import gradio as gr
from huggingface_hub import InferenceClient
from langchain_community.chat_models import ChatOpenAI
from langchain.chains.retrieval_qa.base import RetrievalQA
from langchain_community.embeddings import OpenAIEmbeddings
from langchain.schema import HumanMessage, SystemMessage
import os
from langchain_community.document_loaders import DirectoryLoader
from langchain.text_splitter import CharacterTextSplitter
from langchain.embeddings.huggingface import HuggingFaceEmbeddings
from langchain_community.embeddings import OpenAIEmbeddings
from langchain_community.vectorstores import Chroma
import requests
from langchain_core.prompts import PromptTemplate

"""
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
"""
import gradio as gr
from openai import OpenAI
import os


TOKEN = os.getenv("HF_TOKEN")

client = OpenAI(
    base_url="https://api-inference.huggingface.co/v1/",
    api_key=TOKEN,
)

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.completions.create(
        model="Qwen/Qwen2-7B-Instruct",
        max_tokens=max_tokens,
        stream=True,
        temperature=temperature,
        top_p=top_p,
        messages=messages,
    ):
        token = message.choices[0].delta.content

        response += token
        yield response


chatbot = gr.Chatbot(height=600)

demo = gr.ChatInterface(
    respond,
    fill_height=True,
    chatbot=chatbot,
    additional_inputs=[
        gr.Textbox(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()