> ## Documentation Index
> Fetch the complete documentation index at: https://langchain-zh.cn/llms.txt
> Use this file to discover all available pages before exploring further.

# ChatCohere 集成

> 使用 LangChain Python 与 Cohere 聊天模型集成。

本笔记本介绍如何开始使用 [Cohere 聊天模型](https://cohere.com/chat)。

前往 [API 参考](https://reference.langchain.com/python/langchain-cohere/chat_models/ChatCohere) 查看所有属性和方法的详细文档。

## 设置

集成位于 `langchain-cohere` 包中。我们可以通过以下命令安装：

```bash theme={"theme":{"light":"catppuccin-latte","dark":"catppuccin-mocha"}}
pip install -U langchain-cohere
```

我们还需要获取 [Cohere API 密钥](https://cohere.com/) 并设置 `COHERE_API_KEY` 环境变量：

```python theme={"theme":{"light":"catppuccin-latte","dark":"catppuccin-mocha"}}
import getpass
import os

os.environ["COHERE_API_KEY"] = getpass.getpass()
```

设置 [LangSmith](https://smith.langchain.com/) 以获得最佳的观测性体验也很有帮助（但不是必需的）：

```python theme={"theme":{"light":"catppuccin-latte","dark":"catppuccin-mocha"}}
os.environ["LANGSMITH_TRACING"] = "true"
os.environ["LANGSMITH_API_KEY"] = getpass.getpass("输入你的 LangSmith API 密钥：")
```

## 使用

ChatCohere 支持所有 [ChatModel](/oss/python/langchain/models) 功能：

```python theme={"theme":{"light":"catppuccin-latte","dark":"catppuccin-mocha"}}
from langchain_cohere import ChatCohere
from langchain.messages import HumanMessage
```

```python theme={"theme":{"light":"catppuccin-latte","dark":"catppuccin-mocha"}}
chat = ChatCohere()
```

```python theme={"theme":{"light":"catppuccin-latte","dark":"catppuccin-mocha"}}
messages = [HumanMessage(content="1"), HumanMessage(content="2 3")]
chat.invoke(messages)
```

```text theme={"theme":{"light":"catppuccin-latte","dark":"catppuccin-mocha"}}
AIMessage(content='4 && 5 \n6 || 7 \n\nWould you like to play a game of odds and evens?', additional_kwargs={'documents': None, 'citations': None, 'search_results': None, 'search_queries': None, 'is_search_required': None, 'generation_id': '2076b614-52b3-4082-a259-cc92cd3d9fea', 'token_count': {'prompt_tokens': 68, 'response_tokens': 23, 'total_tokens': 91, 'billed_tokens': 77}}, response_metadata={'documents': None, 'citations': None, 'search_results': None, 'search_queries': None, 'is_search_required': None, 'generation_id': '2076b614-52b3-4082-a259-cc92cd3d9fea', 'token_count': {'prompt_tokens': 68, 'response_tokens': 23, 'total_tokens': 91, 'billed_tokens': 77}}, id='run-3475e0c8-c89b-4937-9300-e07d652455e1-0')
```

```python theme={"theme":{"light":"catppuccin-latte","dark":"catppuccin-mocha"}}
await chat.ainvoke(messages)
```

```text theme={"theme":{"light":"catppuccin-latte","dark":"catppuccin-mocha"}}
AIMessage(content='4 && 5', additional_kwargs={'documents': None, 'citations': None, 'search_results': None, 'search_queries': None, 'is_search_required': None, 'generation_id': 'f0708a92-f874-46ee-9b93-334d616ad92e', 'token_count': {'prompt_tokens': 68, 'response_tokens': 3, 'total_tokens': 71, 'billed_tokens': 57}}, response_metadata={'documents': None, 'citations': None, 'search_results': None, 'search_queries': None, 'is_search_required': None, 'generation_id': 'f0708a92-f874-46ee-9b93-334d616ad92e', 'token_count': {'prompt_tokens': 68, 'response_tokens': 3, 'total_tokens': 71, 'billed_tokens': 57}}, id='run-1635e63e-2994-4e7f-986e-152ddfc95777-0')
```

```python theme={"theme":{"light":"catppuccin-latte","dark":"catppuccin-mocha"}}
for chunk in chat.stream(messages):
    print(chunk.content, end="", flush=True)
```

```text theme={"theme":{"light":"catppuccin-latte","dark":"catppuccin-mocha"}}
4 && 5
```

```python theme={"theme":{"light":"catppuccin-latte","dark":"catppuccin-mocha"}}
chat.batch([messages])
```

```text theme={"theme":{"light":"catppuccin-latte","dark":"catppuccin-mocha"}}
[AIMessage(content='4 && 5', additional_kwargs={'documents': None, 'citations': None, 'search_results': None, 'search_queries': None, 'is_search_required': None, 'generation_id': '6770ca86-f6c3-4ba3-a285-c4772160612f', 'token_count': {'prompt_tokens': 68, 'response_tokens': 3, 'total_tokens': 71, 'billed_tokens': 57}}, response_metadata={'documents': None, 'citations': None, 'search_results': None, 'search_queries': None, 'is_search_required': None, 'generation_id': '6770ca86-f6c3-4ba3-a285-c4772160612f', 'token_count': {'prompt_tokens': 68, 'response_tokens': 3, 'total_tokens': 71, 'billed_tokens': 57}}, id='run-8d6fade2-1b39-4e31-ab23-4be622dd0027-0')]
```

## 工具调用

Cohere 支持工具调用功能！

```python theme={"theme":{"light":"catppuccin-latte","dark":"catppuccin-mocha"}}
from langchain.messages import (
    HumanMessage,
    ToolMessage,
)
from langchain.tools import tool
```

```python theme={"theme":{"light":"catppuccin-latte","dark":"catppuccin-mocha"}}
@tool
def magic_function(number: int) -> int:
    """对整数执行魔法操作
    参数：
        number: 要执行魔法操作的数值
    """
    return number + 10


def invoke_tools(tool_calls, messages):
    for tool_call in tool_calls:
        selected_tool = {"magic_function": magic_function}[tool_call["name"].lower()]
        tool_output = selected_tool.invoke(tool_call["args"])
        messages.append(ToolMessage(tool_output, tool_call_id=tool_call["id"]))
    return messages


tools = [magic_function]
```

```python theme={"theme":{"light":"catppuccin-latte","dark":"catppuccin-mocha"}}
llm_with_tools = chat.bind_tools(tools=tools)
messages = [HumanMessage(content="magic_function(2) 的值是多少？")]
```

```python theme={"theme":{"light":"catppuccin-latte","dark":"catppuccin-mocha"}}
res = llm_with_tools.invoke(messages)
while res.tool_calls:
    messages.append(res)
    messages = invoke_tools(res.tool_calls, messages)
    res = llm_with_tools.invoke(messages)

res
```

```text theme={"theme":{"light":"catppuccin-latte","dark":"catppuccin-mocha"}}
AIMessage(content='magic_function(2) 的值是 12。', additional_kwargs={'documents': [{'id': 'magic_function:0:2:0', 'output': '12', 'tool_name': 'magic_function'}], 'citations': [ChatCitation(start=34, end=36, text='12', document_ids=['magic_function:0:2:0'])], 'search_results': None, 'search_queries': None, 'is_search_required': None, 'generation_id': '96a55791-0c58-4e2e-bc2a-8550e137c46d', 'token_count': {'input_tokens': 998, 'output_tokens': 59}}, response_metadata={'documents': [{'id': 'magic_function:0:2:0', 'output': '12', 'tool_name': 'magic_function'}], 'citations': [ChatCitation(start=34, end=36, text='12', document_ids=['magic_function:0:2:0'])], 'search_results': None, 'search_queries': None, 'is_search_required': None, 'generation_id': '96a55791-0c58-4e2e-bc2a-8550e137c46d', 'token_count': {'input_tokens': 998, 'output_tokens': 59}}, id='run-f318a9cf-55c8-44f4-91d1-27cf46c6a465-0')
```

***

<div className="source-links">
  <Callout icon="edit">
    [Edit this page on GitHub](https://github.com/langchain-ai/docs/edit/main/src/i18n\zh-CN\oss\python\integrations\chat\cohere.mdx) or [file an issue](https://github.com/langchain-ai/docs/issues/new/choose).
  </Callout>

  <Callout icon="terminal-2">
    [Connect these docs](/use-these-docs) to Claude, VSCode, and more via MCP for real-time answers.
  </Callout>
</div>