import os import gradio as gr from huggingface_hub import InferenceClient from huggingface_hub.utils import HfHubHTTPError from dotenv import load_dotenv # Load environment variables from .env file in parent directory env_path = os.path.join(os.path.dirname(os.path.dirname(__file__)), '.env') load_dotenv(dotenv_path=env_path) api_token = os.getenv("HUGGINGFACE_API_TOKEN") if not api_token: raise ValueError("HUGGINGFACE_API_TOKEN environment variable not set. Please check your .env file.") client = InferenceClient("HuggingFaceH4/zephyr-7b-beta", token=api_token) def respond(message, history, 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 = "" try: for message in client.chat_completion( messages, max_tokens=max_tokens, stream=True, temperature=temperature, top_p=top_p, ): if hasattr(message.choices[0], 'delta') and hasattr(message.choices[0].delta, 'content'): token = message.choices[0].delta.content response += token yield response except Exception as e: yield f"Error: {str(e)}" # Create the Gradio interface demo = gr.ChatInterface( fn=respond, title="E-commerce Chatbot", description="Ask me anything about products!", examples=["Tell me about gaming laptops", "What are the best smartphones?"], additional_inputs=[ gr.Textbox(value="You are a friendly E-commerce assistant.", 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") ] ) if __name__ == "__main__": try: demo.launch(server_name="0.0.0.0", server_port=8000, share=True) except Exception as e: print(f"Error launching the demo: {e}")