Update app.py

app.py

@@ -11,38 +11,25 @@ from transformers import pipeline
 import os
 import time
 import groq
-import uuid  # For generating unique filenames
+import uuid
 
-# Add torch imports at the top
-import torch
-import torchaudio
-
-
-# NEW IMPORTS (current):
+# LangChain imports
 from langchain_core.messages import HumanMessage, SystemMessage, AIMessage
 from langchain_text_splitters import RecursiveCharacterTextSplitter
 from langchain_core.documents import Document
-from langchain_community.document_loaders import TextLoader, PyPDFLoader
 from langchain_community.embeddings import HuggingFaceEmbeddings
-from langchain_community.llms import HuggingFaceHub
-#from langchain_community.chains import RetrievalQA
-#from langchain.chains.retrieval_qa.base import RetrievalQA   # This one might still be in main langchain
-from langchain_community.vectorstores import Chroma #from old library
+from langchain_community.vectorstores import Chroma
 from langchain_groq import ChatGroq
 
-# Importing chardet (make sure to add chardet to your requirements.txt)
+# Other imports
 import chardet
-
 import fitz  # PyMuPDF for PDFs
 import docx  # python-docx for Word files
 import gtts  # Google Text-to-Speech library
 from pptx import Presentation  # python-pptx for PowerPoint files
 import re
 
-# Initialize Whisper model for speech-to-text
-transcriber = pipeline("automatic-speech-recognition", model="openai/whisper-base.en")
-
-# Set API Key (Ensure it's stored securely in an environment variable)
+# Set API Key
 groq.api_key = os.getenv("GROQ_API_KEY")
 
 # Initialize Chat Model
@@ -59,7 +46,7 @@ vectorstore = Chroma(
 # Short-term memory for the LLM
 chat_memory = []
 
-# Prompt for quiz generation with added remark
+# Prompt for quiz generation
 quiz_prompt = """
 You are an AI assistant specialized in education and assessment creation. Given an uploaded document or text, generate a quiz with a mix of multiple-choice questions (MCQs) and fill-in-the-blank questions. The quiz should be directly based on the key concepts, facts, and details from the provided material.
 Generate 20 Questions.
@@ -109,13 +96,10 @@ def clean_response(response):
 # Function to generate quiz based on content
 def generate_quiz(content):
     prompt = f"{quiz_prompt}\n\nDocument content:\n{content}"
-    #response = chat_model([HumanMessage(content=prompt)])
-    # Use invoke method instead of direct calling
     response = chat_model.invoke([HumanMessage(content=prompt)])
     cleaned_response = clean_response(response.content)
     return cleaned_response
 
-
 # Function to retrieve relevant documents from vectorstore based on user query
 def retrieve_documents(query):
     results = vectorstore.similarity_search(query, k=3)
@@ -123,7 +107,6 @@ def retrieve_documents(query):
 
 # Function to convert tuple format to message format
 def convert_to_message_format(chat_history):
-    #Convert from [(user, bot)] format to [{"role": "user", "content": user}, {"role": "assistant", "content": bot}] format"""
     message_format = []
     for user_msg, bot_msg in chat_history:
         message_format.append({"role": "user", "content": user_msg})
@@ -132,7 +115,6 @@ def convert_to_message_format(chat_history):
 
 # Function to convert message format to tuple format for processing
 def convert_to_tuple_format(chat_history):
-    #Convert from message format back to tuple format for processing"""
     tuple_format = []
     for i in range(0, len(chat_history), 2):
         if i+1 < len(chat_history):
@@ -153,12 +135,11 @@ def chat_with_groq(user_input, chat_history):
 
         # Construct proper prompting with conversation history
         system_prompt = "You are a helpful AI assistant. Answer questions accurately and concisely."
-        conversation_history = "\n".join(chat_memory[-10:])  # Keep the last 10 exchanges
+        conversation_history = "\n".join(chat_memory[-10:])
         prompt = f"{system_prompt}\n\nConversation History:\n{conversation_history}\n\nUser Input: {user_input}\n\nContext:\n{context}"
 
         # Call the chat model
-        #response = chat_model([HumanMessage(content=prompt)])
-        response = chat_model.invoke([HumanMessage(content=prompt)]) # Call the chat model using invoke method  
+        response = chat_model.invoke([HumanMessage(content=prompt)])
 
         # Clean response to remove any unwanted formatting
         cleaned_response_text = clean_response(response.content)
@@ -167,7 +148,7 @@ def chat_with_groq(user_input, chat_history):
         chat_memory.append(f"User: {user_input}")
         chat_memory.append(f"AI: {cleaned_response_text}")
 
-        # Update chat history - add new messages in the correct format
+        # Update chat history
         chat_history.append({"role": "user", "content": user_input})
         chat_history.append({"role": "assistant", "content": cleaned_response_text})
 
@@ -266,40 +247,6 @@ def process_document(file):
         return f"Error processing document: {str(e)}"
 
 # Function to handle speech-to-text conversion
-
-#def transcribe_audio(audio):
-#    sr, y = audio
-#    if y.ndim > 1:
-#        y = y.mean(axis=1)
-#    y = y.astype(np.float32)
-#    y /= np.max(np.abs(y))
-#    return transcriber({"sampling_rate": sr, "raw": y})["text"]
-
-"""
-# Real-time Whisper setup - cache the model
-#@gr.cache_resource
-#def load_realtime_whisper():
-#    """Load optimized Whisper model for real-time transcription"""
-#    device = "cuda" if torch.cuda.is_available() else "cpu"
-#    torch_dtype = torch.float16 if torch.cuda.is_available() else torch.float32
-    
-#    # Use tiny model for real-time speed
-#    realtime_transcriber = pipeline(
-#        "automatic-speech-recognition",
-#        model="openai/whisper-tiny.en",
-#        device=device,
-#        torch_dtype=torch_dtype,
-#    )
-    
-#    return realtime_transcriber
-
-
-
-
-
-
-# Load model at startup
-# Function to handle speech-to-text conversion
 def transcribe_audio(audio):
     """Simple working transcription"""
     if audio is None:
@@ -336,20 +283,10 @@ def clear_chat_history():
     chat_memory.clear()
     return [], None
 
-
-
-# the remaining is the same 
-
-
-# Clear chat history function
-def clear_chat_history():
-    chat_memory.clear()
-    return [], None
-
 def tutor_ai_chatbot():
     """Main Gradio interface for the Tutor AI Chatbot."""
     with gr.Blocks() as app:
-        gr.Markdown("# 📚 AI Tutor - We.(POC)")
+        gr.Markdown("# AI Tutor - We.(POC)")
         gr.Markdown("An interactive Personal AI Tutor chatbot to help with your learning needs.")
 
         # Chatbot Tab
@@ -366,7 +303,7 @@ def tutor_ai_chatbot():
                 msg = gr.Textbox(
                     label="Ask a question", 
                     placeholder="Type your question here...",
-                    container=False  # Removes the default container styling
+                    container=False
                 )
                 submit = gr.Button("Send")
             
@@ -398,7 +335,7 @@ def tutor_ai_chatbot():
 
             # Clear chat history function
             clear_btn.click(
-                lambda: [],  # Return empty list in message format
+                lambda: [],
                 inputs=None, 
                 outputs=[chatbot]
             )
@@ -451,4 +388,4 @@ def tutor_ai_chatbot():
 
 # Launch the AI chatbot
 if __name__ == "__main__":
-    tutor_ai_chatbot()    
+    tutor_ai_chatbot()