> ## Documentation Index
> Fetch the complete documentation index at: https://dify-6c0370d8-add-new-agent.mintlify.site/llms.txt
> Use this file to discover all available pages before exploring further.

# Upload File to Sandbox

> Upload multimodal files to the sandbox so LLMs can process them with tools and scripts—even file types they can't handle natively

<Info>
  This node is only available in applications using the [sandboxed runtime](/en/use-dify/build/runtime#sandboxed-runtime)
</Info>

When files are passed directly to an LLM, processing is limited by the model's own multimodal capabilities. While the [Doc Extractor](/en/use-dify/nodes/doc-extractor) node can convert some file types to text for LLMs to process, its supported formats are still limited.

This is where the Upload File to Sandbox node helps. Once files are uploaded, downstream [Agent nodes](/en/use-dify/nodes/agent#sandboxed-runtime) (with **Agent Mode** enabled) can execute commands to install tools and run scripts in the sandbox as needed, converting files into formats LLMs can process.

<Note>
  Processing results depends on the model's reasoning capability.
</Note>

You can find uploaded files under **Artifacts**. They follow the same [lifecycle rules](/en/use-dify/build/file-system#artifact-lifecycle) as other artifacts.

**How to use:**

1. In an Upload File to Sandbox node, select a file variable (e.g., from User Input).

2. In a downstream Agent node's prompt, reference the `sandbox_path` and `file_name` variables so the model can locate and process the file. For example:

   ```bash wrap theme={null}
   # System instruction
   You are a data analyst. Analyze uploaded data files and provide insights.

   # User message
   Analyze the data in "{{Upload File to Sandbox.file_name}}" at {{Upload File to Sandbox.sandbox_path}}.
   ```

   <Info>
     The `file_name` variable includes the file extension (e.g., `data.csv`).
   </Info>