app.py

import gradio as gr
from huggingface_hub import InferenceClient
from transformers import RagTokenizer, RagRetriever

"""
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")

# Load the RAG tokenizer and retriever
rag_tokenizer = RagTokenizer.from_pretrained("facebook/rag-sequence-nq")
rag_retriever = RagRetriever.from_pretrained(
    "facebook/rag-sequence-nq", index_name="apexcustoms.pdf", use_dummy_dataset=False
)

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,
        # Pass the RAG tokenizer and retriever to the client
        rag_tokenizer=rag_tokenizer,
        rag_retriever=rag_retriever,
    ):
        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 helpful car configuration assistant, specifically you are the assistant for Apex Customs (https://www.apexcustoms.com/). Given the user's input, provide suggestions for car models, colors, and customization options. Be creative and conversational in your responses. You should remember the user car model and tailor your answers accordingly. \n\nUser: ", 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)",
        ),
    ],
)


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