跳到主要内容
Open In ColabOpen on GitHub

ChatTongyi

Tongyi Qwen 是由阿里巴巴达摩院开发的大型语言模型。它能够通过自然语言理解和语义分析来理解用户意图，基于用户以自然语言输入的内容。它在不同领域和任务中为用户提供服务和帮助。通过提供清晰而详细的指示，您可以获得更符合您期望的结果。在本笔记本中，我们将介绍如何在 langchain 中使用 Tongyi，主要是在 Chat 中，对应于 langchain 中的包 langchain/chat_models

# Install the package
%pip install --upgrade --quiet  dashscope
# Get a new token: https://help.aliyun.com/document_detail/611472.html?spm=a2c4g.2399481.0.0
from getpass import getpass

DASHSCOPE_API_KEY = getpass()
import os

os.environ["DASHSCOPE_API_KEY"] = DASHSCOPE_API_KEY
from langchain_community.chat_models.tongyi import ChatTongyi
from langchain_core.messages import HumanMessage

chatLLM = ChatTongyi(
    streaming=True,
)
res = chatLLM.stream([HumanMessage(content="hi")], streaming=True)
for r in res:
    print("chat resp:", r)
API 参考：ChatTongyi | HumanMessage
chat resp: content='Hello' id='run-f2301962-6d46-423c-8afa-1e667bd11e2b'
chat resp: content='!' id='run-f2301962-6d46-423c-8afa-1e667bd11e2b'
chat resp: content=' How' id='run-f2301962-6d46-423c-8afa-1e667bd11e2b'
chat resp: content=' can I assist you today' id='run-f2301962-6d46-423c-8afa-1e667bd11e2b'
chat resp: content='?' id='run-f2301962-6d46-423c-8afa-1e667bd11e2b'
chat resp: content='' response_metadata={'finish_reason': 'stop', 'request_id': '921db2c5-4d53-9a89-8e87-e4ad6a671237', 'token_usage': {'input_tokens': 20, 'output_tokens': 9, 'total_tokens': 29}} id='run-f2301962-6d46-423c-8afa-1e667bd11e2b'
from langchain_core.messages import HumanMessage, SystemMessage

messages = [
    SystemMessage(
        content="You are a helpful assistant that translates English to French."
    ),
    HumanMessage(
        content="Translate this sentence from English to French. I love programming."
    ),
]
chatLLM(messages)
/Users/cheese/PARA/Projects/langchain-contribution/langchain/libs/core/langchain_core/_api/deprecation.py:119: LangChainDeprecationWarning: The method `BaseChatModel.__call__` was deprecated in langchain-core 0.1.7 and will be removed in 0.2.0. Use invoke instead.
  warn_deprecated(
AIMessage(content="J'adore programmer.", response_metadata={'model_name': 'qwen-turbo', 'finish_reason': 'stop', 'request_id': 'ae725086-0ffa-9728-8c72-b204c7bc7eeb', 'token_usage': {'input_tokens': 36, 'output_tokens': 6, 'total_tokens': 42}}, id='run-060cc103-ef5f-4c8a-af40-792ac7f40c26-0')

工具调用​

ChatTongyi 支持工具调用 API，允许您描述工具及其参数，并让模型返回一个 JSON 对象，其中包含要调用的工具以及该工具的输入。

与 bind_tools 一起使用​

from langchain_community.chat_models.tongyi import ChatTongyi
from langchain_core.tools import tool


@tool
def multiply(first_int: int, second_int: int) -> int:
    """Multiply two integers together."""
    return first_int * second_int


llm = ChatTongyi(model="qwen-turbo")

llm_with_tools = llm.bind_tools([multiply])

msg = llm_with_tools.invoke("What's 5 times forty two")

print(msg)
API 参考：ChatTongyi | tool
content='' additional_kwargs={'tool_calls': [{'function': {'name': 'multiply', 'arguments': '{"first_int": 5, "second_int": 42}'}, 'id': '', 'type': 'function'}]} response_metadata={'model_name': 'qwen-turbo', 'finish_reason': 'tool_calls', 'request_id': '4acf0e36-44af-987a-a0c0-8b5c5eaa1a8b', 'token_usage': {'input_tokens': 200, 'output_tokens': 25, 'total_tokens': 225}} id='run-0ecd0f09-1d20-4e55-a4f3-f14d1f710ae7-0' tool_calls=[{'name': 'multiply', 'args': {'first_int': 5, 'second_int': 42}, 'id': ''}]

手动构建参数​

from langchain_community.chat_models.tongyi import ChatTongyi
from langchain_core.messages import HumanMessage, SystemMessage

tools = [
    {
        "type": "function",
        "function": {
            "name": "get_current_time",
            "description": "当你想知道现在的时间时非常有用。",
            "parameters": {},
        },
    },
    {
        "type": "function",
        "function": {
            "name": "get_current_weather",
            "description": "当你想查询指定城市的天气时非常有用。",
            "parameters": {
                "type": "object",
                "properties": {
                    "location": {
                        "type": "string",
                        "description": "城市或县区，比如北京市、杭州市、余杭区等。",
                    }
                },
            },
            "required": ["location"],
        },
    },
]

messages = [
    SystemMessage(content="You are a helpful assistant."),
    HumanMessage(content="What is the weather like in San Francisco?"),
]
chatLLM = ChatTongyi()
llm_kwargs = {"tools": tools, "result_format": "message"}
ai_message = chatLLM.bind(**llm_kwargs).invoke(messages)
ai_message
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': '87ef33d2-5c6b-9457-91e2-39faad7120eb', 'token_usage': {'input_tokens': 229, 'output_tokens': 19, 'total_tokens': 248}}, id='run-7939ba7f-e3f7-46f8-980b-30499b52723c-0', tool_calls=[{'name': 'get_current_weather', 'args': {'location': 'San Francisco'}, 'id': ''}])

部分模式​

使大型模型能够从您提供的初始文本继续生成内容。

from langchain_community.chat_models.tongyi import ChatTongyi
from langchain_core.messages import AIMessage, HumanMessage

messages = [
    HumanMessage(
        content="""Please continue the sentence "Spring has arrived, and the earth" to express the beauty of spring and the author's joy."""
    ),
    AIMessage(
        content="Spring has arrived, and the earth", additional_kwargs={"partial": True}
    ),
]
chatLLM = ChatTongyi()
ai_message = chatLLM.invoke(messages)
ai_message
AIMessage(content=' has cast off its heavy cloak of snow, donning instead a vibrant garment of fresh greens and floral hues; it is as if the world has woken from a long slumber, stretching and reveling in the warm caress of the sun. Everywhere I look, there is a symphony of life: birdsong fills the air, bees dance from flower to flower, and a gentle breeze carries the sweet fragrance of blossoms. It is in this season that my heart finds particular joy, for it whispers promises of renewal and growth, reminding me that even after the coldest winters, there will always be a spring to follow.', additional_kwargs={}, response_metadata={'model_name': 'qwen-turbo', 'finish_reason': 'stop', 'request_id': '447283e9-ee31-9d82-8734-af572921cb05', 'token_usage': {'input_tokens': 40, 'output_tokens': 127, 'prompt_tokens_details': {'cached_tokens': 0}, 'total_tokens': 167}}, id='run-6a35a91c-cc12-4afe-b56f-fd26d9035357-0')

Tongyi 视觉版​

Qwen-VL (qwen-vl-plus/qwen-vl-max) 是可以处理图像的模型。

from langchain_community.chat_models import ChatTongyi
from langchain_core.messages import HumanMessage

chatLLM = ChatTongyi(model_name="qwen-vl-max")
image_message = {
    "image": "https://lilianweng.github.io/posts/2023-06-23-agent/agent-overview.png",
}
text_message = {
    "text": "summarize this picture",
}
message = HumanMessage(content=[text_message, image_message])
chatLLM.invoke([message])
API 参考：ChatTongyi | HumanMessage
AIMessage(content=[{'text': 'The image presents a flowchart of an artificial intelligence system. The system is divided into two main components: short-term memory and long-term memory, which are connected to the "Memory" box.\n\nFrom the "Memory" box, there are three branches leading to different functionalities:\n\n1. "Tools" - This branch represents various tools that the AI system can utilize, including "Calendar()", "Calculator()", "CodeInterpreter()", "Search()" and others not explicitly listed.\n\n2. "Action" - This branch represents the action taken by the AI system based on its processing of information. It\'s connected to both the "Tools" and the "Agent" boxes.\n\n3. "Planning" - This branch represents the planning process of the AI system, which involves reflection, self-critics, chain of thoughts, subgoal decomposition, and other processes not shown.\n\nThe central component of the system is the "Agent" box, which seems to orchestrate the flow of information between the different components. The "Agent" interacts with the "Tools" and "Memory" boxes, suggesting it plays a crucial role in the AI\'s decision-making process. \n\nOverall, the image depicts a complex and interconnected artificial intelligence system, where different components work together to process information, make decisions, and take actions.'}], response_metadata={'model_name': 'qwen-vl-max', 'finish_reason': 'stop', 'request_id': '6a2b9e90-7c3b-960d-8a10-6a0cf9991ae5', 'token_usage': {'input_tokens': 1262, 'output_tokens': 260, 'image_tokens': 1232}}, id='run-fd030661-c734-4580-b977-b77d42680742-0')

此页面是否有帮助？