app.py

import gradio as gr
from huggingface_hub import InferenceClient
from app.services.embedding_service import EmbeddingService
from app.config import EMBEDDING_MODEL  # Import from config
from app.services.preprocessor import TextPreprocessor

"""
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")

# Initialize EmbeddingService
embedding_service = EmbeddingService(model_name=EMBEDDING_MODEL, preprocessor=TextPreprocessor())


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

def get_embedding(text: str) -> list[float]:
    """
    Endpoint to get the embedding of a text.
    """
    try:
        return embedding_service.get_embedding(text)
    except ValueError as e:
        # Handle the case where the input text is too long
        return f"Error: {str(e)}"
    except Exception as e:
        return f"Error: {str(e)}"

# Create a separate Gradio interface for the embedding endpoint
embedding_iface = gr.Interface(
    fn=get_embedding,
    inputs=gr.Textbox(placeholder="Enter text here...", label="Input Text"),
    outputs=gr.JSON(label="Embedding"),  # Use JSON output for the embedding vector
    title="Embedding Service",
    description="Get the embedding of a text using the Vietnamese Bi-Encoder.",
)

"""
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)",
        ),
    ],
)

# Combine the interfaces
demo = gr.TabbedInterface([demo, embedding_iface], ["Chatbot", "Embedding"])


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