Spaces:
Sleeping
Sleeping
| import gradio as gr | |
| from sentence_transformers import SentenceTransformer, util | |
| import openai | |
| import os | |
| HF_TOKEN = os.getenv('HF_TOKEN') | |
| hf_writer =gr.HuggingFaceDatasetSaver(HF_TOKEN, "kellydoesstuff/RotBot_Flags") | |
| os.environ["TOKENIZERS_PARALLELISM"] = "false" | |
| # Initialize paths and model identifiers for easy configuration and maintenance | |
| filename = "output_chess_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"] | |
| # 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 chess information. | |
| """ | |
| try: | |
| # system_message = "You are a chess chatbot specialized in providing information on chess rules, strategies, and terminology." | |
| system_message = "You are a chatbot that is specialized in translating Gen-Z/Gen-Alpha slang into standard English. In addition to translation, you are knowledgable on synonyms and origins of slang words. You not only act as a dictionary/thesaurus for slang words, you can translate sentences with slang words into standard Englsih." | |
| # system_message = """ You are a chatbot that translates slang English, I'm talking sentences with words like rizz and gyatt, into professional standard English. | |
| # We want a translation that sounds like a sentence from a LinkedIn post. You translate sentences with multiple slang words into sentences with comprehensible standard English. | |
| # Not only that, you are also knowledgeable on definitions, synonyms, and origins of slang words if prompted. | |
| # So,if someone asks you to translate a sentence into standard English like, 'What does the sentence She has the biggest gyatt on god! mean?', you would respond with 'This sentence translates to she has the biggest butt I swear to god!' | |
| # Or, if someone asks you to translate the sentence 'What the sigma! She just ghosted me!', you would translate that to 'What the hell! She is ignoring me!' | |
| # If the output is inappropriate warn the user. DO NOT RESPOND WITH THE SAME TEXT PASSED TO YOU. YOU ARE A TRANSLATOR NOT A CONVERSATIONALIST. | |
| # """ | |
| user_message = f"Here's the question the user inputted: {relevant_segment}" | |
| messages = [ | |
| {"role": "system", "content": system_message}, | |
| {"role": "user", "content": user_message} | |
| ] | |
| response = openai.ChatCompletion.create( | |
| model="gpt-4o", | |
| messages=messages, | |
| max_tokens=200, | |
| temperature=0.2, | |
| top_p=1, | |
| frequency_penalty=0, | |
| presence_penalty=0 | |
| ) | |
| return response['choices'][0]['message']['content'].strip() | |
| except Exception as e: | |
| print(f"Error in generating response: {e}") | |
| return f"Error in generating response: {e}" | |
| def query_model(question, history): | |
| """ | |
| Process a question, find relevant information, and generate a response. | |
| """ | |
| # global question_g | |
| # question_g = question | |
| if question == "": | |
| return "What the sigma! You didn't ask a question. Feel free to ask me anything about the topics listed above." | |
| relevant_segment = find_relevant_segment(question, segments) | |
| if not relevant_segment: | |
| return "Unfortunately I cannot answer your question..😔 Try refining your question so I can try again." | |
| # global response_g | |
| 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 RotBot! | |
| ## Your AI assistant for translating slang into standard English! | |
| """ | |
| topics = """ | |
| ### Feel Free to ask me anything from the topics below! | |
| - Translating slang sentences into standard English | |
| - Defining slang into standard English | |
| - Providing standard English synonyms for slang | |
| """ | |
| # callback = gr.CSVLogger() | |
| # Setup the Gradio Blocks interface with custom layout components | |
| with gr.Blocks(theme='gradio/soft') as demo: | |
| 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="RotBot Response", placeholder="RotBot will respond here...", interactive=False, lines=10) | |
| # submit_button = gr.Button("Submit") | |
| # submit_button.click(fn=query_model, inputs=question, outputs=answer) | |
| # chatbot = gr.ChatInterface( | |
| # fn=query_model, | |
| # examples=["Help me translate this sentence into standard English: Stop glazing him! He isn't even that good. ", "What's a synonym for rizz?", "What is the definition of gyatt?"], | |
| # multimodal=False, | |
| # ) | |
| # with gr.Row(): | |
| # flag_btn = gr.Button("Flag") | |
| # callback.setup([chatbot], "flagged_data_points") | |
| # flag_btn.click(lambda *args: callback.flag(args), [chatbot], None, preprocess=False) | |
| chatbot = gr.Interface( | |
| fn=query_model, | |
| inputs=gr.Textbox(label="Your question", placeholder="What do you want to ask about?"), | |
| outputs=gr.Textbox(label="RotBot Response", placeholder="RotBot will respond here...", interactive=False, lines=10, show_copy_button = True | |
| ), | |
| # outputs = gr.Markdown(label="RotBot Response"), | |
| theme='gradio/soft', | |
| examples=[ | |
| ["Help me translate this sentence into standard English: Stop glazing him! He isn't even that good."], | |
| ["What's a synonym for rizz?"], | |
| ["What is the definition of gyatt?"] | |
| ], | |
| allow_flagging="manual", | |
| # flagging_dir = "flag", | |
| flagging_options=["Ambiguous", "Wrong", "Other"], | |
| flagging_callback=hf_writer | |
| # show_copy_button = True | |
| ) | |
| # Launch the Gradio app to allow user interaction | |
| demo.launch(share=True) | |