Update app.py

app.py

@@ -2,7 +2,6 @@ import streamlit as st
 import streamlit.components.v1 as components
 import huggingface_hub
 import gradio_client as gc
-
 import os
 import json
 import random
@@ -17,7 +16,6 @@ import textract
 import time
 import zipfile
 import dotenv
-
 from gradio_client import Client
 from audio_recorder_streamlit import audio_recorder
 from bs4 import BeautifulSoup
@@ -33,26 +31,11 @@ from xml.etree import ElementTree as ET
 from PIL import Image
 from urllib.parse import quote  # Ensure this import is included
 
-
-## Show examples
-sample_outputs = {
-    'output_placeholder': 'The LLM will provide an answer to your question here...',
-    'search_placeholder': '1. What is MoE, Multi Agent Systems, Self Rewarding AI, Semantic and Episodic memory, What is AutoGen, ChatDev, Omniverse, Lumiere, SORA?'
-}
-
-def save_file(content, file_type):
-    timestamp = datetime.now().strftime("%Y%m%d_%H%M%S")
-    file_name = f"{file_type}_{timestamp}.md"
-    with open(file_name, "w") as file:
-        file.write(content)
-    return file_name
-
 def load_file(file_name):
     with open(file_name, "r") as file:
         content = file.read()
     return content
 
-
 # HTML5 based Speech Synthesis (Text to Speech in Browser)
 @st.cache_resource
 def SpeechSynthesis(result):
@@ -84,33 +67,22 @@ def SpeechSynthesis(result):
     components.html(documentHTML5, width=1280, height=300)
 
 def parse_to_markdown(text):
-    # Split text into fields by | character
     fields = text.split("|")
-    
     markdown = ""
     for field in fields:
-        # Remove leading/trailing quotes and whitespace
         field = field.strip(" '")
-        
-        # Add field to markdown with whitespace separator
         markdown += field + "\n\n"
-
     return markdown
     
 def search_arxiv(query):
-    
     # Show ArXiv Scholary Articles! ----------------*************-------------***************----------------------------------------
-    # st.title("▶️ Semantic and Episodic Memory System")
     client = Client("awacke1/Arxiv-Paper-Search-And-QA-RAG-Pattern")
-    
     search_query = query
     #top_n_results = st.slider(key='topnresults', label="Top n results as context", min_value=4, max_value=100, value=100)
     #search_source = st.sidebar.selectbox(key='searchsource', label="Search Source", ["Semantic Search - up to 10 Mar 2024", "Arxiv Search - Latest - (EXPERIMENTAL)"])
     search_source = "Arxiv Search - Latest - (EXPERIMENTAL)" # "Semantic Search - up to 10 Mar 2024"
     #llm_model = st.sidebar.selectbox(key='llmmodel', label="LLM Model", ["mistralai/Mixtral-8x7B-Instruct-v0.1", "mistralai/Mistral-7B-Instruct-v0.2", "google/gemma-7b-it", "None"])
     llm_model = "mistralai/Mixtral-8x7B-Instruct-v0.1"
-
-    
     st.sidebar.markdown('### 🔎 ' + query)
     result = client.predict(
         search_query,
@@ -127,16 +99,8 @@ def search_arxiv(query):
     SpeechSynthesis(result)  # Search History Reader / Writer IO Memory - Audio at Same time as Reading.
     filename=generate_filename(result, "md")
     create_file(filename, query, result, should_save)
-
-    
-    #file_type = st.radio("Select Which Type of Memory You Prefer:", ("Semantic", "Episodic"))
-    #if st.button("Save"):
-    #    file_name = save_file(result, file_type)
-    #    st.success(f"File saved: {file_name}")
-
     saved_files = [f for f in os.listdir(".") if f.endswith(".md")]
     selected_file = st.sidebar.selectbox("Saved Files", saved_files)
-
     if selected_file:
         file_content = load_file(selected_file)
         st.sidebar.markdown(file_content)
@@ -177,7 +141,6 @@ def display_glossary_grid(roleplaying_glossary):
         "📚": lambda k: f"https://huggingface.co/spaces/awacke1/World-Ship-Design?q={quote(k)}-{quote(PromptPrefix2)}",  # this url plus query!
         "🔬": lambda k: f"https://huggingface.co/spaces/awacke1/World-Ship-Design?q={quote(k)}-{quote(PromptPrefix3)}",  # this url plus query!
     }
-
     for category, details in roleplaying_glossary.items():
         st.write(f"### {category}")
         cols = st.columns(len(details))  # Create dynamic columns based on the number of games
@@ -187,7 +150,6 @@ def display_glossary_grid(roleplaying_glossary):
                 for term in terms:
                     gameterm = category + ' - ' + game + ' - ' + term
                     links_md = ' '.join([f"[{emoji}]({url(gameterm)})" for emoji, url in search_urls.items()])
-                    #links_md = ' '.join([f"[{emoji}]({url(term)})" for emoji, url in search_urls.items()])
                     st.markdown(f"{term} {links_md}", unsafe_allow_html=True)
                     
 def display_glossary_entity(k):
@@ -206,10 +168,6 @@ def display_glossary_entity(k):
     links_md = ' '.join([f"[{emoji}]({url(k)})" for emoji, url in search_urls.items()])
     st.markdown(f"{k} {links_md}", unsafe_allow_html=True)
 
-
-
-#st.markdown('''### 📖✨🔍 Arxiv-Paper-Search-QA-RAG-Streamlit-Gradio-AP ''')
-
 roleplaying_glossary = {
 "🤖 AI Concepts": {
 "MoE (Mixture of Experts) 🧠": [
@@ -383,7 +341,6 @@ def get_table_download_link(file_path):
     href = f'<a href="data:{mime_type};base64,{b64}" target="_blank" download="{file_name}">{file_name}</a>'
     return href
 
-
 @st.cache_resource
 def create_zip_of_files(files): # ----------------------------------
     zip_name = "Arxiv-Paper-Search-QA-RAG-Streamlit-Gradio-AP.zip"
@@ -402,7 +359,6 @@ def get_zip_download_link(zip_file):
 
 def FileSidebar():
     # ----------------------------------------------------- File Sidebar for Jump Gates ------------------------------------------
-    # Compose a file sidebar of markdown md files:
     all_files = glob.glob("*.md")
     all_files = [file for file in all_files if len(os.path.splitext(file)[0]) >= 10]  # 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
@@ -438,19 +394,16 @@ def FileSidebar():
             if st.button("🗑", key="delete_"+file):
                 os.remove(file)
                 st.experimental_rerun()
-
                 
     if len(file_contents) > 0:
         if next_action=='open':
             file_content_area = st.text_area("File Contents:", file_contents, height=500)
-        #try:
             if st.button("🔍", key="filecontentssearch"):
                 #search_glossary(file_content_area)
                 filesearch = PromptPrefix + file_content_area
                 st.markdown(filesearch)
                 if st.button(key=rerun, label='🔍Re-Spec' ):
                     search_glossary(filesearch)
-        #except:
             st.markdown('GPT is sleeping.  Restart ETA 30 seconds.')
 
         if next_action=='md':
@@ -458,28 +411,21 @@ def FileSidebar():
             buttonlabel = '🔍Run'
             if st.button(key='Runmd', label = buttonlabel):
                 user_prompt = file_contents
-            #try:
                 search_glossary(file_contents)
-            #except:
                 st.markdown('GPT is sleeping.  Restart ETA 30 seconds.')
 
         if next_action=='search':
             file_content_area = st.text_area("File Contents:", file_contents, height=500)
             user_prompt = file_contents
-        #try:
-            #search_glossary(file_contents)
             filesearch = PromptPrefix2 + file_content_area
             st.markdown(filesearch)
             if st.button(key=rerun, label='🔍Re-Code' ):
                 search_glossary(filesearch)
-                    
-        #except:
+
             st.markdown('GPT is sleeping.  Restart ETA 30 seconds.')
     # ----------------------------------------------------- File Sidebar for Jump Gates ------------------------------------------
 FileSidebar()
 
-
-    
 # ---- Art Card Sidebar with Random Selection of image:
 def get_image_as_base64(url):
     response = requests.get(url)
@@ -794,8 +740,6 @@ def clear_query_params():
 
 # My Inference API Copy
 API_URL = 'https://qe55p8afio98s0u3.us-east-1.aws.endpoints.huggingface.cloud'  # Dr Llama
-# Meta's Original - Chat HF Free Version:
-#API_URL = "https://api-inference.huggingface.co/models/meta-llama/Llama-2-7b-chat-hf"
 API_KEY = os.getenv('API_KEY')
 MODEL1="meta-llama/Llama-2-7b-chat-hf"
 MODEL1URL="https://huggingface.co/meta-llama/Llama-2-7b-chat-hf"
@@ -809,8 +753,6 @@ prompt = "...."
 should_save = st.sidebar.checkbox("💾 Save", value=True, help="Save your session data.")
 
 
-
-
 # 3. Stream Llama Response
 # @st.cache_resource
 def StreamLLMChatResponse(prompt):
@@ -1253,28 +1195,11 @@ if 'action' in st.query_params:
         clear_query_params()
         st.experimental_rerun()
 
-# Handling repeated keys
-#if 'multi' in st.query_params:
-#    multi_values = get_all_query_params('multi')
-#    st.write("Values for 'multi':", multi_values)
-
-# Manual entry for demonstration
-#st.write("Enter query parameters in the URL like this: ?action=show_message&multi=1&multi=2")
-
 if 'query' in st.query_params:
     query = st.query_params['query'][0]  # Get the query parameter
-    # Display content or image based on the query
     display_content_or_image(query)
 
-# Add a clear query parameters button for convenience
-#if st.button("Clear Query Parameters", key='ClearQueryParams'):
-    # This will clear the browser URL's query parameters
-#    st.experimental_set_query_params
-#    st.experimental_rerun()
-
-
 st.markdown("### 🎲🗺️ Arxiv Paper Search QA RAG MAS using Streamlit and Gradio API")
-
 filename = save_and_play_audio(audio_recorder)
 if filename is not None:
     transcription = transcribe_audio(filename)
@@ -1308,8 +1233,6 @@ if filename is not None:
         os.remove(filename)
 
 
-
-
 prompt = '''
 What is MoE?
 What are Multi Agent Systems?
@@ -1355,10 +1278,6 @@ if openai.api_key == None: openai.api_key = st.secrets['OPENAI_API_KEY']
 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'))        
-#user_prompt = st.text_area("Enter prompts, instructions & questions:", '', height=100)
-
-
 collength, colupload = st.columns([2,3])  # adjust the ratio as needed
 with collength:
     max_length = st.slider(key='maxlength', label="File section length for large files", min_value=1000, max_value=128000, value=12000, step=1000)
@@ -1391,20 +1310,6 @@ if len(document_sections) > 0:
                 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...')
-#    user_prompt_sections = divide_prompt(user_prompt, max_length)
-#    full_response = ''
-#    for prompt_section in user_prompt_sections:
-#        response = chat_with_model(prompt_section, ''.join(list(document_sections)), model_choice)
-#        full_response += response + '\n'  # Combine the responses
-#    response = full_response
-#    st.write('Response:')
-#    st.write(response)
-#    filename = generate_filename(user_prompt, choice)
-#    create_file(filename, user_prompt, response, should_save)
-
 display_glossary_grid(roleplaying_glossary)  # Word Glossary Jump Grid
 display_videos_and_links()   # Video Jump Grid
 display_images_and_wikipedia_summaries()   # Image Jump Grid
-#display_buttons_with_scores()  # Feedback Jump Grid