Update app.py

app.py

@@ -11,7 +11,7 @@ import requests
 import time
 import re
 import textract
-import zipfile
+import zipfile  # New import for zipping files
 
 
 from datetime import datetime
@@ -20,7 +20,6 @@ from xml.etree import ElementTree as ET
 from bs4 import BeautifulSoup
 from collections import deque
 from audio_recorder_streamlit import audio_recorder
-
 from dotenv import load_dotenv
 from PyPDF2 import PdfReader
 from langchain.text_splitter import CharacterTextSplitter
@@ -31,7 +30,9 @@ from langchain.memory import ConversationBufferMemory
 from langchain.chains import ConversationalRetrievalChain
 from templates import css, bot_template, user_template
 
-
+# page config and sidebar declares up front allow all other functions to see global class variables
+st.set_page_config(page_title="GPT Streamlit Document Reasoner", layout="wide")
+should_save = st.sidebar.checkbox("💾 Save")
 
 def generate_filename(prompt, file_type):
     central = pytz.timezone('US/Central')
@@ -55,7 +56,10 @@ def transcribe_audio(openai_key, file_path, model):
         #st.write('Responses:')
         #st.write(chatResponse)
         filename = generate_filename(transcript, 'txt')
-        create_file(filename, transcript, chatResponse)
+        #create_file(filename, transcript, chatResponse)
+        response = chatResponse
+        user_prompt = transcript
+        create_file(filename, user_prompt, response, should_save)
         return transcript
     else:
         st.write(response.json())
@@ -72,7 +76,9 @@ def save_and_play_audio(audio_recorder):
         return filename
     return None
 
-def create_file(filename, prompt, response):
+def create_file(filename, prompt, response, should_save=True):
+    if not should_save:
+        return
     if filename.endswith(".txt"):
         with open(filename, 'w') as file:
             file.write(f"{prompt}\n{response}")
@@ -275,55 +281,64 @@ def process_user_input(user_question):
         st.write(template.replace("{{MSG}}", message.content), unsafe_allow_html=True)
         # Save file output from PDF query results
         filename = generate_filename(user_question, 'txt')
-        create_file(filename, user_question, message.content)
-        
+        #create_file(filename, user_question, message.content)
+        response = message.content
+        user_prompt = user_question
+        create_file(filename, user_prompt, response, should_save)       
         #st.sidebar.markdown(get_table_download_link(filename), unsafe_allow_html=True)
 
-def create_zip_of_all_files():
-    # Get all files in the current directory
-    all_files = glob.glob("*.*")
-    
-    # Name the zip file based on the current date and time
-    central = pytz.timezone('US/Central')
-    safe_date_time = datetime.now(central).strftime("%Y%m%d_%H%M%S")
-    zip_filename = f"all_files_{safe_date_time}.zip"
-    
-    with zipfile.ZipFile(zip_filename, 'w') as zipf:
-        for file in all_files:
+def divide_prompt(prompt, max_length):
+    words = prompt.split()
+    chunks = []
+    current_chunk = []
+    current_length = 0
+    for word in words:
+        if len(word) + current_length <= max_length:
+            current_length += len(word) + 1  # Adding 1 to account for spaces
+            current_chunk.append(word)
+        else:
+            chunks.append(' '.join(current_chunk))
+            current_chunk = [word]
+            current_length = len(word)
+    chunks.append(' '.join(current_chunk))  # Append the final chunk
+    return chunks
+
+def create_zip_of_files(files):
+    """
+    Create a zip file from a list of files.
+    """
+    zip_name = "all_files.zip"
+    with zipfile.ZipFile(zip_name, 'w') as zipf:
+        for file in files:
             zipf.write(file)
-    
-    return zip_filename
+    return zip_name
+
 
-def get_zip_download_link(zip_filepath):
-    with open(zip_filepath, 'rb') as f:
+def get_zip_download_link(zip_file):
+    """
+    Generate a link to download the zip file.
+    """
+    with open(zip_file, 'rb') as f:
         data = f.read()
-    
     b64 = base64.b64encode(data).decode()
-    file_name = os.path.basename(zip_filepath)
-    href = f'<a href="data:application/zip;base64,{b64}" target="_blank" download="{file_name}">Download All Files</a>'
+    href = f'<a href="data:application/zip;base64,{b64}" download="{zip_file}">Download All</a>'
     return href
 
     
 def main():
-    # Sidebar and global
     openai.api_key = os.getenv('OPENAI_API_KEY')
-    st.set_page_config(page_title="GPT Streamlit Document Reasoner",layout="wide")
 
     # File type for output, model choice
-    menu = ["htm", "txt", "xlsx", "csv", "md", "py"]  #619
+    menu = ["txt", "htm", "xlsx", "csv", "md", "py"]
     choice = st.sidebar.selectbox("Output File Type:", menu)
     model_choice = st.sidebar.radio("Select Model:", ('gpt-3.5-turbo', 'gpt-3.5-turbo-0301'))
-    
+
     # Audio, transcribe, GPT:
     filename = save_and_play_audio(audio_recorder)
     if filename is not None:
         transcription = transcribe_audio(openai.api_key, filename, "whisper-1")
         st.sidebar.markdown(get_table_download_link(filename), unsafe_allow_html=True)
-        filename=None # since transcription is finished next time just use the saved transcript
-
-    if st.sidebar.button("📦 Download All"):
-        zip_file_path = create_zip_of_all_files()
-        st.sidebar.markdown(get_zip_download_link(zip_file_path), unsafe_allow_html=True)
+        filename = None
 
     # prompt interfaces
     user_prompt = st.text_area("Enter prompts, instructions & questions:", '', height=100)
@@ -333,9 +348,11 @@ def main():
     with collength:
         max_length = st.slider("File section length for large files", min_value=1000, max_value=128000, value=12000, step=1000)
     with colupload:
-        uploaded_file = st.file_uploader("Add a file for context:", type=["pdf", "xml", "json", "xlsx","csv","html", "htm", "md", "txt"])
+        uploaded_file = st.file_uploader("Add a file for context:", type=["pdf", "xml", "json", "xlsx", "csv", "html", "htm", "md", "txt"])
+
 
     # Document section chat
+        
     document_sections = deque()
     document_responses = {}
     if uploaded_file is not None:
@@ -358,24 +375,49 @@ def main():
                     st.write(response)
                     document_responses[i] = response
                     filename = generate_filename(f"{user_prompt}_section_{i+1}", choice)
-                    create_file(filename, user_prompt, response)
+                    create_file(filename, user_prompt, response, should_save)
                     st.sidebar.markdown(get_table_download_link(filename), unsafe_allow_html=True)
 
     if st.button('💬 Chat'):
         st.write('Reasoning with your inputs...')
-        response = chat_with_model(user_prompt, ''.join(list(document_sections,)), model_choice) # *************************************
+        
+        #response = chat_with_model(user_prompt, ''.join(list(document_sections,)), model_choice) # *************************************
+
+        # Divide the user_prompt into smaller sections
+        user_prompt_sections = divide_prompt(user_prompt, max_length)
+        full_response = ''
+        for prompt_section in user_prompt_sections:
+            # Process each section with the model
+            response = chat_with_model(prompt_section, ''.join(list(document_sections)), model_choice)
+            full_response += response + '\n'  # Combine the responses
+        
+        #st.write('Response:')
+        #st.write(full_response)
+
+        response = full_response
         st.write('Response:')
         st.write(response)
         
         filename = generate_filename(user_prompt, choice)
-        create_file(filename, user_prompt, response)
+        create_file(filename, user_prompt, response, should_save)
         st.sidebar.markdown(get_table_download_link(filename), unsafe_allow_html=True)
 
     all_files = glob.glob("*.*")
     all_files = [file for file in all_files if len(os.path.splitext(file)[0]) >= 20]  # exclude files with short names
     all_files.sort(key=lambda x: (os.path.splitext(x)[1], x), reverse=True)  # sort by file type and file name in descending order
 
-    # sidebar of files
+    # Added "Delete All" button
+    if st.sidebar.button("🗑 Delete All"):
+        for file in all_files:
+            os.remove(file)
+        st.experimental_rerun()
+
+    # Added "Download All" button
+    if st.sidebar.button("⬇️ Download All"):
+        zip_file = create_zip_of_files(all_files)
+        st.sidebar.markdown(get_zip_download_link(zip_file), unsafe_allow_html=True)
+        
+    # Sidebar of Files Saving History and surfacing files as context of prompts and responses
     file_contents=''
     next_action=''
     for file in all_files:
@@ -412,7 +454,7 @@ def main():
             st.write('Reasoning with your inputs...')
             response = chat_with_model(user_prompt, file_contents, model_choice)
             filename = generate_filename(file_contents, choice)
-            create_file(filename, file_contents, response)
+            create_file(filename, user_prompt, response, should_save)
 
             st.experimental_rerun()
             #st.sidebar.markdown(get_table_download_link(filename), unsafe_allow_html=True)
@@ -440,4 +482,5 @@ with st.sidebar:
             st.session_state.conversation = get_chain(vectorstore)
             st.markdown('# AI Search Index of Length:' + length + ' Created.')  # add timing
             filename = generate_filename(raw, 'txt')
-            create_file(filename, raw, '')
+            create_file(filename, raw, '', should_save)
+            #create_file(filename, raw, '')