app.py

# app.py


# import pipelines
# import datasets
import os

if not os.getenv('HF_TOKEN'):
    raise ValueError('HF_TOKEN must be set')

from huggingface_hub import InferenceClient
import gradio as gr
from gradio import ChatMessage

MODEL = "meta-llama/Meta-Llama-3-8B-Instruct"
# PROMPT = "What is happiness?"
HF_TOKEN = os.getenv('HF_TOKEN')

client = InferenceClient(MODEL, token=HF_TOKEN)
# inputs = [{"role": "user", "content": PROMPT}]
# output = client.chat_completion(messages, max_tokens=100)

# print(output.choices[0].message.content)
# print(output.model)

def interact_with_agent(prompt, messages):
    messages.append(ChatMessage(role="user", content=prompt))
    yield messages
    # for msg in stream_from_transformers_agent(agent, prompt):
    for msg in client.chat_completion(messages, max_tokens=100):
        messages.append(msg)
        yield messages
    yield messages

with gr.Blocks() as demo:
    chatbot = gr.Chatbot()
    text_input = gr.Textbox(lines=1, label="Chat Message")
    text_input.submit(interact_with_agent, [text_input, chatbot], [chatbot])
    
if __name__ == "__main__":
    demo.launch()