langchain/docs/docs/integrations/chat/tongyi.ipynb

{
 "cells": [
  {
   "cell_type": "raw",
   "metadata": {},
   "source": [
    "---\n",
    "sidebar_label: Tongyi Qwen\n",
    "---"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {
    "collapsed": false,
    "jupyter": {
     "outputs_hidden": false
    }
   },
   "source": [
    "# ChatTongyi\n",
    "Tongyi Qwen is a large language model developed by Alibaba's Damo Academy. It is capable of understanding user intent through natural language understanding and semantic analysis, based on user input in natural language. It provides services and assistance to users in different domains and tasks. By providing clear and detailed instructions, you can obtain results that better align with your expectations.\n",
    "In this notebook, we will introduce how to use langchain with [Tongyi](https://www.aliyun.com/product/dashscope) mainly in `Chat` corresponding\n",
    " to the package `langchain/chat_models` in langchain"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {
    "collapsed": false,
    "jupyter": {
     "outputs_hidden": false
    }
   },
   "outputs": [],
   "source": [
    "# Install the package\n",
    "%pip install --upgrade --quiet  dashscope"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 2,
   "metadata": {
    "collapsed": false,
    "jupyter": {
     "outputs_hidden": false
    }
   },
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      " ········\n"
     ]
    }
   ],
   "source": [
    "# Get a new token: https://help.aliyun.com/document_detail/611472.html?spm=a2c4g.2399481.0.0\n",
    "from getpass import getpass\n",
    "\n",
    "DASHSCOPE_API_KEY = getpass()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 3,
   "metadata": {
    "collapsed": false,
    "jupyter": {
     "outputs_hidden": false
    }
   },
   "outputs": [],
   "source": [
    "import os\n",
    "\n",
    "os.environ[\"DASHSCOPE_API_KEY\"] = DASHSCOPE_API_KEY"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 4,
   "metadata": {
    "collapsed": false,
    "jupyter": {
     "outputs_hidden": false
    }
   },
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "chat resp: content='Hello! How' additional_kwargs={} example=False\n",
      "chat resp: content=' can I assist you today?' additional_kwargs={} example=False\n"
     ]
    }
   ],
   "source": [
    "from langchain_community.chat_models.tongyi import ChatTongyi\n",
    "from langchain_core.messages import HumanMessage\n",
    "\n",
    "chatLLM = ChatTongyi(\n",
    "    streaming=True,\n",
    ")\n",
    "res = chatLLM.stream([HumanMessage(content=\"hi\")], streaming=True)\n",
    "for r in res:\n",
    "    print(\"chat resp:\", r)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 5,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "AIMessageChunk(content=\"J'aime programmer.\", additional_kwargs={}, example=False)"
      ]
     },
     "execution_count": 5,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "from langchain_core.messages import HumanMessage, SystemMessage\n",
    "\n",
    "messages = [\n",
    "    SystemMessage(\n",
    "        content=\"You are a helpful assistant that translates English to French.\"\n",
    "    ),\n",
    "    HumanMessage(\n",
    "        content=\"Translate this sentence from English to French. I love programming.\"\n",
    "    ),\n",
    "]\n",
    "chatLLM(messages)"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## Tool Calling\n",
    "ChatTongyi supports tool calling API that lets you describe tools and their arguments, and have the model return a JSON object with a tool to invoke and the inputs to that tool."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 5,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "AIMessage(content='', additional_kwargs={'tool_calls': [{'function': {'name': 'get_current_weather', 'arguments': '{\"location\": \"San Francisco\"}'}, 'id': '', 'type': 'function'}]}, response_metadata={'model_name': 'qwen-turbo', 'finish_reason': 'tool_calls', 'request_id': 'dae79197-8780-9b7e-8c15-6a83e2a53534', 'token_usage': {'input_tokens': 229, 'output_tokens': 19, 'total_tokens': 248}}, id='run-9e06f837-582b-473b-bb1f-5e99a68ecc10-0', tool_calls=[{'name': 'get_current_weather', 'args': {'location': 'San Francisco'}, 'id': ''}])"
      ]
     },
     "execution_count": 5,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "from langchain_community.chat_models.tongyi import ChatTongyi\n",
    "from langchain_core.messages import HumanMessage, SystemMessage\n",
    "\n",
    "tools = [\n",
    "    {\n",
    "        \"type\": \"function\",\n",
    "        \"function\": {\n",
    "            \"name\": \"get_current_time\",\n",
    "            \"description\": \"当你想知道现在的时间时非常有用。\",\n",
    "            \"parameters\": {},\n",
    "        },\n",
    "    },\n",
    "    {\n",
    "        \"type\": \"function\",\n",
    "        \"function\": {\n",
    "            \"name\": \"get_current_weather\",\n",
    "            \"description\": \"当你想查询指定城市的天气时非常有用。\",\n",
    "            \"parameters\": {\n",
    "                \"type\": \"object\",\n",
    "                \"properties\": {\n",
    "                    \"location\": {\n",
    "                        \"type\": \"string\",\n",
    "                        \"description\": \"城市或县区，比如北京市、杭州市、余杭区等。\",\n",
    "                    }\n",
    "                },\n",
    "            },\n",
    "            \"required\": [\"location\"],\n",
    "        },\n",
    "    },\n",
    "]\n",
    "\n",
    "messages = [\n",
    "    SystemMessage(content=\"You are a helpful assistant.\"),\n",
    "    HumanMessage(content=\"What is the weather like in San Francisco?\"),\n",
    "]\n",
    "chatLLM = ChatTongyi()\n",
    "llm_kwargs = {\"tools\": tools, \"result_format\": \"message\"}\n",
    "ai_message = chatLLM.bind(**llm_kwargs).invoke(messages)\n",
    "ai_message"
   ]
  }
 ],
 "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
}