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

# Cohere 集成

> Cohere 是一家加拿大初创公司，提供自然语言处理模型 帮助企业提升人机交互体验。

> [Cohere](https://cohere.ai/about) 是一家加拿大初创公司，提供自然语言处理模型
> 帮助企业提升人机交互体验。

## 安装与配置

* 安装 Python SDK :

```bash pip theme={null}
pip install langchain-cohere
```

```bash uv theme={null}
uv add langchain-cohere
```

获取 [Cohere api key](https://dashboard.cohere.ai/) 并将其设置为环境变量（`COHERE_API_KEY`）

## Cohere LangChain 集成

| API | 描述 | 端点文档 | 导入 | 示例用法 |
| - | - | - | - | - |
| Chat | 构建聊天机器人 | [chat](https://docs.cohere.com/reference/chat) | `from langchain_cohere import ChatCohere` | [cohere.ipynb](https://langchain-docs-zh.mintlify.site/langchain/oss/python/integrations/chat/cohere.md) |
| LLM | 生成文本 | [generate](https://docs.cohere.com/reference/generate) | `from langchain_cohere.llms import Cohere` | [cohere.ipynb](https://langchain-docs-zh.mintlify.site/langchain/oss/python/integrations/llms/cohere.md) |
| RAG Retriever | 连接外部数据源 | [chat + rag](https://docs.cohere.com/reference/chat) | `from langchain_classic.retrievers import CohereRagRetriever` | [cohere.ipynb](https://langchain-docs-zh.mintlify.site/langchain/oss/python/integrations/retrievers/cohere.md) |
| Text Embedding | 将字符串转换为向量 | [embed](https://docs.cohere.com/reference/embed) | `from langchain_cohere import CohereEmbeddings` | [cohere.ipynb](https://langchain-docs-zh.mintlify.site/langchain/oss/python/integrations/embeddings/cohere.md) |
| Rerank Retriever | 基于相关性排序字符串 | [rerank](https://docs.cohere.com/reference/rerank) | `from langchain_classic.retrievers.document_compressors import CohereRerank` | [cohere.ipynb](https://langchain-docs-zh.mintlify.site/langchain/oss/python/integrations/retrievers/cohere-reranker.md) |

## 快速示例

### 聊天

```python theme={null}
from langchain_cohere import ChatCohere
from langchain.messages import HumanMessage
chat = ChatCohere()
messages = [HumanMessage(content="knock knock")]
print(chat.invoke(messages))
```

使用 Cohere [chat model](https://langchain-docs-zh.mintlify.site/langchain/oss/python/integrations/chat/cohere.md)

### LLM

```python theme={null}
from langchain_cohere.llms import Cohere

llm = Cohere()
print(llm.invoke("Come up with a pet name"))
```

使用 Cohere (遗留) [LLM model](https://langchain-docs-zh.mintlify.site/langchain/oss/python/integrations/llms/cohere.md)

### 工具调用

```python theme={null}
from langchain_cohere import ChatCohere
from langchain.messages import (
    HumanMessage,
    ToolMessage,
)
from langchain.tools import tool

@tool
def magic_function(number: int) -> int:
    """Applies a magic operation to an integer

    Args:
        number: Number to have magic operation performed on
    """
    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]

llm = ChatCohere()
llm_with_tools = llm.bind_tools(tools=tools)
messages = [
    HumanMessage(
        content="What is the value of magic_function(2)?"
    )
]

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)

print(res.content)
```

Cohere LLM 的工具调用可通过绑定必要工具实现（如上所示）。另一种方式是通过 ReAct 智能体支持多步工具调用（如下所示）。

### ReAct 智能体

该智能体基于论文
[ReAct: Synergizing Reasoning and Acting in Language Models](https://arxiv.org/abs/2210.03629)。

> [!WARNING]
>
> `langchain-community`包已不再维护。从`langchain_community`导入的示例可能过时或无法使用。请谨慎使用。

```python theme={null}
from langchain_community.tools.tavily_search import TavilySearchResults
from langchain_cohere import ChatCohere, create_cohere_react_agent
from langchain_core.prompts import ChatPromptTemplate
from langchain_classic.agents import AgentExecutor

llm = ChatCohere()

internet_search = TavilySearchResults(max_results=4)
internet_search.name = "internet_search"
internet_search.description = "Route a user query to the internet"

prompt = ChatPromptTemplate.from_template("{input}")

agent = create_cohere_react_agent(
    llm,
    [internet_search],
    prompt
)

agent_executor = AgentExecutor(agent=agent, tools=[internet_search], verbose=True)

agent_executor.invoke({
    "input": "In what year was the company that was founded as Sound of Music added to the S&P 500?",
})
```

ReAct 智能体可用于按顺序调用多个工具。

### RAG 检索器

```python theme={null}
from langchain_cohere import ChatCohere
from langchain_classic.retrievers import CohereRagRetriever
from langchain_core.documents import Document

rag = CohereRagRetriever(llm=ChatCohere())
print(rag.invoke("What is cohere ai?"))
```

使用 Cohere [RAG Retriever](https://langchain-docs-zh.mintlify.site/langchain/oss/python/integrations/retrievers/cohere.md)

### 文本嵌入

```python theme={null}
from langchain_cohere import CohereEmbeddings

embeddings = CohereEmbeddings(model="embed-english-light-v3.0")
print(embeddings.embed_documents(["This is a test document."]))
```

使用 Cohere [Text Embeddings model](https://langchain-docs-zh.mintlify.site/langchain/oss/python/integrations/embeddings/cohere.md)

### 重排序器

使用 Cohere [Reranker](https://langchain-docs-zh.mintlify.site/langchain/oss/python/integrations/retrievers/cohere-reranker.md)

***

> 官方原文：[src/oss/python/integrations/providers/cohere.mdx](https://github.com/langchain-ai/docs/blob/main/src/oss/python/integrations/providers/cohere.mdx) · 非官方翻译，译文由 AI 生成，以英文原文为准。


This documentation is built and hosted on [Mintlify](https://mintlify.com), a developer documentation platform.