app.py

import gradio as gr
from huggingface_hub import InferenceClient

"""
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("meta-llama/Meta-Llama-3.1-8B-Instruct")
client = InferenceClient("HuggingFaceH4/zephyr-7b-beta")


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="Act as a Prompt Enhancer AI that takes user-input prompts and transforms them into more engaging, detailed, and thought-provoking questions. Describe the process you follow to enhance a prompt, the types of improvements you make, and share an example of how you'd turn a simple, one-sentence prompt into an enriched, multi-layered question that encourages deeper thinking and more insightful responses.", label="System message", visible=False),
        gr.Slider(minimum=1, maximum=2048, value=2048, 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__":
    demo.launch()
#####################################
# import gradio as gr

# gr.load("models/meta-llama/Meta-Llama-3.1-70B-Instruct").launch()
########################################
# from openai import OpenAI
# import streamlit as st
# import os
# import sys
# from dotenv import load_dotenv, dotenv_values
# load_dotenv()

# st.title("ChatGPT-like clone")

# client = OpenAI(api_key=os.environ.get["OPENAI_API_KEY"])

# if "openai_model" not in st.session_state:
#     st.session_state["openai_model"] = "gpt-3.5-turbo"

# if "messages" not in st.session_state:
#     st.session_state.messages = []

# for message in st.session_state.messages:
#     with st.chat_message(message["role"]):
#         st.markdown(message["content"])

# if prompt := st.chat_input("What is up?"):
#     st.session_state.messages.append({"role": "user", "content": prompt})
#     with st.chat_message("user"):
#         st.markdown(prompt)

#     with st.chat_message("assistant"):
#         stream = client.chat.completions.create(
#             model=st.session_state["openai_model"],
#             messages=[
#                 {"role": m["role"], "content": m["content"]}
#                 for m in st.session_state.messages
#             ],
#             stream=True,
#         )
#         response = st.write_stream(stream)
#     st.session_state.messages.append({"role": "assistant", "content": response})