Skip to content
Nappai Documentation

LlamaCloud Component Extract

LlamaCloud Component Extract is a tool in the Nappai dashboard that lets you work with LlamaCloud’s extraction services.
You can upload files, run an extraction job, list all jobs, or get the parsed text from a finished job.
It’s designed for non‑technical users, so you only need to fill in a few fields and choose the operation you want.

How it Works

When you use this component, it talks to the LlamaCloud API.
First, you must have a LlamaCloud API credential set up in Nappai’s credentials section.
After selecting that credential, the component sends your data to LlamaCloud, where the extraction agent processes the file.
Depending on the operation you choose, the component will either start a new extraction job, list all existing jobs, or fetch the parsed text from a completed job.
If you enable Mapping Mode, you can feed many records at once and choose how each input is supplied (Fixed, Mapped, or Javascript).

Operations

This component offers several operations that you can select based on what you need to do. You can only use one operation at a time:

  • Run on file: Upload one or more files and start a new extraction job using the selected extraction agent.
  • List Alls Jobs: Retrieve a list of all extraction jobs that have been created in your project.
  • Get Parsed Text: Get the parsed text output from a specific extraction job that has already finished.

To use the component, first select the operation you need in the “Operation” field.

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.

Input Fields

The following fields are available to configure this component. Each field may be visible in different operations:

  • Records: The file or files to be parsed in LlamaCloud. This uses the Binary Component to upload the files.
    • Visible in: Run on file
  • Parse Action: Choose the action that the extraction agent should perform.
    • Visible in: Run on file, List Alls Jobs, Get Parsed Text
  • Access Token: The access token for your LlamaCloud account.
    • Visible in: Run on file, List Alls Jobs, Get Parsed Text
  • Extraction Agent Name: Select one of the extraction agents declared in your project. You must declare the agents before in the project.
    • Visible in: Run on file
  • Job Name: Select one of the files parsed in your project. You must parse the files before in the project.
    • Visible in: Get Parsed Text
  • Last Access Token: The last access token for LlamaCloud.
    • Visible in: Run on file, List Alls Jobs, Get Parsed Text
  • Mapping Mode: Enable mapping mode to process multiple data records in batch.
    • Visible in: Run on file, List Alls Jobs, Get Parsed Text
  • Organization Name: Introduce first access token. After that, you can select the organization name.
    • Visible in: Run on file, List Alls Jobs, Get Parsed Text
  • Project Name: Introduce first access token. After that and selected the organization name, you can select the project name.
    • Visible in: Run on file, List Alls Jobs, Get Parsed Text
  • 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.
    • Visible in: Run on file, List Alls Jobs, Get Parsed Text
  • 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.
    • Visible in: Run on file, List Alls Jobs, Get Parsed Text
  • Tools arguments metadata: Defines the arguments metadata for the tools.
    • Visible in: Run on file, List Alls Jobs, Get Parsed Text

Outputs

  • Result: The raw data returned by the LlamaCloud API after performing the chosen operation. This can be used as input for other components or for further processing.
  • Tool: A tool representation that can be used by Nappai’s AI agents. It includes the tool name, description, and argument metadata.

Usage Example

  1. Run on file

    • Enable the component and select Run on file.
    • Upload a PDF or CSV file in the Records field.
    • Choose an extraction agent in Extraction Agent Name.
    • Click Run. The component will start a job and return the job ID in the Result output.

  2. Get Parsed Text

    • After the job finishes, switch the operation to Get Parsed Text.
    • Select the finished job in Job Name.
    • Click Run. The parsed text will appear in the Result output, ready to be used in the next step of your workflow.
  • LlamaCloud Component Upload – Upload files to LlamaCloud without starting an extraction job.
  • LlamaCloud Component Delete – Remove files or jobs from your LlamaCloud project.
  • LlamaCloud Component List – List all files that have been uploaded to your project.

Tips and Best Practices

  • Keep your Access Token and Last Access Token up to date; they expire after a set period.
  • Use Mapping Mode when you need to process many files at once; it saves time and reduces manual input.
  • Always check the Result output for error messages before moving to the next component.
  • If you’re working with large files, consider splitting them into smaller chunks to avoid timeouts.

Security Considerations

  • Store your LlamaCloud API credentials securely in Nappai’s credential manager.
  • Never expose your access tokens in public workflows or share them with unauthorized users.
  • Use the Credential input to select the pre‑configured LlamaCloud API credential; this keeps sensitive data out of the component’s visible fields.