from getpass import getpass
DASHSCOPE_API_KEY = getpass()import os
os.environ["DASHSCOPE_API_KEY"] = "sk61"
from langchain_community.chat_models.tongyi import ChatTongyifrom langchain_core.messages import HumanMessage
chatLLM = ChatTongyi(streaming=True, )
from langchain_core.messages import HumanMessage, SystemMessage
messages = [    SystemMessage(        content=        "You are a helpful assistant that translates English to Chinese."),    HumanMessage(        content=        "Translate this sentence from English to Chinese. I love programming."    ),]res = chatLLM(messages)print(res)

from getpass import getpass
DASHSCOPE_API_KEY = getpass()import os
os.environ["DASHSCOPE_API_KEY"] = "sk-"
from langchain_community.chat_models.tongyi import ChatTongyifrom langchain_core.messages import HumanMessage, SystemMessagefrom langchain_core.tools import tool

@tooldef 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("5乘以32的结果是多少？").tool_calls
print(msg)

[{'name': 'multiply', 'args': {'first_int': 5, 'second_int': 32}, 'id': '', 'type': 'tool_call'}]

from langchain_core.messages import HumanMessage, ToolMessage
messages = [HumanMessage(query)]ai_msg = llm_with_tools.invoke(messages)messages.append(ai_msg)for tool_call in ai_msg.tool_calls:    selected_tool = {"add": add, "multiply": multiply}[tool_call["name"].lower()]    tool_output = selected_tool.invoke(tool_call["args"])    messages.append(ToolMessage(tool_output, tool_call_id=tool_call["id"]))messages

#完整代码from getpass import getpass
DASHSCOPE_API_KEY = getpass()import os
os.environ["DASHSCOPE_API_KEY"] = "sk-"
from langchain_community.chat_models.tongyi import ChatTongyifrom langchain_core.messages import HumanMessage, SystemMessagefrom langchain_core.tools import toolfrom langchain_core.messages import HumanMessage, ToolMessage

@tooldef multiply(first_int: int, second_int: int) -> int:    """Multiply two integers together."""    return first_int * second_int
tools=[multiply]llm = ChatTongyi(model="qwen-turbo")
llm_with_tools = llm.bind_tools(tools)

query="what is 3*12?"
messages = [HumanMessage(query)]ai_msg = llm_with_tools.invoke(messages)messages.append(ai_msg)for tool_call in ai_msg.tool_calls:    selected_tool = {"multiply": multiply}[tool_call["name"].lower()]    tool_output = selected_tool.invoke(tool_call["args"])    messages.append(ToolMessage(tool_output, tool_call_id=tool_call["id"]))

print(messages)

[HumanMessage(content='what is 3*12?'), AIMessage(content='', additional_kwargs={'tool_calls': [{'function': {'name': 'multiply', 'arguments': '{"first_int": 3, "second_int": 12}'}, 'id': '', 'type': 'function'}]}, response_metadata={'model_name': 'qwen-turbo', 'finish_reason': 'tool_calls', 'request_id': '941b5989-73fc-9d7b-a010-d63772296db2', 'token_usage': {'input_tokens': 187, 'output_tokens': 25, 'total_tokens': 212}}, id='run-58c2c22b-46fd-4d61-a1e9-9b4d1b2e4ec2-0', tool_calls=[{'name': 'multiply', 'args': {'first_int': 3, 'second_int': 12}, 'id': '', 'type': 'tool_call'}]), ToolMessage(content='36', tool_call_id='')]

from langchain_community.chat_models import ChatTongyifrom langchain_core.messages import HumanMessage
chatLLM = ChatTongyi(model_name="qwen-vl-max")image_message = {    "image": "https://ai-studio-static-online.cdn.bcebos.com/ea894a305d714a1790df1282975b01be0532f2b81f6f4860abda0c5eeb1f1211",}text_message = {    "text": "summarize this picture",}message = HumanMessage(content=[text_message, image_message])chatLLM.invoke([message])

AIMessage(content=[{'text': "The image presents an abstract representation of the Agent, which serves as the central hub for various cognitive processes and tools. The Agent is connected to both short-term memory and long-term memory, indicating its role in integrating past experiences and immediate perceptions.\n\nFrom the Agent, several tools branch out, including Calendar(), Calculator(), CodeInterpreter(), Search(), and more, suggesting that it can leverage various resources to accomplish tasks. Additionally, the Agent engages in planning by connecting back to itself through a feedback loop.\n\nSelf-reflection plays a crucial role in the Agent's operation, as indicated by its connections with self-critics. Furthermore, the Agent exhibits problem-solving abilities through its chain of thoughts, subgoal decomposition, and the use of external tools like Code Interpreter(). Overall, the Agent appears to be a highly adaptable and resourceful entity that integrates various cognitive functions and external aids to navigate complex environments or solve problems."}], response_metadata={'model_name': 'qwen-vl-max', 'finish_reason': 'stop', 'request_id': '557f9c6b-dacd-9aa1-ade2-f617453d3474', 'token_usage': {'input_tokens': 1264, 'output_tokens': 181, 'image_tokens': 1232}}, id='run-a39305d2-7c17-402f-bbd4-960d815ae55e-0')

import osfrom langchain_community.chat_models.moonshot import MoonshotChatfrom langchain_core.messages import HumanMessage, SystemMessage#Generate your api key from: https://platform.moonshot.cn/console/api-keysos.environ["MOONSHOT_API_KEY"] = "MOONSHOT_API_KEY"chat = MoonshotChat()#or use a specific model#Available models: https://platform.moonshot.cn/docs#chat = MoonshotChat(model="moonshot-v1-128k")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."    ),]
chat.invoke(messages)

from openai import OpenAI client = OpenAI(    api_key = "$MOONSHOT_API_KEY",    base_url = "https://api.moonshot.cn/v1",) completion = client.chat.completions.create(    model = "moonshot-v1-8k",    messages = [        {"role": "system", "content": "你是 Kimi，由 Moonshot AI 提供的人工智能助手，你更擅长中文和英文的对话。你会为用户提供安全，有帮助，准确的回答。同时，你会拒绝一切涉及恐怖主义，种族歧视，黄色暴力等问题的回答。Moonshot AI 为专有名词，不可翻译成其他语言。"},        {"role": "user", "content": "你好，我叫李雷，1+1等于多少？"}    ],    temperature = 0.3,) print(completion.choices[0].message.content)

from openai import OpenAI client = OpenAI(    api_key = "$MOONSHOT_API_KEY",    base_url = "https://api.moonshot.cn/v1",) history = [    {"role": "system", "content": "你是 Kimi，由 Moonshot AI 提供的人工智能助手，你更擅长中文和英文的对话。你会为用户提供安全，有帮助，准确的回答。同时，你会拒绝一切涉及恐怖主义，种族歧视，黄色暴力等问题的回答。Moonshot AI 为专有名词，不可翻译成其他语言。"}] def chat(query, history):    history.append({        "role": "user",         "content": query    })    completion = client.chat.completions.create(        model="moonshot-v1-8k",        messages=history,        temperature=0.3,    )    result = completion.choices[0].message.content    history.append({        "role": "assistant",        "content": result    })    return result print(chat("地球的自转周期是多少？", history))print(chat("月球呢？", history))

from langchain_community.chat_models import ChatBaichuanfrom langchain_core.messages import HumanMessagechat = ChatBaichuan(baichuan_api_key="sk-")#也可以使用192K开启流式输出#chat = ChatBaichuan(#baichuan_api_key="YOUR_API_KEY",#streaming=True,#)chat([HumanMessage(content="结合北京市发展情况，编写《北京商务发展报告2023》的提纲。")])

AIMessage(content='《北京商务发展报告2023》提纲\n\n一、引言\n   1. 报告背景\n   2. 报告目的与意义\n   3. 数据来源与研究方法\n\n二、北京市商务发展概况\n   1. 北京市经济发展总体情况\n   2. 北京市商务发展主要指标分析\n   3. 北京市商务发展特点与趋势\n\n三、北京市重点行业商务发展分析\n   1. 金融业\n       1.1 北京市金融业发展现状\n       1.2 北京市金融业发展特点与趋势\n       1.3 北京市金融业发展前景展望\n   2. 高新技术产业\n       2.1 北京市高新技术产业发展现状\n       2.2 北京市高新技术产业发展特点与趋势\n       2.3 北京市高新技术产业发展前景展望\n   3. 现代物流业\n       3.1 北京市现代物流业发展现状\n       3.2 北京市现代物流业发展特点与趋势\n       3.3 北京市现代物流业发展前景展望\n   4. 其他重点行业（如旅游业、文化创意产业等）\n\n四、北京市商务发展政策环境分析\n   1. 北京市商务发展政策环境概述\n   2. 北京市商务发展政策环境对行业发展的影响分析\n   3. 北京市商务发展政策环境展望\n\n五、北京市商务发展区域布局分析\n   1. 北京市商务发展区域布局现状\n   2. 北京市商务发展区域布局特点与趋势\n   3. 北京市商务发展区域布局展望\n\n六、北京市商务发展面临的挑战与机遇\n   1. 北京市商务发展面临的挑战\n   2. 北京市商务发展面临的机遇\n   3. 北京市商务发展应对挑战与把握机遇的策略建议\n\n七、北京市商务发展展望\n   1. 北京市商务发展总体展望\n   2. 北京市重点行业商务发展展望\n   3. 北京市商务发展政策环境与区域布局展望\n\n八、结论\n   1. 北京市商务发展主要成果与经验总结\n   2. 对北京市商务发展的建议与展望\n\n九、附录\n   1. 北京市商务发展相关数据汇总\n   2. 北京市商务发展相关政策汇总\n   3. 北京市商务发展相关研究报告与文献汇总', response_metadata={'token_usage': {'prompt_tokens': 21, 'completion_tokens': 475, 'total_tokens': 496}, 'model': 'Baichuan2-Turbo-192K'}, id='run-071ed1da-6950-412a-9a60-7216ceb53af0-0')

curl --location --request POST 'https://api.coze.cn/v3/chat' \--header 'Authorization: Bearer {{Personal_Access_Token}}' \--header 'Content-Type: application/json' \--data-raw '{    "bot_id": "{{Bot_Id}}",    "user_id": "{{UserId}}",    "stream": false,    "auto_save_history":true,    "additional_messages":[        {            "role":"user",            "content":"{{yourquery}}",            "content_type":"text"        }    ]}'