import gradio as gr from openai import OpenAI import json import os import requests from pypdf import PdfReader import gradio as gr from huggingface_hub import InferenceClient from huggingface_hub import login """ For more information on `huggingface_hub` Inference API support, please check the docs: https://huggingface.co/docs/huggingface_hub/v0.22.2/en/guides/inference """ login(token=os.getenv("HF_TOKEN")) client = InferenceClient("HuggingFaceH4/zephyr-7b-beta") class Harold: def __init__(self): self.openai_client = OpenAI(api_key=os.getenv("OPENAI_API_KEY")) self.name = "Harold" reader = PdfReader("data/Living-Playbook.pdf") self.text = "" for page in reader.pages: text = page.extract_text() if text: self.text += text def system_prompt(self): system_prompt = f""" You are acting as {self.name}, a helpful assistant. You are answering questions and having discussions about the contents of the book "Living Playbook". Be friendly and approachable but also consise and to the point. If you don't know the answer, say so. You might be asked to explain a concept or idea in the book and describe a purpose of a game. You should be able to do this. """ system_prompt += f""" Here is the context of the book: {self.text} """ return system_prompt def chat(self, message, history): messages = [{"role": "system", "content": self.system_prompt()}] + history + [{"role": "user", "content": message}] response = self.openai_client.chat.completions.create( model="gpt-4o-mini", messages=messages, ) return response.choices[0].message.content def respond( message, history: list[tuple[str, str]], system_message, max_tokens, temperature, top_p, ): messages = [{"role": "system", "content": system_message}] for val in history: if val[0]: messages.append({"role": "user", "content": val[0]}) if val[1]: messages.append({"role": "assistant", "content": val[1]}) messages.append({"role": "user", "content": message}) response = "" for message in client.chat_completion( messages, max_tokens=max_tokens, stream=True, temperature=temperature, top_p=top_p, ): token = message.choices[0].delta.content response += token yield response """ For information on how to customize the ChatInterface, peruse the gradio docs: https://www.gradio.app/docs/chatinterface """ demo = gr.ChatInterface( respond, additional_inputs=[ gr.Textbox(value="Hello, You are a friendly Chatbot.", label="System message"), gr.Slider(minimum=1, maximum=2048, value=512, step=1, label="Max new tokens"), gr.Slider(minimum=0.1, maximum=4.0, value=0.7, step=0.1, label="Temperature"), gr.Slider( minimum=0.1, maximum=1.0, value=0.95, step=0.05, label="Top-p (nucleus sampling)", ), ], ) if __name__ == "__main__": harold = Harold() gr.ChatInterface(harold.chat, type="messages").launch()