> For the complete documentation index, see [llms.txt](https://docs.n8n.io/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://docs.n8n.io/build/code-in-n8n/use-built-in-shortcuts/langchain-code-node.md).

# LangChain Code node

n8n provides these methods to make it easier to perform common tasks in the [LangChain Code node](/integrations/builtin/cluster-nodes/root-nodes/n8n-nodes-langchain.code.md).

{% hint style="info" %}
**LangChain Code node only**

These variables are for use in expressions in the LangChain Code node. You can't use them in other nodes.
{% endhint %}

| Method                                                           | Description                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                    |
| ---------------------------------------------------------------- | ---------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
| `this.addInputData(inputName, data)`                             | <p>Populate the data of a specified non-main input. Useful for mocking data.</p><ul><li><code>inputName</code> is the input connection type, and must be one of: <code>ai\_agent</code>, <code>ai\_chain</code>, <code>ai\_document</code>, <code>ai\_embedding</code>, <code>ai\_languageModel</code>, <code>ai\_memory</code>, <code>ai\_outputParser</code>, <code>ai\_retriever</code>, <code>ai\_textSplitter</code>, <code>ai\_tool</code>, <code>ai\_vectorRetriever</code>, <code>ai\_vectorStore</code></li><li><code>data</code> contains the data you want to add. Refer to <a href="/spaces/rPN1zU5jaYNvwH7RzxqA/pages/4w4R7N2ysLi9xAC7Jfde">Data structure</a> for information on the data structure expected by n8n.</li></ul>   |
| `this.addOutputData(outputName, data)`                           | <p>Populate the data of a specified non-main output. Useful for mocking data.</p><ul><li><code>outputName</code> is the input connection type, and must be one of: <code>ai\_agent</code>, <code>ai\_chain</code>, <code>ai\_document</code>, <code>ai\_embedding</code>, <code>ai\_languageModel</code>, <code>ai\_memory</code>, <code>ai\_outputParser</code>, <code>ai\_retriever</code>, <code>ai\_textSplitter</code>, <code>ai\_tool</code>, <code>ai\_vectorRetriever</code>, <code>ai\_vectorStore</code></li><li><code>data</code> contains the data you want to add. Refer to <a href="/spaces/rPN1zU5jaYNvwH7RzxqA/pages/4w4R7N2ysLi9xAC7Jfde">Data structure</a> for information on the data structure expected by n8n.</li></ul> |
| `this.getInputConnectionData(inputName, itemIndex, inputIndex?)` | <p>Get data from a specified non-main input.</p><ul><li><code>inputName</code> is the input connection type, and must be one of: <code>ai\_agent</code>, <code>ai\_chain</code>, <code>ai\_document</code>, <code>ai\_embedding</code>, <code>ai\_languageModel</code>, <code>ai\_memory</code>, <code>ai\_outputParser</code>, <code>ai\_retriever</code>, <code>ai\_textSplitter</code>, <code>ai\_tool</code>, <code>ai\_vectorRetriever</code>, <code>ai\_vectorStore</code></li><li><code>itemIndex</code> should always be <code>0</code> (this parameter will be used in upcoming functionality)</li><li>Use <code>inputIndex</code> if there is more than one node connected to the specified input.</li></ul>                         |
| `this.getInputData(inputIndex?, inputName?)`                     | Get data from the main input.                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                  |
| `this.getNode()`                                                 | Get the current node.                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                          |
| `this.getNodeOutputs()`                                          | Get the outputs of the current node.                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                           |
| `this.getExecutionCancelSignal()`                                | Use this to stop the execution of a function when the workflow stops. In most cases n8n handles this, but you may need to use it if building your own chains or agents. It replaces the [Cancelling a running LLMChain](https://js.langchain.com/docs/modules/chains/foundational/llm_chain#cancelling-a-running-llmchain) code that you'd use if building a LangChain application normally.                                                                                                                                                                                                                                                                                                                                                   |