Skip to content
Nappai Documentation

LlamaCloud Component Parse

This component lets you parse files using LlamaCloud’s parsing service, turning documents into structured data that can be used by your automation workflows.

How it Works

When you drop a file into the Base 64 input, the component sends that file to LlamaCloud’s parsing API. LlamaCloud processes the document and returns structured data. The component then outputs this data as a Result that can be fed into other parts of your workflow. If you want the parsed data to be used by an AI agent, the component can also expose the parsed information as a Tool that the agent can call.

Inputs

Mapping Mode

This component has a special mode called “Mapping Mode”. When you enable this mode using the toggle switch, an additional input called “Mapping Data” is activated, and each input field offers you three different ways to provide data:

  • Fixed: You type the value directly into the field.
  • Mapped: You connect the output of another component to use its result as the value.
  • Javascript: You write Javascript code to dynamically calculate the value.

This flexibility allows you to create more dynamic and connected workflows.

Note: This component requires a credential of type LlamaCloud API. Configure the credential in the credentials section of Nappai and then select it in the Credential field of this component.

Input Fields

  • Base 64 input: The file or files to be parsed in LlamaCloud. This uses the Binary Component to upload the files.
  • Access Token: The access token for your LlamaCloud.
  • Last Access Token: The last access token for LlamaCloud.
  • Mapping Mode: Enable mapping mode to process multiple data records in batch.
  • Organization Name: Select the organization name.
  • Project Name: Select the project name.
  • Tool Name: The name of the tool that will be used when this component is connected as a tool. This name will be displayed to the agent when it selects tools to use.
  • Tool Description: A detailed description of what this tool does. This description will help the agent understand when and how to use this tool effectively.
  • Tools arguments metadata: Defines the arguments metadata for the tools.

Outputs

  • Result: The parsed data returned from LlamaCloud. This is a Data object that can be passed to other components.
  • Tool: A Tool object that can be used by an AI agent to call the parsed data as a tool.

Usage Example

  1. Upload a PDF
    Drag a PDF file into the Base 64 input.
  2. Set Credentials
    In the Credential field, choose the LlamaCloud API credential you created earlier.
  3. Enable Mapping Mode (Optional)
    If you want to parse multiple files at once, toggle Mapping Mode on and connect a list of files to the Base 64 input.
  4. Run the Component
    The component will send the file(s) to LlamaCloud, receive the parsed data, and output it in the Result field.
  5. Use the Result
    Connect the Result output to a downstream component, such as a database writer or a text summarizer.
  • Binary Component – Uploads files in Base64 format.
  • LlamaCloud API Credential – Stores your LlamaCloud access token and server URL.
  • Tool Output – Allows the parsed data to be exposed as a tool for AI agents.

Tips and Best Practices

  • Use Mapping Mode when you need to process a batch of documents in one run.
  • Keep your access token secure; never expose it in public workflows.
  • Verify that the file format is supported by LlamaCloud (PDF, DOCX, etc.) before uploading.
  • If you encounter parsing errors, check the LlamaCloud logs for detailed error messages.

Security Considerations

  • The Access Token and Last Access Token are sensitive credentials. Store them in a secure credential store and never hard‑code them in your workflow.
  • Ensure that only authorized users have access to the LlamaCloud API credential.
  • Use HTTPS when the component communicates with LlamaCloud to protect data in transit.