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 = """ """ 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()