Upload 2 files

app.py

@@ -0,0 +1,244 @@
+# -*- coding: utf-8 -*-
+"""App
+
+Automatically generated by Colab.
+
+Original file is located at
+    https://colab.research.google.com/drive/1TdjbTSA8V5GUProQ3Bd-uYmTLXSInoWf
+"""
+
+import subprocess
+
+def install_espeak():
+    try:
+        #subprocess.run(["sudo", "apt-get", "install", "espeak", "-y"], check=True)
+        subprocess.run(["apt-get", "install", "espeak", "-y"], check=True)  # Removed 'sudo'
+        print("eSpeak installed successfully!")
+    except subprocess.CalledProcessError as e:
+        print(f"Error occurred while installing eSpeak: {e}")
+
+# Call the function to install eSpeak
+install_espeak()
+
+import gradio as gr
+import numpy as np
+from transformers import pipeline
+import os
+import groq
+from langchain_groq import ChatGroq
+from langchain.schema import HumanMessage
+from langchain.text_splitter import RecursiveCharacterTextSplitter
+from langchain.vectorstores import Chroma
+from langchain.embeddings import HuggingFaceEmbeddings
+from langchain.docstore.document import Document
+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", "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")  # Replace with a valid API key
+
+# Initialize Chat Model
+chat_model = ChatGroq(model_name="DeepSeek-R1-Distill-Llama-70b", api_key=groq.api_key)     # llama-3.3-70b-versatile
+
+# Initialize Embeddings
+embedding_model = HuggingFaceEmbeddings()
+
+# Initialize ChromaDB
+vectorstore = Chroma(embedding_function=embedding_model)
+
+# Prompt for quiz generation with added remark
+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.
+Remove all unnecessary formatting generated by the LLM, including <think> tags, asterisks, markdown formatting, and any bold or italic text, as well as **, ###, ##, and # tags."
+
+For each question:
+
+- Provide 4 answer choices (for MCQs), with only one correct answer.
+- Ensure fill-in-the-blank questions focus on key terms, phrases, or concepts from the document.
+- Include an answer key for all questions.
+- Ensure questions vary in difficulty and encourage comprehension rather than memorization.
+- Additionally, implement an instant feedback mechanism:
+    - When a user selects an answer, indicate whether it is correct or incorrect.
+    - If incorrect, provide a brief explanation from the document to guide learning.
+    - Ensure responses are concise and educational to enhance understanding.
+
+Output Example:
+1. Fill in the blank: The LLM Agent framework has a central decision-making unit called the _______________________.
+
+Answer: Agent Core
+
+Feedback: The Agent Core is the central component of the LLM Agent framework, responsible for managing goals, tool instructions, planning modules, memory integration, and agent persona.
+
+2. What is the main limitation of LLM-based applications?
+a) Limited token capacity
+b) Lack of domain expertise
+c) Prone to hallucination
+d) All of the above
+
+Answer: d) All of the above
+
+Feedback: LLM-based applications have several limitations, including limited token capacity, lack of domain expertise, and being prone to hallucination, among others.
+
+
+"""
+
+# Function to clean AI response by removing unwanted formatting
+def clean_response(response):
+    """Removes <think> tags, asterisks, and markdown formatting."""
+    cleaned_text = re.sub(r"<think>.*?</think>", "", response, flags=re.DOTALL)  # Remove <think> tags
+    cleaned_text = re.sub(r"(\*\*|\*)", "", cleaned_text)  # Remove **bold** and *italics*
+    cleaned_text = re.sub(r"^#+\s*", "", cleaned_text, flags=re.MULTILINE)  # Remove # and ### tags
+    return cleaned_text.strip()
+
+# 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)])
+
+    # Apply text cleaning before returning the response
+    cleaned_response = clean_response(response.content)
+
+    return cleaned_response
+
+
+# Function to handle chatbot interactions
+def chat_with_groq(user_input):
+    try:
+        response = chat_model([HumanMessage(content=user_input)])
+        cleaned_response_text = clean_response(response.content)  # Clean the response here
+        audio_file = speech_playback(cleaned_response_text)  # Play the speech after generating the response
+        return cleaned_response_text, audio_file  # Return both response and audio file path
+    except Exception as e:
+        return f"Error: {str(e)}", None
+
+# Function to play response as speech using gTTS
+def speech_playback(text):
+    tts = gtts.gTTS(text, lang='en')
+    audio_file = "output_audio.mp3"
+    tts.save(audio_file)
+    return audio_file  # Return the path to the audio file
+
+# Function to detect encoding safely
+def detect_encoding(file_path):
+    try:
+        with open(file_path, "rb") as f:
+            raw_data = f.read(4096)  # Read first 4KB for detection
+            detected = chardet.detect(raw_data)
+            encoding = detected["encoding"]
+        return encoding if encoding else "utf-8"  # Default to UTF-8 if detection fails
+    except Exception:
+        return "utf-8"
+
+# Function to extract text from PDF
+def extract_text_from_pdf(pdf_path):
+    try:
+        doc = fitz.open(pdf_path)
+        text = "\n".join([page.get_text("text") for page in doc])
+        return text if text.strip() else "No extractable text found."
+    except Exception as e:
+        return f"Error extracting text from PDF: {str(e)}"
+
+# Function to extract text from Word files (.docx)
+def extract_text_from_docx(docx_path):
+    try:
+        doc = docx.Document(docx_path)
+        text = "\n".join([para.text for para in doc.paragraphs])
+        return text if text.strip() else "No extractable text found."
+    except Exception as e:
+        return f"Error extracting text from Word document: {str(e)}"
+
+# Function to extract text from PowerPoint files (.pptx)
+def extract_text_from_pptx(pptx_path):
+    try:
+        presentation = Presentation(pptx_path)
+        text = ""
+        for slide in presentation.slides:
+            for shape in slide.shapes:
+                if hasattr(shape, "text"):
+                    text += shape.text + "\n"
+        return text if text.strip() else "No extractable text found."
+    except Exception as e:
+        return f"Error extracting text from PowerPoint: {str(e)}"
+
+# Function to process documents safely
+def process_document(file):
+    try:
+        file_extension = os.path.splitext(file.name)[-1].lower()
+
+        if file_extension in [".png", ".jpg", ".jpeg"]:
+            return f"Error: Images cannot be processed for text extraction."
+
+        # Extract text based on file type
+        if file_extension == ".pdf":
+            content = extract_text_from_pdf(file.name)
+        elif file_extension == ".docx":
+            content = extract_text_from_docx(file.name)
+        elif file_extension == ".pptx":
+            content = extract_text_from_pptx(file.name)
+        else:
+            encoding = detect_encoding(file.name)
+            with open(file.name, "r", encoding=encoding, errors="replace") as f:
+                content = f.read()
+
+        # Process text into chunks
+        text_splitter = RecursiveCharacterTextSplitter(chunk_size=500, chunk_overlap=50)
+        documents = [Document(page_content=chunk) for chunk in text_splitter.split_text(content)]
+        vectorstore.add_documents(documents)
+
+        # Generate quiz based on document content
+        quiz = generate_quiz(content)
+
+        return f"Document processed successfully (File Type: {file_extension}). Quiz generated:\n{quiz}"
+
+    except Exception as e:
+        return f"Error processing document: {str(e)}"
+
+# Function to handle speech-to-text conversion
+def transcribe_audio(audio):
+    sr, y = audio
+
+    # Convert to mono if stereo
+    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"]
+
+# Gradio UI
+with gr.Blocks() as demo:
+    gr.HTML("<h2 style='text-align: center;'>AI Tutor</h2>")
+    gr.HTML("""
+        <div style="text-align: center; margin-bottom: 20px;">
+            <img src="https://img.freepik.com/premium-photo/little-girl-is-seen-sitting-front-laptop-computer-engaged-with-nearby-robot-robot-assistant-helping-child-with-homework-ai-generated_585735-12266.jpg" style="max-width: 60%; height: auto; border-radius: 10px; box-shadow: 0 4px 8px rgba(0,0,0,0.2);" />
+        </div>
+    """)
+
+    with gr.Row():
+        with gr.Column():
+            audio_input = gr.Audio(type="numpy", label="Record Audio")
+            transcription_output = gr.Textbox(label="Transcription")
+            user_input = gr.Textbox(label="Ask a question")
+            chat_output = gr.Textbox(label="Response")
+            audio_output = gr.Audio(label="Audio Playback")  # Add an audio output component
+            submit_btn = gr.Button("Ask")
+        with gr.Column():
+            file_upload = gr.File(label="Upload a document")
+            process_status = gr.Textbox(label="Processing Status", interactive=False)
+            process_btn = gr.Button("Process Document")
+
+    audio_input.change(fn=transcribe_audio, inputs=audio_input, outputs=transcription_output)
+    transcription_output.change(fn=lambda x: x, inputs=transcription_output, outputs=user_input)
+    submit_btn.click(chat_with_groq, inputs=user_input, outputs=[chat_output, audio_output])  # Fixed closing brackets
+    process_btn.click(process_document, inputs=file_upload, outputs=process_status)
+
+# Launch the Gradio app
+demo.launch()

requirements.txt

@@ -0,0 +1,18 @@
+gradio
+groq
+gtts
+langchain
+langchain-core
+langchain-community
+langchain-text-splitters
+langgraph
+chromadb
+langsmith
+llama-cpp-python
+langchain_huggingface
+pymupdf
+sentence_transformers
+langchain-groq
+langchain-docling
+langchain-chroma
+pyttsx3