{
 "cells": [
  {
   "cell_type": "code",
   "execution_count": 1,
   "id": "6797ba2e-ef94-42d6-9e64-a1559b507173",
   "metadata": {},
   "outputs": [
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "C:\\Users\\singl\\anaconda3\\envs\\pshcy\\lib\\site-packages\\tqdm\\auto.py:21: TqdmWarning: IProgress not found. Please update jupyter and ipywidgets. See https://ipywidgets.readthedocs.io/en/stable/user_install.html\n",
      "  from .autonotebook import tqdm as notebook_tqdm\n"
     ]
    }
   ],
   "source": [
    "import gradio as gr\n",
    "from huggingface_hub import InferenceClient\n",
    "\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "f50cbd8a-777f-440c-8b7f-8eca9e611e12",
   "metadata": {},
   "outputs": [],
   "source": [
    "\"\"\"\n",
    "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\n",
    "\"\"\"\n",
    "client = InferenceClient(\"HuggingFaceH4/zephyr-7b-beta\")\n",
    "\n",
    "\n",
    "def respond(\n",
    "    message,\n",
    "    history: list[tuple[str, str]],\n",
    "    system_message,\n",
    "    max_tokens,\n",
    "    temperature,\n",
    "    top_p,\n",
    "):\n",
    "    messages = [{\"role\": \"system\", \"content\": system_message}]\n",
    "\n",
    "    for val in history:\n",
    "        if val[0]:\n",
    "            messages.append({\"role\": \"user\", \"content\": val[0]})\n",
    "        if val[1]:\n",
    "            messages.append({\"role\": \"assistant\", \"content\": val[1]})\n",
    "\n",
    "    messages.append({\"role\": \"user\", \"content\": message})\n",
    "\n",
    "    response = \"\"\n",
    "\n",
    "    for message in client.chat_completion(\n",
    "        messages,\n",
    "        max_tokens=max_tokens,\n",
    "        stream=True,\n",
    "        temperature=temperature,\n",
    "        top_p=top_p,\n",
    "    ):\n",
    "        token = message.choices[0].delta.content\n",
    "\n",
    "        response += token\n",
    "        yield response\n",
    "\n",
    "\n",
    "\"\"\"\n",
    "For information on how to customize the ChatInterface, peruse the gradio docs: https://www.gradio.app/docs/chatinterface\n",
    "\"\"\"\n",
    "demo = gr.ChatInterface(\n",
    "    respond,\n",
    "    additional_inputs=[\n",
    "        gr.Textbox(value=\"You are a friendly Chatbot.\", label=\"System message\"),\n",
    "        gr.Slider(minimum=1, maximum=2048, value=512, step=1, label=\"Max new tokens\"),\n",
    "        gr.Slider(minimum=0.1, maximum=4.0, value=0.7, step=0.1, label=\"Temperature\"),\n",
    "        gr.Slider(\n",
    "            minimum=0.1,\n",
    "            maximum=1.0,\n",
    "            value=0.95,\n",
    "            step=0.05,\n",
    "            label=\"Top-p (nucleus sampling)\",\n",
    "        ),\n",
    "    ],\n",
    ")\n",
    "\n",
    "\n",
    "if __name__ == \"__main__\":\n",
    "    demo.launch()\n"
   ]
  }
 ],
 "metadata": {
  "kernelspec": {
   "display_name": "Python (Psych)",
   "language": "python",
   "name": "pshcy"
  },
  "language_info": {
   "codemirror_mode": {
    "name": "ipython",
    "version": 3
   },
   "file_extension": ".py",
   "mimetype": "text/x-python",
   "name": "python",
   "nbconvert_exporter": "python",
   "pygments_lexer": "ipython3",
   "version": "3.10.18"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 5
}