Update app.py

app.py

@@ -15,7 +15,7 @@ import sys
 import time
 import re
 import textract
-import zipfile  # New import for zipping files
+import zipfile  
 import random
 
 from datetime import datetime
@@ -33,6 +33,8 @@ from langchain.chat_models import ChatOpenAI
 from langchain.memory import ConversationBufferMemory
 from langchain.chains import ConversationalRetrievalChain
 from templates import css, bot_template, user_template
+from io import BytesIO
+
 
 # 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")
@@ -163,7 +165,6 @@ def add_paper_buttons_and_links():
 add_paper_buttons_and_links()
 
 
-
 # Process user input is a post processor algorithm which runs after document embedding vector DB play of GPT on context of documents..
 def process_user_input(user_question):
     # Check and initialize 'conversation' in session state if not present
@@ -205,32 +206,6 @@ def extract_feature_and_detail(paragraph):
         return header, detail
     return None, None
 
-
-def process_user_input_old(user_question):
-    response = st.session_state.conversation({'question': user_question})
-    st.session_state.chat_history = response['chat_history']
-    for i, message in enumerate(st.session_state.chat_history):
-        template = user_template if i % 2 == 0 else bot_template
-        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)
-        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 generate_filename_old(prompt, file_type):
-    central = pytz.timezone('US/Central')
-    safe_date_time = datetime.now(central).strftime("%m%d_%H%M")  # Date and time DD-HHMM
-    safe_prompt = "".join(x for x in prompt if x.isalnum())[:90]  # Limit file name size and trim whitespace
-    return f"{safe_date_time}_{safe_prompt}.{file_type}"  # Return a safe file name
-
 def generate_filename(prompt, file_type):
     central = pytz.timezone('US/Central')
     safe_date_time = datetime.now(central).strftime("%m%d_%H%M")
@@ -333,71 +308,6 @@ def create_file(filename, prompt, response, should_save=True):
             file.write(combined_content)
 
 
-def create_file_old2(filename, prompt, response, should_save=True):
-    if not should_save:
-        return
-
-    # Step 2: Extract base filename without extension
-    base_filename, ext = os.path.splitext(filename)
-
-    # Step 3: Check if the response contains Python code
-    has_python_code = bool(re.search(r"```python([\s\S]*?)```", response))
-
-    # Step 4: Initialize the combined content
-    combined_content = ""
-
-    # Add Prompt with markdown title and emoji
-    combined_content += "# Prompt 📝\n" + prompt + "\n\n"
-
-    # Add Response with markdown title and emoji
-    combined_content += "# Response 💬\n" + response + "\n\n"
-
-    # Check for Python code or other resources and add them with markdown title and emoji
-    resources = re.findall(r"```([\s\S]*?)```", response)
-    for resource in resources:
-        # Check if the resource contains Python code
-        if "python" in resource.lower():
-            st.markdown('# Running python.. ')
-            # Remove the word 'python' from the beginning of the code block
-            cleaned_code = re.sub(r'^\s*python', '', resource, flags=re.IGNORECASE | re.MULTILINE)
-            
-            # Add Code Results title with markdown and emoji
-            combined_content += "# Code Results 🚀\n"
-
-            # Capture standard output
-            original_stdout = sys.stdout
-            sys.stdout = io.StringIO()
-            
-            # Execute cleaned Python code and capture the output
-            try:
-                st.markdown('# Running exec.. ')
-
-                exec(cleaned_code)
-                code_output = sys.stdout.getvalue()
-                combined_content += f"```\n{code_output}\n```\n\n"
-                realtimeEvalResponse = "# Code Results 🚀\n" + "```" + code_output + "```\n\n"
-                
-                st.write(realtimeEvalResponse)
-
-                st.markdown('# Completed exec.. ')
-
-            
-            except Exception as e:
-                combined_content += f"```python\nError executing Python code: {e}\n```\n\n"
-                st.markdown('# Error in exec.. ' + combined_content)
-            
-            # Restore the original standard output
-            sys.stdout = original_stdout
-        else:
-            # Add Resource title with markdown and emoji for non-Python resources
-            combined_content += "# Resource 🛠️\n" + "```" + resource + "```\n\n"
-
-    # Write the combined content into one file
-    with open(f"{base_filename}-Combined.md", 'w') as file:
-        file.write(combined_content)        
-
-
-
 def truncate_document(document, length):
     return document[:length]
 
@@ -474,8 +384,7 @@ def extract_mime_type(file):
     else:
         raise TypeError("Input should be a string or a streamlit.UploadedFile object")
 
-from io import BytesIO
-import re
+
 
 def extract_file_extension(file):
     # get the file name directly from the UploadedFile object
@@ -505,20 +414,6 @@ def pdf2txt(docs):
                     text += pdf.pages[page].extract_text() # new PyPDF2 syntax
         except Exception as e:
             st.write(f"Error processing file {file.name}: {e}")
-
-    return text
-
-def pdf2txt_old(pdf_docs):
-    st.write(pdf_docs)
-    for file in pdf_docs:
-        mime_type = extract_mime_type(file)
-        st.write(f"MIME type of file: {mime_type}")
-    
-    text = ""
-    for pdf in pdf_docs:
-        pdf_reader = PdfReader(pdf)
-        for page in pdf_reader.pages:
-            text += page.extract_text()
     return text
 
 def txt2chunks(text):
@@ -636,8 +531,6 @@ def main():
     if st.button('💬 Chat'):
         st.write('Reasoning with your inputs...')
         
-        #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 = ''
@@ -714,7 +607,6 @@ def main():
             create_file(filename, user_prompt, response, should_save)
 
             st.experimental_rerun()
-            #st.sidebar.markdown(get_table_download_link(filename), unsafe_allow_html=True)
                 
 if __name__ == "__main__":
     main()
@@ -740,4 +632,3 @@ with st.sidebar:
             st.markdown('# AI Search Index of Length:' + length + ' Created.')  # add timing
             filename = generate_filename(raw, 'txt')
             create_file(filename, raw, '', should_save)
-            #create_file(filename, raw, '')