app.py

import gradio as gr
from huggingface_hub import InferenceClient
from langchain_community.chat_models import ChatOllama
from langchain_core.prompts import ChatPromptTemplate
from langchain_core.output_parsers import StrOutputParser
"""
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
"""
# client = InferenceClient("HuggingFaceH4/zephyr-7b-beta")


def respond(
    message,
    history: list[tuple[str, str]],
    system_message,
    max_tokens,
    temperature,
    top_p,
    model_name="llama3-8b",
    api_key=None
):
    client = ChatOllama(
        model=model_name,
        base_url="https://lintasmediadanawa-hf-llm-api.hf.space", 
        headers={"Authorization": f"Bearer {api_key}"},
        temperature=temperature,
        top_p=top_p,
        max_tokens=max_tokens
    )
    
    messages = [("system", system_message)]

    for val in history:
        if val[0]:
            # messages.append({"role": "user", "content": val[0]})
            messages.append(("human", val[0]))
        if val[1]:
            # messages.append({"role": "assistant", "content": val[1]})
            messages.append(("ai", val[1]))

    # messages.append({"role": "user", "content": message})
    messages.append(("user", message))

    chain = ChatPromptTemplate.from_messages(messages) | ChatOllama | StrOutputParser()
    return chain.invoke()
    # 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="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)",
        ),
        gr.Textbox(value="llama3-8b", label="Available Model Name, please refer to https://lintasmediadanawa-hf-llm-api.hf.space/api/tags"),
        gr.Textbox(value="hf_xxx", label="Huggingface API key")
    ],
)


if __name__ == "__main__":
    demo.launch()