langchain/docs/docs/integrations/chat/alibaba_cloud_pai_eas.ipynb

{
 "cells": [
  {
   "cell_type": "raw",
   "metadata": {},
   "source": [
    "---\n",
    "sidebar_label: Alibaba Cloud PAI EAS\n",
    "---"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "# Alibaba Cloud PAI EAS\n",
    "\n",
    ">[Alibaba Cloud PAI (Platform for AI)](https://www.alibabacloud.com/help/en/pai/?spm=a2c63.p38356.0.0.c26a426ckrxUwZ) is a lightweight and cost-efficient machine learning platform that uses cloud-native technologies. It provides you with an end-to-end modelling service. It accelerates model training based on tens of billions of features and hundreds of billions of samples in more than 100 scenarios.\n",
    "\n",
    ">[Machine Learning Platform for AI of Alibaba Cloud](https://www.alibabacloud.com/help/en/machine-learning-platform-for-ai/latest/what-is-machine-learning-pai) is a machine learning or deep learning engineering platform intended for enterprises and developers. It provides easy-to-use, cost-effective, high-performance, and easy-to-scale plug-ins that can be applied to various industry scenarios. With over 140 built-in optimization algorithms, `Machine Learning Platform for AI` provides whole-process AI engineering capabilities including data labelling (`PAI-iTAG`), model building (`PAI-Designer` and `PAI-DSW`), model training (`PAI-DLC`), compilation optimization, and inference deployment (`PAI-EAS`).\n",
    ">\n",
    ">`PAI-EAS` supports different types of hardware resources, including CPUs and GPUs, and features high throughput and low latency. It allows you to deploy large-scale complex models with a few clicks and perform elastic scale-ins and scale-outs in real-time. It also provides a comprehensive O&M and monitoring system."
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## Setup EAS Service\n",
    "\n",
    "Set up environment variables to init EAS service URL and token.\n",
    "Use [this document](https://www.alibabacloud.com/help/en/pai/user-guide/service-deployment/) for more information.\n",
    "\n",
    "```bash\n",
    "export EAS_SERVICE_URL=XXX\n",
    "export EAS_SERVICE_TOKEN=XXX\n",
    "```\n",
    "Another option is to use this code:"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 9,
   "metadata": {},
   "outputs": [],
   "source": [
    "import os\n",
    "\n",
    "from langchain_community.chat_models import PaiEasChatEndpoint\n",
    "from langchain_core.language_models.chat_models import HumanMessage\n",
    "\n",
    "os.environ[\"EAS_SERVICE_URL\"] = \"Your_EAS_Service_URL\"\n",
    "os.environ[\"EAS_SERVICE_TOKEN\"] = \"Your_EAS_Service_Token\"\n",
    "chat = PaiEasChatEndpoint(\n",
    "    eas_service_url=os.environ[\"EAS_SERVICE_URL\"],\n",
    "    eas_service_token=os.environ[\"EAS_SERVICE_TOKEN\"],\n",
    ")"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## Run Chat Model\n",
    "\n",
    "You can use the default settings to call EAS service as follows:"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "output = chat.invoke([HumanMessage(content=\"write a funny joke\")])\n",
    "print(\"output:\", output)"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "Or, call EAS service with new inference params:"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "kwargs = {\"temperature\": 0.8, \"top_p\": 0.8, \"top_k\": 5}\n",
    "output = chat.invoke([HumanMessage(content=\"write a funny joke\")], **kwargs)\n",
    "print(\"output:\", output)"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "Or, run a stream call to get a stream response:"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "outputs = chat.stream([HumanMessage(content=\"hi\")], streaming=True)\n",
    "for output in outputs:\n",
    "    print(\"stream output:\", output)"
   ]
  }
 ],
 "metadata": {
  "kernelspec": {
   "display_name": "Python 3 (ipykernel)",
   "language": "python",
   "name": "python3"
  },
  "language_info": {
   "codemirror_mode": {
    "name": "ipython",
    "version": 3
   },
   "file_extension": ".py",
   "mimetype": "text/x-python",
   "name": "python",
   "nbconvert_exporter": "python",
   "pygments_lexer": "ipython3",
   "version": "3.10.12"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 4
}