app.py

# You can find this code for Chainlit python streaming here (https://docs.chainlit.io/concepts/streaming/python)

# OpenAI Chat completion
import os
from openai import AsyncOpenAI  # importing openai for API usage
import chainlit as cl  # importing chainlit for our app
from chainlit.prompt import Prompt, PromptMessage  # importing prompt tools
from chainlit.playground.providers import ChatOpenAI  # importing ChatOpenAI tools
from dotenv import load_dotenv
import requests

load_dotenv()

prompt_template = """\
<|begin_of_text|><|start_header_id|>system<|end_header_id|>

Gen-Z-ify<|eot_id|><|start_header_id|>user<|end_header_id|>

{english}<|eot_id|><|start_header_id|>assistant<|end_header_id|>
"""

API_URL = "https://nc7q281oard1b1ar.us-east-1.aws.endpoints.huggingface.cloud"

@cl.on_message  # marks a function that should be run each time the chatbot receives a message from a user
async def main(message: cl.Message):
    headers = {
        "Accept" : "application/json",
        "Authorization": f"Bearer {os.environ['HF_TOKEN']}",
        "Content-Type": "application/json" 
    }

    def query(payload):
        response = requests.post(API_URL, headers=headers, json=payload)
        return response.json()
    
    formatted_prompt = prompt_template.format(english=message.content)

    print(formatted_prompt)

    output = query({
        "inputs": formatted_prompt,
        "parameters": {
            "return_full_text": False,
            "clean_up_tokenization_spaces": False
        }
    })

    msg = cl.Message(content=output[0]["generated_text"])

    # Send and close the message stream
    await msg.send()