langchain/docs/versioned_docs/version-0.2.x/integrations/chat/ernie.ipynb

{
 "cells": [
  {
   "cell_type": "raw",
   "metadata": {},
   "source": [
    "---\n",
    "sidebar_label: Ernie Bot Chat\n",
    "---"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "# ErnieBotChat\n",
    "\n",
    "[ERNIE-Bot](https://cloud.baidu.com/doc/WENXINWORKSHOP/s/jlil56u11) is a large language model developed by Baidu, covering a huge amount of Chinese data.\n",
    "This notebook covers how to get started with ErnieBot chat models."
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "**Deprecated Warning**\n",
    "\n",
    "We recommend users using `langchain_community.chat_models.ErnieBotChat` \n",
    "to use `langchain_community.chat_models.QianfanChatEndpoint` instead.\n",
    "\n",
    "documentation for `QianfanChatEndpoint` is [here](/docs/integrations/chat/baidu_qianfan_endpoint/).\n",
    "\n",
    "they are 4 why we recommend users to use `QianfanChatEndpoint`:\n",
    "\n",
    "1. `QianfanChatEndpoint` support more LLM in the Qianfan platform.\n",
    "2. `QianfanChatEndpoint` support streaming mode.\n",
    "3. `QianfanChatEndpoint` support function calling usgage.\n",
    "4. `ErnieBotChat` is lack of maintenance and deprecated."
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "Some tips for migration:\n",
    "\n",
    "- change `ernie_client_id` to `qianfan_ak`, also change `ernie_client_secret` to `qianfan_sk`.\n",
    "- install `qianfan` package. like `pip install qianfan`\n",
    "- change `ErnieBotChat` to `QianfanChatEndpoint`."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "from langchain_community.chat_models.baidu_qianfan_endpoint import QianfanChatEndpoint\n",
    "\n",
    "chat = QianfanChatEndpoint(\n",
    "    qianfan_ak=\"your qianfan ak\",\n",
    "    qianfan_sk=\"your qianfan sk\",\n",
    ")"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## Usage"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 13,
   "metadata": {},
   "outputs": [],
   "source": [
    "from langchain_community.chat_models import ErnieBotChat\n",
    "from langchain_core.messages import HumanMessage\n",
    "\n",
    "chat = ErnieBotChat(\n",
    "    ernie_client_id=\"YOUR_CLIENT_ID\", ernie_client_secret=\"YOUR_CLIENT_SECRET\"\n",
    ")"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "or you can set `client_id` and `client_secret` in your environment variables\n",
    "```bash\n",
    "export ERNIE_CLIENT_ID=YOUR_CLIENT_ID\n",
    "export ERNIE_CLIENT_SECRET=YOUR_CLIENT_SECRET\n",
    "```"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 15,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "AIMessage(content='Hello, I am an artificial intelligence language model. My purpose is to help users answer questions or provide information. What can I do for you?', additional_kwargs={}, example=False)"
      ]
     },
     "execution_count": 15,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "chat([HumanMessage(content=\"hello there, who are you?\")])"
   ]
  }
 ],
 "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": "3.11.4"
  },
  "orig_nbformat": 4
 },
 "nbformat": 4,
 "nbformat_minor": 2
}