import gradio as gr
from huggingface_hub import InferenceClient, login
from langchain_community.vectorstores import FAISS
from langchain_huggingface import HuggingFaceEmbeddings
import os


"""
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
"""
login(token=os.getenv('TOKEN'))
client = InferenceClient("meta-llama/Llama-3.2-1B-Instruct")
#client = InferenceClient("mistralai/Mistral-7B-Instruct-v0.3")

folder = snapshot_download(repo_id="umaiku/faiss_index", repo_type="dataset", local_dir=os.getcwd())

embeddings = HuggingFaceEmbeddings(model_name="intfloat/multilingual-e5-small")

vector_db = FAISS.load_local("faiss_index", embeddings, allow_dangerous_deserialization=True)
retriever = vector_db.as_retriever()


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="An Expert in Legal advice.", 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)",
        ),
    ],
    description="# 📜 Legal AI RAG Chatbot",
)


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