Update app.py

app.py

@@ -38,92 +38,17 @@ transcriber = pipeline("automatic-speech-recognition", model="openai/whisper-bas
 # Set API Key (Ensure it's stored securely in an environment variable)
 groq.api_key = os.getenv("GROQ_API_KEY")  # Replace with a valid API key
 
-#___________________________________
-
-# Authenticate with Hugging Face API using the token
-#hf_token = os.getenv("HF_TOKEN")  # Replace with the environment variable containing your Hugging Face token
-#login(token=hf_token)
-
-# Load the LLaVA model
-#model_id = "liuhaotian/LLaVA-7B"  # You can change the model ID based on what is available
-#processor = AutoProcessor.from_pretrained(model_id)
-#model = AutoModelForVision2Seq.from_pretrained(model_id, torch_dtype=torch.float16).cuda()
-
-# Load and preprocess an image
-#image = Image.open("your_image.jpg")  # Replace with the path to your image
-#inputs = processor(text="Describe this image", images=image, return_tensors="pt").to("cuda")
-
-# Generate output from LLaVA model
-#output = model.generate(**inputs)
-
-# Decode and print the output
-#print(processor.decode(output[0]))
-
-#___________________________________
-
 # Initialize Chat Model
 chat_model = ChatGroq(model_name="llama-3.3-70b-versatile", api_key=groq.api_key) #DeepSeek-R1-Distill-Llama-70b , llama-3.3-70b-versatile , deepseek-r1-distill-qwen-32b
 
-# Initialize Embeddings and chromaDB
-
-embedding_model = HuggingFaceEmbeddings()
-vectorstore = Chroma(embedding_function=embedding_model)
-
-
-# -*- coding: utf-8 -*-
-"""app
-
-Automatically generated by Colab.
-
-Original file is located at
-    https://colab.research.google.com/drive/1jdKA4WQJcLb0_aQ3vtGVM46B1wriSsDv
-"""
-
-import gradio as gr
-import numpy as np
-from transformers import pipeline
-import os
-import time
-import groq
-import uuid  # For generating unique filenames
-
-# Updated imports to address LangChain deprecation warnings:
-from langchain_groq import ChatGroq
-from langchain.schema import HumanMessage
-from langchain.text_splitter import RecursiveCharacterTextSplitter
-from langchain_community.vectorstores import Chroma
-from langchain_community.embeddings import HuggingFaceEmbeddings
-from langchain.docstore.document import Document
-
-# Importing chardet (make sure to add chardet to your requirements.txt)
-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)
-groq.api_key = os.getenv("GROQ_API_KEY")
-
-# Initialize Chat Model
-chat_model = ChatGroq(model_name="llama-3.3-70b-versatile", api_key=groq.api_key) #DeepSeek-R1-Distill-Llama-70b    |   deepseek-r1-distill-qwen-32b
-
 # Initialize Embeddings and chromaDB
 os.makedirs("chroma_db", exist_ok=True)
 embedding_model = HuggingFaceEmbeddings()
-#new
 vectorstore = Chroma(
     embedding_function=embedding_model,
     persist_directory="chroma_db"  # Set a valid folder name or path
 )
 vectorstore.persist()
-#end New
 
 # Short-term memory for the LLM
 chat_memory = []
@@ -171,7 +96,7 @@ d) 0.4
 
 Answer: d) 0.4
 
-Feedback: This question tests understanding of Bayes’ Theorem by requiring the calculation of conditional probability using the given values.
+Feedback: This question tests understanding of Bayes' Theorem by requiring the calculation of conditional probability using the given values.
 """
 
 # Function to clean AI response by removing unwanted formatting
@@ -197,7 +122,7 @@ def retrieve_documents(query):
     return [doc.page_content for doc in results]
 
 # Function to handle chatbot interactions with short-term memory
-def chat_with_groq(user_input):
+def chat_with_groq(user_input, chat_history):
     try:
         # Retrieve relevant documents for additional context
         relevant_docs = retrieve_documents(user_input)
@@ -218,14 +143,16 @@ def chat_with_groq(user_input):
         chat_memory.append(f"User: {user_input}")
         chat_memory.append(f"AI: {cleaned_response_text}")
 
+        # Update chat history for Gradio
+        chat_history.append((user_input, cleaned_response_text))
+
         # Convert response to speech
         audio_file = speech_playback(cleaned_response_text)
 
-        # Ensure the return format is a list of tuples
-        return [(user_input, cleaned_response_text)], audio_file
+        return chat_history, "", audio_file
     except Exception as e:
-        return [("Error", str(e))], None
-
+        chat_history.append((user_input, f"Error: {str(e)}"))
+        return chat_history, "", None
 
 # Function to play response as speech using gTTS
 def speech_playback(text):
@@ -321,37 +248,10 @@ def transcribe_audio(audio):
     y /= np.max(np.abs(y))
     return transcriber({"sampling_rate": sr, "raw": y})["text"]
 
-# Modify chat_with_groq function to return audio file for playback
-def chat_with_groq(user_input):
-    try:
-        # Retrieve relevant documents for additional context
-        relevant_docs = retrieve_documents(user_input)
-        context = "\n".join(relevant_docs) if relevant_docs else "No relevant documents found."
-
-        # 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
-        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)])
-
-        # Clean response to remove any unwanted formatting
-        cleaned_response_text = clean_response(response.content)
-
-        # Append conversation history
-        chat_memory.append(f"User: {user_input}")
-        chat_memory.append(f"AI: {cleaned_response_text}")
-
-        # Convert response to speech
-        audio_file = speech_playback(cleaned_response_text)
-
-        # Return both chat response and audio file path
-        return [(user_input, cleaned_response_text)], audio_file  # Return as a tuple
-    except Exception as e:
-        return [("Error", str(e))], None
-
-#__________________________________________________________________________________________________________________________
+# 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."""
@@ -363,17 +263,14 @@ def tutor_ai_chatbot():
         with gr.Tab("AI Chatbot"):
             with gr.Row():
                 with gr.Column(scale=3):
-                    #chatbot = gr.Chatbot(height=500)  # Chatbot display area
                     chatbot = gr.Chatbot(height=500, type="messages")
                     with gr.Row():
                         msg = gr.Textbox(label="Ask a question", placeholder="Type your question here...")
                         submit = gr.Button("Send")
 
-                    #with gr.Row():
                     with gr.Column(scale=1):
                         audio_input = gr.Audio(type="numpy", label="Record or Upload Audio")   # Audio input for speech-to-text
 
-
                 with gr.Column(scale=1):
                    audio_playback = gr.Audio(label="Audio Response", type="filepath")
 
@@ -383,21 +280,18 @@ def tutor_ai_chatbot():
             # Handle chat interaction
             submit.click(
                 chat_with_groq,
-                inputs=[msg],
-                outputs=[chatbot, audio_playback]
+                inputs=[msg, chatbot],
+                outputs=[chatbot, msg, audio_playback]
             )
 
             # Clear chat history function
-            def clear_chat_history():
-                return None, None
-
-            clear_btn.click(clear_chat_history, inputs=None, outputs=[chatbot, audio_playback])    #,audio_input
+            clear_btn.click(clear_chat_history, inputs=None, outputs=[chatbot, audio_playback])
 
             # Also allow Enter key to submit
             msg.submit(
                 chat_with_groq,
-                inputs=[msg],
-                outputs=[chatbot, audio_playback]
+                inputs=[msg, chatbot],
+                outputs=[chatbot, msg, audio_playback]
             )
 
             # Add some examples of questions students might ask
@@ -413,35 +307,30 @@ def tutor_ai_chatbot():
                     inputs=msg
                 )
 
+            # Connect audio input to transcription
+            audio_input.change(fn=transcribe_audio, inputs=audio_input, outputs=msg)
+
         # Upload Notes & Generate Quiz Tab
         with gr.Tab("Upload Notes & Generate Quiz"):
             with gr.Row():
                 with gr.Column(scale=2):
                     file_input = gr.File(label="Upload Lecture Notes (PDF, DOCX, PPTX)")
-                    #generate_btn = gr.Button("Generate Quiz")
                 with gr.Column(scale=3):
                     quiz_output = gr.Textbox(label="Generated Quiz", lines=10)
 
+            # Connect file input to document processing
+            file_input.change(process_document, inputs=file_input, outputs=quiz_output)
 
          # Introduction Video
         with gr.Tab("Introduction Video"):
             with gr.Row():
                 with gr.Column(scale=1):
-                    #with gr.Column(scale=1):  # Adjust scale for equal width
-                    gr.Markdown("### Welcome to the Introduction Video")  # Adding a heading
-                    gr.Markdown("Music from Xu Mengyuan - China-O, musician Xu Mengyuan YUAN! | 徐梦圆 - China-O 音乐人徐梦圆YUAN! ")  # Adding descriptive text
-                    #gr.Video("https://github.com/lesterchia1/AI_tutor/raw/main/We%20not%20me%20video.mp4", label="Introduction Video")
+                    gr.Markdown("### Welcome to the Introduction Video")
+                    gr.Markdown("Music from Xu Mengyuan - China-O, musician Xu Mengyuan YUAN! | 徐梦圆 - China-O 音乐人徐梦圆YUAN! ")
                     gr.Video("https://huggingface.co/spaces/Lesterchia174/FPOC2_AI-Tutor_Chatbot/raw/main/We%20not%20me%20video.mp4", label="Introduction Video")
 
-
-            # Connect the button to the document processing function
-            audio_input.change(fn=transcribe_audio, inputs=audio_input, outputs=msg)  # transcribe and fill the msg textbox
-            file_input.change(process_document, inputs=file_input, outputs=quiz_output)
-
-
     # Launch the application
-    app.launch(share=True)  # Set share=True to create a public link
-
+    app.launch(share=True)
 
 # Launch the AI chatbot
 if __name__ == "__main__":