app.py

import gradio as gr
from sentence_transformers import SentenceTransformer, util
import openai
import os
import random
#import transformers
#from transformers import pipeline

os.environ["TOKENIZERS_PARALLELISM"] = "false"

# Initialize paths and model identifiers for easy configuration and maintenance
filename = "output_topic_details.txt"  # Path to the file storing AI-specific details
retrieval_model_name = 'output/sentence-transformer-finetuned/'

openai.api_key = os.environ["OPENAI_API_KEY"]

system_message = "You are an AI chatbot specialized in providing information on AI usage, helpful tools, and teaching users about AI."
# Initial system message to set the behavior of the assistant
messages = [{"role": "system", "content": system_message}]

# Attempt to load the necessary models and provide feedback on success or failure
try:
    retrieval_model = SentenceTransformer(retrieval_model_name)
    print("Models loaded successfully.")
except Exception as e:
    print(f"Failed to load models: {e}")

def load_and_preprocess_text(filename):
    """
    Load and preprocess text from a file, removing empty lines and stripping whitespace.
    """
    try:
        with open(filename, 'r', encoding='utf-8') as file:
            segments = [line.strip() for line in file if line.strip()]
        print("Text loaded and preprocessed successfully.")
        return segments
    except Exception as e:
        print(f"Failed to load or preprocess text: {e}")
        return []

segments = load_and_preprocess_text(filename)

def find_relevant_segment(user_query, segments):
    """
    Find the most relevant text segment for a user's query using cosine similarity among sentence embeddings.
    This version finds the best match based on the content of the query.
    """
    try:
        # Lowercase the query for better matching
        lower_query = user_query.lower()
        
        # Encode the query and the segments
        query_embedding = retrieval_model.encode(lower_query)
        segment_embeddings = retrieval_model.encode(segments)
        
        # Compute cosine similarities between the query and the segments
        similarities = util.pytorch_cos_sim(query_embedding, segment_embeddings)[0]
        
        # Find the index of the most similar segment
        best_idx = similarities.argmax()
        
        # Return the most relevant segment
        return segments[best_idx]
    except Exception as e:
        print(f"Error in finding relevant segment: {e}")
        return ""

def generate_response(user_query, relevant_segment):
    """
    Generate a response emphasizing the bot's capability in providing AI information.
    """
    try:
        user_message = f"Here's the information on AI: {relevant_segment}"

        # Append user's message to messages list
        messages.append({"role": "user", "content": user_message})
        
        response = openai.ChatCompletion.create(
            model="gpt-3.5-turbo",
            messages=messages,
            max_tokens=350,
            temperature=0.2,
            top_p=1,
            frequency_penalty=0,
            presence_penalty=0
        )
        
        # Extract the response text
        output_text = response['choices'][0]['message']['content'].strip()
        
        # Append assistant's message to messages list for context
        messages.append({"role": "assistant", "content": output_text})
        fun_int=random.randint(0,11)
        fun_facts=["Young Einstein didn't talk until much later in his childhood.","Einstein had larger-than-average perietal lobes.","Einstein was a talented violinist","Einstein's brain was preserved after his death!","Einstein started as a teacher, but couldn't find a job.","Einstein's famous equation E=mc² was announced in 1905.","Einstein won The Nobel Prize in Physics in 1921","Einstien did not wear socks!","Einstein loved sailing.",'Einstein once said -"If you can not explain it simply, you don not understand it well enough."','Einstein once said- "Logic will get you from A to B. Imagination will get you anywhere."']
        output_text=output_text+"\n\n Here is a fun fact about Albert Einstein!: " + fun_facts[fun_int-1]
        ai_int=random.randint(0,10)
        ai_helpers=["https://chatgpt.com/ - An AI chatbot","https://www.grammarly.com/ - Help with grammar and writing!","https://www.any.do/ - Creates a to do list to help you get your tasks completed!","https://scheduler.ai/- AI optimizes your schedule and works around pre-scheduled deadlines","ChatGPT Data Analyst - Helps you visualize and analize your data","ChatGPT Logo creator - Helps to create professional logos for companies or brands","ScholarGPT - Enhances your reaserch capabilities","ChatGPT's Math solver","Tutor Me by Khan Academy","Travel Guide by capchair - helps find destinations, plan trips, and manage budgets"]
        output_text=output_text+"\n\n Here is a helpful chatbot tool for you!: "+ ai_helpers[ai_int-1]
        return output_text

        # Create pipeline for text generation with confidence scores
        #generator = pipeline("text-davinci-003", device=0)  # Adjust device if needed

        # Generate response and get confidence score
        #response = generator(query=f"Here's the information on AI: {relevant_segment} {user_query}", max_length=150, temperature=0.2, top_p=1)
        #generated_text = response[0]['generated_text'].strip()
        #confidence_score = response[0]['score']

        #return generated_text, confidence_score, output_text
        
    except Exception as e:
        print(f"Error in generating response: {e}")
        return f"Error in generating response: {e}"

def query_model(question):
    """
    Process a question, find relevant information, and generate a response.
    """
    if question == "":
        return "Welcome to AI-nstein! Ask me anything about AI ML, and helpful tools you may want to use!"
    relevant_segment = find_relevant_segment(question, segments)
    if not relevant_segment:
        return "Could not find specific information. Please refine your question."
    response = generate_response(question, relevant_segment)
    return response

# Define the welcome message and specific topics the chatbot can provide information about
welcome_message = """
## Your AI-driven assistant for all AI-related queries.
"""
topicList = """
### Feel free to ask me anything from the topics below! \nI give you a fun chatbot and an Einstein fact with every answer.
"""

topics1 = """
    \n- AI Usage
    \n- AI Safety
    \n- How AI Works

    """
topics2 = """
    \n- Basics of AI
    \n- Fun Facts about AI
    \n- Examples of AI

    """
headline="""
#Welcome to AI-nstein!
"""



#def display_image():
    #return "https://i.giphy.com/media/v1.Y2lkPTc5MGI3NjExZzdqMnkzcWpjbGhmM3hzcXp0MGpuaTF5djR4bjBxM3Biam5zbzNnMCZlcD12MV9pbnRlcm5hbF9naWZfYnlfaWQmY3Q9cw/GxMnTi3hV3qaIgbgQL/giphy.gif"
    #return "https://cdn-uploads.huggingface.co/production/uploads/6668622b72b61ba78fe7d4bb/PkWjNxvGm9MOqGkZdiT4e.png"
theme = gr.themes.Monochrome(
    primary_hue="amber", #okay this did NOT work lmaoo
    secondary_hue="rose",
).set(
    body_text_color='#FFFFFF',
    body_text_color_dark='#000000',
    background_fill_primary='#81A4CD',  # BACKGROUND
    background_fill_primary_dark='#81A4CD',
    background_fill_secondary='#884e4c',  # BUTTON HOVER
    background_fill_secondary_dark='#EDDEC0', #LOADING BAR
    border_color_accent='#EDDEC0',
    border_color_accent_dark='#EDDEC0',
    border_color_accent_subdued='#EDDEC0',
    border_color_primary='#F17300',
    block_border_color='#F17300',
    button_primary_background_fill='#054A91',
    button_primary_background_fill_dark='#054A91'
    
)
# Setup the Gradio Blocks interface with custom layout components
with gr.Blocks(theme=theme) as demo:
     with gr.Row(equal_height=True):
        with gr.Column():
            gr.Image("ally.png", container = False, show_share_button = False, show_download_button = False, label="output", show_label=True, elem_id="output_image", scale=0, width=500)
            gr.Markdown(welcome_message)  # Display the formatted welcome message
            with gr.Row():
                with gr.Column():
                    gr.Markdown(topicList)
                    with gr.Row(equal_height=True):
                        gr.Markdown(topics1)  # Show the topics on the left side
                        gr.Markdown(topics2)
            
        with gr.Row():
            with gr.Column():
                gr.Markdown("      ")
                gr.Markdown(headline)
                gr.Markdown("      ")
                question = gr.Textbox(label="Your question:", placeholder="What do you want to ask about?")
                submit_button = gr.Button("Submit!")
                answer = gr.Textbox(label="AI-nswer:", placeholder="AI-nstein will respond here...", interactive=False, lines=10)
                submit_button.click(fn=query_model, inputs=question, outputs=answer)


            #def display_response(question):
                #response, confidence_score = query_model(question)
                #answer.value = f"Response: {response}\nConfidence Score: {confidence_score:.2f}"  

            #submit_button.click(fn=display_response, inputs=question, outputs=None)
            

            
            

# Launch the Gradio app to allow user interaction
demo.launch(share=True)