app.py

import gradio as gr
from sentence_transformers import SentenceTransformer, util
import openai
import os

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 chess-specific details
retrieval_model_name = 'output/sentence-transformer-finetuned/'

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

system_message = "You are a eco-friendly travel chatbot specialized in providing information on eco-friendly restaurants, hotels, and attractions in NYC, you can also provide the user with environment-themed pickup lines."
# 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 eco-friendly travel information.
    """
    try:
        user_message = f"Here's the information on eco-friendly travel information: {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=150,
            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})
        
        return 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 GreenGuide! Ask me anything about eco-friendly hotels, restaurants, and things to do in NYC."
    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 HTML iframe content

iframe = '''
<iframe src="https://www.google.com/maps/embed?pb=!1m18!1m12!1m3!1d193595.2528001417!2d-74.1444872802558!3d40.69763123330436!2m3!1f0!2f0!3f0!3m2!1i1024!2i768!4f13.1!3m3!1m2!1s0x89c24fa5d33f083b%3A0xc80b8f06e177fe62!2sNew%20York%2C%20NY!5e0!3m2!1sen!2sus!4v1722483445443!5m2!1sen!2sus" width="600" height="450" style="border:0;" allowfullscreen="" loading="lazy" referrerpolicy="no-referrer-when-downgrade"></iframe>
'''


# Define the welcome message and specific topics the chatbot can provide information about
welcome_message = """
# 🌱 Welcome to GreenGuide!
## Your AI-driven assistant for all eco-friendly travel-related queries in NYC. Created by Eva, Amy, and Ambur of the 2024 Kode With Klossy NYC AI/ML Camp. 
"""

topics = """
### Feel free to ask me anything things to do in the city!
- Hotels (affordable, luxury)
- Restaurants (regular, vegetarian, vegan)
- Parks & Gardens
- Thrift Stores
- Attractions
"""

# Create a Gradio HTML component
def display_iframe():
    return iframe
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(
    background_fill_primary='#CBE9A2',  # BACKGROUND
    background_fill_primary_dark='#768550',
    background_fill_secondary='#768550',  # BUTTON HOVER
    background_fill_secondary_dark='#99a381', #LOADING BAR
    border_color_accent='#768550',
    border_color_accent_dark='#768550',
    border_color_accent_subdued='#768550',
    border_color_primary='#03a9f4',
    block_border_color='#b3e5fc',
    button_primary_background_fill='#768550',
    button_primary_background_fill_dark='#768550'
)

# Setup the Gradio Blocks interface with custom layout components
with gr.Blocks(theme=theme) as demo:
    gr.Image("header2.png", show_label = False, show_share_button = False, show_download_button = False) #CHANGE !!
    gr.Markdown(welcome_message)  # Display the formatted welcome message
    with gr.Row():
        with gr.Column():
            gr.Markdown(topics)  # Show the topics on the left side
    with gr.Row():
        with gr.Column():
            question = gr.Textbox(label="Your question", placeholder="What do you want to ask about?")
            answer = gr.Textbox(label="GreenGuide Response", placeholder="GreenGuide will respond here...", interactive=False, lines=10)
            submit_button = gr.Button("Submit")
            submit_button.click(fn=query_model, inputs=question, outputs=answer)

    gr.HTML(iframe)        
    

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