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

{
 "cells": [
  {
   "cell_type": "markdown",
   "id": "3ddface67cd10a87",
   "metadata": {
    "collapsed": false
   },
   "source": [
    "# SparkLLM Chat\n",
    "\n",
    "SparkLLM chat models API by iFlyTek. For more information, see [iFlyTek Open Platform](https://www.xfyun.cn/)."
   ]
  },
  {
   "cell_type": "markdown",
   "id": "b895d98989d4de01",
   "metadata": {},
   "source": [
    "## Basic use"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 10,
   "id": "43daa39972d4c533",
   "metadata": {
    "ExecuteTime": {
     "end_time": "2024-02-17T07:55:44.526904Z",
     "start_time": "2024-02-17T07:55:43.166698Z"
    },
    "collapsed": false
   },
   "outputs": [
    {
     "data": {
      "text/plain": "AIMessage(content='Hello! How can I help you today?')"
     },
     "execution_count": 10,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "\"\"\"For basic init and call\"\"\"\n",
    "from langchain_community.chat_models import ChatSparkLLM\n",
    "from langchain_core.messages import HumanMessage\n",
    "\n",
    "chat = ChatSparkLLM(\n",
    "    spark_app_id=\"<app_id>\", spark_api_key=\"<api_key>\", spark_api_secret=\"<api_secret>\"\n",
    ")\n",
    "message = HumanMessage(content=\"Hello\")\n",
    "chat([message])"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "df755f4c5689510",
   "metadata": {
    "collapsed": false
   },
   "source": [
    "- Get SparkLLM's app_id, api_key and api_secret from [iFlyTek SparkLLM API Console](https://console.xfyun.cn/services/bm3) (for more info, see [iFlyTek SparkLLM Intro](https://xinghuo.xfyun.cn/sparkapi) ), then set environment variables `IFLYTEK_SPARK_APP_ID`, `IFLYTEK_SPARK_API_KEY` and `IFLYTEK_SPARK_API_SECRET` or pass parameters when creating `ChatSparkLLM` as the demo above."
   ]
  },
  {
   "cell_type": "markdown",
   "id": "984e32ee47bc6772",
   "metadata": {
    "collapsed": false
   },
   "source": [
    "## For ChatSparkLLM with Streaming"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 13,
   "id": "7dc162bd65fec08f",
   "metadata": {
    "collapsed": false
   },
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Hello! How can I help you today?"
     ]
    }
   ],
   "source": [
    "chat = ChatSparkLLM(\n",
    "    spark_app_id=\"<app_id>\",\n",
    "    spark_api_key=\"<api_key>\",\n",
    "    spark_api_secret=\"<api_secret>\",\n",
    "    streaming=True,\n",
    ")\n",
    "for chunk in chat.stream(\"Hello!\"):\n",
    "    print(chunk.content, end=\"\")"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "566c85e0",
   "metadata": {},
   "source": [
    "## For v2"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "3103ebdf",
   "metadata": {},
   "outputs": [],
   "source": [
    "\"\"\"For basic init and call\"\"\"\n",
    "from langchain_community.chat_models import ChatSparkLLM\n",
    "from langchain_core.messages import HumanMessage\n",
    "\n",
    "chat = ChatSparkLLM(\n",
    "    spark_app_id=\"<app_id>\",\n",
    "    spark_api_key=\"<api_key>\",\n",
    "    spark_api_secret=\"<api_secret>\",\n",
    "    spark_api_url=\"wss://spark-api.xf-yun.com/v2.1/chat\",\n",
    "    spark_llm_domain=\"generalv2\",\n",
    ")\n",
    "message = HumanMessage(content=\"Hello\")\n",
    "chat([message])"
   ]
  }
 ],
 "metadata": {
  "kernelspec": {
   "display_name": "Python 3",
   "language": "python",
   "name": "python3"
  },
  "language_info": {
   "codemirror_mode": {
    "name": "ipython",
    "version": 2
   },
   "file_extension": ".py",
   "mimetype": "text/x-python",
   "name": "python",
   "nbconvert_exporter": "python",
   "pygments_lexer": "ipython2",
   "version": "2.7.6"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 5
}