app.py

import gradio as gr
import random
from huggingface_hub import InferenceClient



# ===== LOAD & PROCESS YOUR NEW CONTENT =====
from sentence_transformers import SentenceTransformer
import torch


# ===== APPLY THE COMPLETE WORKFLOW =====
# Open the water_cycle.txt file in read mode with UTF-8 encoding
with open("rrights.txt", "r", encoding="utf-8") as file:
  # Read the entire contents of the file and store it in a variable
  rrights_text = file.read()

# Print the text below
print(rrights_text)

# ===== EXPERIMENT & VERIFY =====

def preprocess_text(text):
  # Strip extra whitespace from the beginning and the end of the text
  cleaned_text = text.strip()

  # Split the cleaned_text by every newline character (\n)
  chunks = cleaned_text.split(".")

  # Create an empty list to store cleaned chunks
  cleaned_chunks = []

  # Write your for-in loop below to clean each chunk and add it to the cleaned_chunks list
  for chunk in chunks:
    stripped_chunk = chunk.strip()
    cleaned_chunks.append(stripped_chunk)


  # Print cleaned_chunks
  print(cleaned_chunks)


  # Print the length of cleaned_chunks
  print(len(cleaned_chunks))


  # Return the cleaned_chunks
  return cleaned_chunks

# Call the preprocess_text function and store the result in a cleaned_chunks variable
cleaned_chunks = preprocess_text(rrights_text) # Complete this line

# Load the pre-trained embedding model that converts text to vectors
model = SentenceTransformer('all-MiniLM-L6-v2')

def create_embeddings(text_chunks):
  # Convert each text chunk into a vector embedding and store as a tensor
  chunk_embeddings = model.encode(cleaned_chunks, convert_to_tensor=True) # Replace ... with the text_chunks list

  # Print the chunk embeddings
  print(chunk_embeddings)


  # Print the shape of chunk_embeddings
  print(chunk_embeddings.shape)


  # Return the chunk_embeddings
  return chunk_embeddings

# Call the create_embeddings function and store the result in a new chunk_embeddings variable
chunk_embeddings = create_embeddings(cleaned_chunks) # Complete this line


# Define a function to find the most relevant text chunks for a given query, chunk_embeddings, and text_chunks
def get_top_chunks(query, chunk_embeddings, text_chunks):
  # Convert the query text into a vector embedding
  query_embedding = model.encode(query, convert_to_tensor=True) # Complete this line

  # Normalize the query embedding to unit length for accurate similarity comparison
  query_embedding_normalized = query_embedding / query_embedding.norm()

  # Normalize all chunk embeddings to unit length for consistent comparison
  chunk_embeddings_normalized = chunk_embeddings / chunk_embeddings.norm(dim=1, keepdim=True)

  # Calculate cosine similarity between query and all chunks using matrix multiplication
  similarities = torch.matmul(chunk_embeddings_normalized,query_embedding_normalized) # Complete this line

  # Print the similarities
  print(similarities)

  # Find the indices of the 3 chunks with highest similarity scores
  top_indices  = torch.topk(similarities, k=5).indices

  # Print the top indices
  print(top_indices)


  # Create an empty list to store the most relevant chunks
  top_chunks = []

  # Loop through the top indices and retrieve the corresponding text chunks
  for i in top_indices:
    relevant_info = cleaned_chunks[i]
    top_chunks.append(relevant_info)


  # Return the list of most relevant chunks
  return top_chunks




client = InferenceClient('Qwen/Qwen2.5-72B-Instruct')

 

def respond(message, history):
    # Call the get_top_chunks function with the original query
    top_results = get_top_chunks(message, chunk_embeddings, cleaned_chunks) # Complete this line

# Print the top results
    print(top_results)

    messages = [{"role": "system", "content": f"You are a friendly chatbot. You give people information about ways to get involved in different social causes. Base your response on the following information {top_results}"}]

    if history:
        messages.extend(history)

    messages.append({"role": "user", "content": message})

    response = client.chat_completion(messages, max_tokens = 500)

    return response['choices'][0]['message']['content'].strip()

 
#chatbot = gr.ChatInterface(respond, type="messages")


    #gr.Markdown("P2A", elem_id="title")
    #gr.Image("chatbot_logo.png", width=100)
spotify_embed_code = """<iframe data-testid="embed-iframe" style="border-radius:12px" src="https://open.spotify.com/embed/playlist/7eWlClzmwXPwvAjxPJYn7Q?utm_source=generator" width="100%" height="352" frameBorder="0" allowfullscreen="" allow="autoplay; clipboard-write; encrypted-media; fullscreen; picture-in-picture" loading="lazy"></iframe>
    """
    
theme = gr.themes.Base(
    primary_hue="pink",
    secondary_hue="indigo",
    neutral_hue="rose",
    font=['Montserrat', 'ui-sans-serif', 'system-ui', 'sans-serif'],
).set(
    background_fill_primary='*neutral_50',
    shadow_drop='0 1px 4px 0 rgb(0 0 0 / 0.1)',
    shadow_drop_lg='0 2px 5px 0 rgb(0 0 0 / 0.1)',
    shadow_spread='6px',
    block_background_fill='white',
    block_border_width='0px',
    block_border_width_dark='0px',
    block_label_background_fill='*primary_100',
    block_label_background_fill_dark='*primary_600',
    block_label_text_color='*primary_500',
    block_label_text_color_dark='white',
    block_label_margin='*spacing_md',
    block_label_padding='*spacing_sm *spacing_md',
    block_label_radius='*radius_md',
    block_label_text_size='*text_md',
    block_label_text_weight='600',
    block_title_background_fill='*block_label_background_fill',
    block_title_background_fill_dark='*block_label_background_fill',
    block_title_text_color='*primary_500',
    block_title_text_color_dark='white',
    block_title_padding='*block_label_padding',
    block_title_radius='*block_label_radius',
    block_title_text_weight='600',
    panel_border_width='1px',
    panel_border_width_dark='1px',
    checkbox_background_color_selected='*primary_600',
    checkbox_background_color_selected_dark='*primary_700',
    checkbox_border_color='*neutral_100',
    checkbox_border_color_dark='*neutral_600',
    checkbox_border_color_focus='*primary_500',
    checkbox_border_color_focus_dark='*primary_600',
    checkbox_border_color_selected='*primary_600',
    checkbox_border_color_selected_dark='*primary_700',
    checkbox_border_width='1px',
    checkbox_shadow='none',
    checkbox_label_background_fill_selected='*primary_500',
    checkbox_label_background_fill_selected_dark='*primary_600',
    checkbox_label_shadow='*shadow_drop_lg',
    checkbox_label_text_color_selected='white',
    input_background_fill='white',
    input_border_color='*neutral_50',
    input_shadow='*shadow_drop',
    input_shadow_dark='*shadow_drop',
    input_shadow_focus='*shadow_drop_lg',
    input_shadow_focus_dark='*shadow_drop_lg',
    slider_color='*primary_500',
    slider_color_dark='*primary_600',
    button_primary_background_fill_hover='*primary_400',
    button_primary_background_fill_hover_dark='*primary_500',
    button_primary_shadow='*shadow_drop_lg',
    button_primary_shadow_hover='*shadow_drop_lg',
    button_primary_shadow_active='*shadow_inset',
    button_primary_shadow_dark='*shadow_drop_lg',
    button_secondary_background_fill='white',
    button_secondary_background_fill_hover='*neutral_100',
    button_secondary_background_fill_hover_dark='*primary_500',
    button_secondary_text_color='*neutral_800',
    button_secondary_shadow='*shadow_drop_lg',
    button_secondary_shadow_hover='*shadow_drop_lg',
    button_secondary_shadow_active='*shadow_inset',
    button_secondary_shadow_dark='*shadow_drop_lg'
)

with gr.Blocks(theme=theme) as demo:
    #gr.ChatInterface(respond, type="messages")


    with gr.Row():
        with gr.Column():
            gr.Image(value = "pta.jpg", show_label = False, show_share_button = False, show_download_button = False)

    title = "Passion to Action"
    topics = """
    We are dedicated to helping you pursue causes you care about! Ask us about any of the following, and we will give you ways to get involved!

    Ask me any of the following questions to get involved:
    "I am passionate about LGBTQIA+ rights. What can I do to get involved?"
    "I care deeply about reproductive rights. Are there places I can donate?"
    "I want to help end educational funding disparities. Where can I start?"
    "I care very much about immigration rights. What can I do to help?"
    
    """

    with gr.TabItem("Passion to Action"):
            with gr.Column():
                gr.Markdown(topics) #saying topics not defined 
                gr.ChatInterface(
                    fn = respond,
                    type = "messages",
                    examples = [
                        "I am passionate about LGBTQIA+ rights. What can I do to get involved?",
                        "I care deeply about reproductive rights. Are there places I can donate?",
                        "I want to help end educational funding disparities. Where can I start?",
                        "I care very much about immigration rights. What can I do to help?",
                    ] 
                )
            with gr.Row(scale = 1):
                gr.Markdown("### Enjoy Passion 2 Action's favorite songs!")
                
            with gr.Row(scale = 1):
                gr.HTML(spotify_embed_code)

            




demo.launch()