Update app.py

app.py

@@ -1,7 +1,48 @@
 import streamlit as st
+import os
+import json
+from PIL import Image
+from urllib.parse import quote  # Ensure this import is included
+import base64
+import glob
+import json
+import math
+import openai
+import os
+import pytz
+import re
+import requests
+import textract
+import time
+import zipfile
+import huggingface_hub
+import dotenv
+from audio_recorder_streamlit import audio_recorder
+from bs4 import BeautifulSoup
+from collections import deque
+from datetime import datetime
+from dotenv import load_dotenv
+from huggingface_hub import InferenceClient
+from io import BytesIO
+from openai import ChatCompletion
+from PyPDF2 import PdfReader
+from templates import bot_template, css, user_template
+from xml.etree import ElementTree as ET
+import streamlit.components.v1 as components  # Import Streamlit Components for HTML5
 
-st.set_page_config(layout="wide")
 
+# Set page configuration with a title and favicon
+st.set_page_config(
+    page_title="🌌🚀 Mixable AI - Voice Search",
+    page_icon="🌠",
+    layout="wide",
+    initial_sidebar_state="expanded",
+    menu_items={
+        'Get Help': 'https://huggingface.co/awacke1',
+        'Report a bug': "https://huggingface.co/spaces/awacke1/WebDataDownload",
+        'About': "# Midjourney: https://discord.com/channels/@me/997514686608191558"
+    }
+)
 st.markdown("""
 ## Anatomy Head to Toe Table with Body Organs Costly Conditions, Spending, CPT Codes and Frequency
 
@@ -31,23 +72,7 @@ st.markdown("""
 """)
 
 
-import os
-import json
-from PIL import Image
-from urllib.parse import quote  # Ensure this import is included
 
-# Set page configuration with a title and favicon
-st.set_page_config(
-    page_title="🌌🚀 Mixable AI - Voice Search",
-    page_icon="🌠",
-    layout="wide",
-    initial_sidebar_state="expanded",
-    menu_items={
-        'Get Help': 'https://huggingface.co/awacke1',
-        'Report a bug': "https://huggingface.co/spaces/awacke1/WebDataDownload",
-        'About': "# Midjourney: https://discord.com/channels/@me/997514686608191558"
-    }
-)
 
 # Ensure the directory for storing scores exists
 score_dir = "scores"
@@ -323,95 +348,6 @@ def display_content_or_image(query):
 
 
 
-    
-# Imports
-import base64
-import glob
-import json
-import math
-import openai
-import os
-import pytz
-import re
-import requests
-import streamlit as st
-import textract
-import time
-import zipfile
-import huggingface_hub
-import dotenv
-from audio_recorder_streamlit import audio_recorder
-from bs4 import BeautifulSoup
-from collections import deque
-from datetime import datetime
-from dotenv import load_dotenv
-from huggingface_hub import InferenceClient
-from io import BytesIO
-from langchain.chat_models import ChatOpenAI
-from langchain.chains import ConversationalRetrievalChain
-from langchain.embeddings import OpenAIEmbeddings
-from langchain.memory import ConversationBufferMemory
-from langchain.text_splitter import CharacterTextSplitter
-from langchain.vectorstores import FAISS
-from openai import ChatCompletion
-from PyPDF2 import PdfReader
-from templates import bot_template, css, user_template
-from xml.etree import ElementTree as ET
-import streamlit.components.v1 as components  # Import Streamlit Components for HTML5
-
-
-def add_Med_Licensing_Exam_Dataset():
-    import streamlit as st
-    from datasets import load_dataset
-    dataset = load_dataset("augtoma/usmle_step_1")['test']  # Using 'test' split
-    st.title("USMLE Step 1 Dataset Viewer")
-    if len(dataset) == 0:
-        st.write("😢 The dataset is empty.")
-    else:
-        st.write("""
-        🔍 Use the search box to filter questions or use the grid to scroll through the dataset.
-        """)
-    
-        # 👩‍🔬 Search Box
-        search_term = st.text_input("Search for a specific question:", "")
-        
-        # 🎛 Pagination
-        records_per_page = 100
-        num_records = len(dataset)
-        num_pages = max(int(num_records / records_per_page), 1)
-        
-        # Skip generating the slider if num_pages is 1 (i.e., all records fit in one page)
-        if num_pages > 1:
-            page_number = st.select_slider("Select page:", options=list(range(1, num_pages + 1)))
-        else:
-            page_number = 1  # Only one page
-        
-        # 📊 Display Data
-        start_idx = (page_number - 1) * records_per_page
-        end_idx = start_idx + records_per_page
-    
-        # 🧪 Apply the Search Filter
-        filtered_data = []
-        for record in dataset[start_idx:end_idx]:
-            if isinstance(record, dict) and 'text' in record and 'id' in record:
-                if search_term:
-                    if search_term.lower() in record['text'].lower():
-                        st.markdown(record)
-                        filtered_data.append(record)
-                else:
-                    filtered_data.append(record)
-    
-        # 🌐 Render the Grid
-        for record in filtered_data:
-            st.write(f"## Question ID: {record['id']}")
-            st.write(f"### Question:")
-            st.write(f"{record['text']}")
-            st.write(f"### Answer:")
-            st.write(f"{record['answer']}")
-            st.write("---")
-    
-        st.write(f"😊 Total Records: {num_records} | 📄 Displaying {start_idx+1} to {min(end_idx, num_records)}")
-
 # 1. Constants and Top Level UI Variables
 
 # My Inference API Copy
@@ -644,7 +580,7 @@ def read_file_content(file,max_length):
     else:
         return ""
 
-# 11. Chat with GPT - Caution on quota - now favoring fastest AI pipeline STT Whisper->LLM Llama->TTS
+# 11. Chat with GPT - Caution on quota 
 @st.cache_resource
 def chat_with_model(prompt, document_section='', model_choice='gpt-3.5-turbo'):
     model = model_choice
@@ -676,16 +612,6 @@ def chat_with_model(prompt, document_section='', model_choice='gpt-3.5-turbo'):
     st.write(time.time() - start_time)
     return full_reply_content
 
-# 12. Embedding VectorDB for LLM query of documents to text to compress inputs and prompt together as Chat memory using Langchain
-@st.cache_resource
-def chat_with_file_contents(prompt, file_content, model_choice='gpt-3.5-turbo'):
-    conversation = [{'role': 'system', 'content': 'You are a helpful assistant.'}]
-    conversation.append({'role': 'user', 'content': prompt})
-    if len(file_content)>0:
-        conversation.append({'role': 'assistant', 'content': file_content})
-    response = openai.ChatCompletion.create(model=model_choice, messages=conversation)
-    return response['choices'][0]['message']['content']
-
 def extract_mime_type(file):
     if isinstance(file, str):
         pattern = r"type='(.*?)'"