# create_cohere_react_agent

> **Function** in `langchain_cohere`

📖 [View in docs](https://reference.langchain.com/python/langchain-cohere/react_multi_hop/agent/create_cohere_react_agent)

Create an agent that enables multiple tools to be used in sequence.

.. deprecated:: 0.6.0
    Use ``langgraph.prebuilt.create_react_agent`` with
    :class:`~langchain_cohere.ChatCohere` instead.

## Signature

```python
create_cohere_react_agent(
    llm: BaseLanguageModel,
    tools: Sequence[BaseTool],
    prompt: ChatPromptTemplate,
) -> Runnable
```

## Parameters

| Name | Type | Required | Description |
|------|------|----------|-------------|
| `llm` | `BaseLanguageModel` | Yes | The `ChatCohere` LLM instance to use. |
| `tools` | `Sequence[BaseTool]` | Yes | Tools this agent has access to. |
| `prompt` | `ChatPromptTemplate` | Yes | The prompt to use. |

## Returns

`Runnable`

A `Runnable` sequence representing an agent.

## ⚠️ Deprecated

Deprecated since version 0.6.0. Use langgraph Will be removed in version 1.0.0.

---

[View source on GitHub](https://github.com/langchain-ai/langchain-cohere/blob/0e86adc8d140bf6e3da49836173bd5a50a194b63/libs/cohere/langchain_cohere/react_multi_hop/agent.py#L35)