Chatbot to learn GenAI

Generative Models/Chatbot-learn-GenAI/README.md

@@ -0,0 +1,65 @@
+# Generative AI Learning Chatbot
+
+This project is an interactive chatbot designed to help users learn about Generative AI. The chatbot is built using **Streamlit** and **DialoGPT**, and it integrates a knowledge base of Generative AI concepts along with a quiz functionality.
+
+## Features
+
+- **Generative AI Knowledge Base:** The chatbot can answer pre-defined questions about Generative AI concepts such as Generative Adversarial Networks (GANs), Variational Autoencoders (VAEs), and their applications.
+
+- **Quiz Functionality:** Users can engage with quiz questions related to Generative AI. Users can type `quiz` to receive a question, and then input the question in the format `Quiz: [question]` to see the answer.
+
+- **DialoGPT Integration:** For any question that is not in the predefined knowledge base, the chatbot uses the **DialoGPT** model from Hugging Face’s transformers library to generate a text-based response.
+
+## How to Run the Project
+
+### Prerequisites
+
+1. Python 3.7+
+2. Install required libraries using pip:
+    ```bash
+    pip install streamlit transformers
+    ```
+
+### Running the Chatbot
+
+1. Clone this repository:
+    ```bash
+    git clone <repository-url>
+    cd <repository-directory>
+    ```
+
+2. Run the Streamlit app:
+    ```bash
+    streamlit run chatbot.py
+    ```
+
+3. The chatbot will open in your web browser, and you can start interacting with it.
+
+### Sample Interaction
+
+- Ask about Generative AI:
+    ```
+    You: What is Generative AI?
+    Chatbot: Generative AI refers to a category of artificial intelligence techniques that create new data instances that resemble existing data. Examples include Generative Adversarial Networks (GANs) and Variational Autoencoders (VAEs).
+    ```
+
+- Take a quiz:
+    ```
+    You: quiz
+    Chatbot: Here’s a quiz question for you. Type 'Quiz: [question]' to see the answer.
+    ```
+
+    ```
+    You: Quiz: What is the purpose of the discriminator in a GAN?
+    Chatbot: Quiz: What is the purpose of the discriminator in a GAN? (Answer: To distinguish between real and generated data.)
+    ```
+
+## Code Structure
+
+- `chatbot.py`: Contains the main code for the chatbot, including the knowledge base, quiz handling logic, and integration with DialoGPT.
+
+## Future Enhancements
+
+- **Expand Knowledge Base:** Add more detailed information and concepts related to Generative AI.
+- **Improve Quiz Functionality:** Implement more advanced quiz interactions, such as scoring or random question selection.
+- **Personalization:** Integrate user-specific learning paths or history-based interactions.

Generative Models/Chatbot-learn-GenAI/app.py

@@ -0,0 +1,66 @@
+# Install necessary libraries
+# !pip install transformers
+# !pip install torch
+# !pip install streamlit
+
+import streamlit as st
+from transformers import pipeline
+
+# Initialize the text generation pipeline with DialoGPT
+chatbot = pipeline("text-generation", model="microsoft/DialoGPT-medium")
+
+# Define the knowledge base for Generative AI concepts
+knowledge_base = {
+    "What is Generative AI?": "Generative AI refers to a category of artificial intelligence techniques that create new data instances that resemble existing data. Examples include Generative Adversarial Networks (GANs) and Variational Autoencoders (VAEs).",
+    "What is a GAN?": "A Generative Adversarial Network (GAN) consists of two neural networks, a generator and a discriminator, that compete against each other to generate new, synthetic instances of data that resemble real data.",
+    "What is a VAE?": "A Variational Autoencoder (VAE) is a type of generative model that learns to encode input data into a lower-dimensional latent space and then decodes it to generate new data samples.",
+    "Applications of Generative AI": "Generative AI has various applications, including image generation, text generation, style transfer, data augmentation, and more.",
+}
+
+# Define a set of quiz questions and answers
+quizzes = {
+    "What is the purpose of the discriminator in a GAN?": "To distinguish between real and generated data.",
+    "In a VAE, what does the encoder do?": "It compresses input data into a latent space representation."
+}
+
+# Function to generate responses based on the knowledge base
+def chatbot_response(user_input):
+    if user_input.startswith("Quiz:"):
+        return handle_quiz(user_input[5:].strip())
+
+    # Check if the user input matches any predefined questions
+    response = knowledge_base.get(user_input, None)
+    if response is not None:
+        return response
+    else:
+        # Generate a response using the text generation pipeline if no match in knowledge base
+        responses = chatbot(user_input, max_length=100, num_return_sequences=1)
+        return responses[0]['generated_text']
+
+# Function to handle quiz questions
+def handle_quiz(question):
+    answer = quizzes.get(question, None)
+    if answer is not None:
+        return f"Quiz: {question} (Answer: {answer})"
+    else:
+        return "No quiz question found for that input. Try another question or ask about Generative AI concepts."
+
+# Streamlit code for the interactive learning chatbot
+def main():
+    st.title("Generative AI Learning Chatbot")
+
+    st.write("Hello! I am here to help you learn about Generative AI. Ask me questions or type 'quiz' to take a quiz.")
+
+    # Input from user
+    user_input = st.text_input("You:", placeholder="Ask me about Generative AI or type 'quiz' for a quiz question")
+
+    if user_input:
+        if user_input.lower() == 'quiz':
+            st.write("Here’s a quiz question for you. Type 'Quiz: [question]' to see the answer.")
+        else:
+            # Get response from chatbot
+            response = chatbot_response(user_input)
+            st.write(f"Chatbot: {response}")
+
+if __name__ == "__main__":
+    main()