
 
-        try:
-            worksheet_output = None
-            for wks in sheet.worksheets():
-                if wks.title == 'question_answers':
-                    worksheet_output = wks
-                    break
+#         try:
+#             worksheet_output = None
+#             for wks in sheet.worksheets():
+#                 if wks.title == 'question_answers':
+#                     worksheet_output = wks
+#                     break
 
-            if worksheet_output is None:
-                worksheet_output = sheet.add_worksheet(title="question_answers", rows="100", cols="20")
+#             if worksheet_output is None:
+#                 worksheet_output = sheet.add_worksheet(title="question_answers", rows="100", cols="20")
 
-            if parsed_successfully:
-                new_data = pd.DataFrame(final_output, columns=['Theme', 'Question', 'Answer'])
-            else:
-                new_data = pd.DataFrame([final_output], columns=['Output'])
+#             if parsed_successfully:
+#                 new_data = pd.DataFrame(final_output, columns=['Theme', 'Question', 'Answer'])
+#             else:
+#                 new_data = pd.DataFrame([final_output], columns=['Output'])
 
-            worksheet_output.clear()
-            set_with_dataframe(worksheet_output, new_data)
-            st.write("Data written successfully to Google Sheets.")
-        except Exception as e:
-            st.error(f"An error occurred while writing to Google Sheets: {e}")
+#             worksheet_output.clear()
+#             set_with_dataframe(worksheet_output, new_data)
+#             st.write("Data written successfully to Google Sheets.")
+#         except Exception as e:
+#             st.error(f"An error occurred while writing to Google Sheets: {e}")
+
+if page == 'question_answers':
+    st.title('question answers')
+
+    #gc = gspread.service_account(filename='arctic-rite-381810-e8bee8664772.json')
+    gc = gspread.service_account(filename='arctic-rite-381810-b124ba8c96a9.json')
+
+    sheet_url = st.text_input('Enter the URL of your Google Sheet')
+
+    models = ["gpt-3.5-turbo", "gpt-4", "gpt-3.5-turbo-16k"]
+    selected_model = st.selectbox("Choose a model:", models)
+
+        # Extract sheet ID from URL
+    sheet_id = sheet_url.split('/')[5]
+    # Open the Google spreadsheet
+    sheet = gc.open_by_key(sheet_id)
+
+    # Select sheet named 'Listing'
+    worksheet = sheet.worksheet('Q&A')
+    # Get all records of the data
+    df = get_as_dataframe(worksheet)
+
+    df= df.dropna(subset = ['Question', 'Answer'])
+
+    st.write(df)
+
+    question_answer = "\n".join(["Question: {}\nAnswer: {}".format(q, a) for q, a in zip(df['Question'], df['Answer'])])
+
+    #st.write(question_answer)
+
+    st.write(len(question_answer))
+
+    # Display default prompt to user
+    default_prompt = """Below is question-answer pairs from amazon listing:
+    ------------------------------------
+    {}
+    -------------------------------------    
+    please analyze these question-answer pairs and group them theme-wise. you have find themes and then group question-answer pairs as per theme. Don't miss any question pair given above. give numbering to questions.
+            """.format(question_answer)
+
+    prompt = st.text_area("Edit the prompt:", value=default_prompt, height=200)
+
+    # If the user has input a URL, fetch the data from Google Sheets
+    if st.button('generate'):
+
+        messages = [
+                    {"role": "system", "content": "You are helpful assistant"},
+                    {"role": "user", "content": prompt}
+                ]
+
+        model_response = get_chatgpt_response(messages, selected_model)
+
+        question_answers= model_response
+
+        st.session_state.question_answers = question_answers
+
+        st.write(question_answers)
+
+
+    if st.button('Write output to sheet'):
+            question_answers = st.session_state.question_answers
+            # Create a new Google Sheets file
+            new_worksheet = sheet.add_worksheet(title="QnA_analyzed", rows="100", cols="20")
+
+            # Add rows one by one
+            new_worksheet.append_row(['question_answers', question_answers])
 
 
 if page == 'feature_mapping':
@@ -1191,7 +1257,7 @@ if page == 'feature_mapping':
     sheet_url = st.text_input('Enter the URL of your Google Sheet')
 
     # Add this in the part of your Streamlit app where the user can select the model
-    models = ["gpt-3.5-turbo", "gpt-4"]
+    models = ["gpt-3.5-turbo", "gpt-4", "gpt-3.5-turbo-16k"]
     selected_model = st.selectbox("Choose a model:", models)
 
     # Extract sheet ID from URL
@@ -1315,7 +1381,7 @@ if page == 'benefit_mapping':
     sheet_url = st.text_input('Enter the URL of your Google Sheet')
 
     # Add this in the part of your Streamlit app where the user can select the model
-    models = ["gpt-3.5-turbo", "gpt-4"]
+    models = ["gpt-3.5-turbo", "gpt-4", "gpt-3.5-turbo-16k"]
     selected_model = st.selectbox("Choose a model:", models)
 
     # Extract sheet ID from URL
@@ -1447,7 +1513,7 @@ def page_combined_features_and_benefits():
         for url in sheet_urls:
             st.write(url)
 
-    models = ["gpt-3.5-turbo", "gpt-4"]
+    models = ["gpt-3.5-turbo", "gpt-4", "gpt-3.5-turbo-16k"]
     selected_model = st.selectbox("Choose a model:", models)
 
     user_char_limit = st.number_input("Enter character limit for chunk:", value=9000, step=500)