import gradio as gr from sentence_transformers import SentenceTransformer, util import openai import os import matplotlib.pyplot as plt from matplotlib import font_manager 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 game chatbot specialized in recommending video games based on genre, what they are about, and price." # 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 video game reccomendations. """ try: user_message = f"Here's the information on this game: {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=400, 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 Plai! Ask me for any game recommendations." 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 = """ 🎮 Welcome to Plai! Your AI-driven assistant for all videogame related queries. Created by Perennial, Jiya, and Ly-Ly of the 2024 Kode With Klossy San Francisco Camp. """ topics = """ ### Feel Free to ask for recommendations based on: 🕹️ Genre 🕹️ Affordability 🕹️ Feeling """ theme = gr.themes.Base().set( background_fill_primary='#FAB9CB', # Light pink background background_fill_primary_dark='#AB4E68', # Light pink background background_fill_secondary='#AB4E68', # Light orange background background_fill_secondary_dark='#AB4E68', # Dark orange background border_color_accent='#FFF2F1', # Accent border color border_color_accent_dark='#AB4E68', # Dark accent border color border_color_accent_subdued='#AB4E68', # Subdued accent border color border_color_primary='#AB4E68', # Primary border color block_border_color='#FFF2F1', # Block border color button_primary_background_fill='#AB4E68', # Primary button background color button_primary_background_fill_dark='#AB4E68', # Dark primary button background color ) # Setup the Gradio Blocks interface with custom layout components with gr.Blocks(theme=theme) as demo: gr.Image("Video Game Banner.gif", show_label = False, show_share_button = False, show_download_button = False) 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 gr.Image("Internet_pop-up-removebg-preview (1).png", show_label = False, show_share_button = False, show_download_button = False) with gr.Row(): with gr.Column(): question = gr.Textbox(label="Your question", placeholder="What do you want to ask about?") answer = gr.Textbox(label="Plai Response", placeholder="Plai will respond here...", interactive=False, lines=10) submit_button = gr.Button("Submit") submit_button.click(fn=query_model, inputs=question, outputs=answer) # Launch the Gradio app to allow user interaction demo.launch(share=True)