View as Markdown
Cradl AI icon

Cradl AI ACTION

Parse Document

Parses data from a document using a custom selected model. See the documentation
  • Action
  • Writes data
  • OAuth
  • SDK
  • MCP

IMPLEMENTATION

Call this tool

Connect a user's Cradl AI account once, then configure and run Parse Document from your backend or agent.

import { PipedreamClient } from "@pipedream/sdk"

const pd = new PipedreamClient({
  projectId: process.env.PIPEDREAM_PROJECT_ID!,
  clientId: process.env.PIPEDREAM_CLIENT_ID!,
  clientSecret: process.env.PIPEDREAM_CLIENT_SECRET!,
  projectEnvironment: "production",
})

const result = await pd.actions.run({
  id: "cradl_ai-parse-document",
  externalUserId: "{external_user_id}", // any stable ID for this user in your system
  configuredProps: {
    cradl_ai: { authProvisionId: "apn_xxxxxxx" },
    filePath: "File Path or URL",
    contentType: "Content Type",
  },
})

console.log(result)

SCHEMA

Inputs

Pipedream supplies the connected account. Your application provides the operation-specific values below. Dynamic inputs are resolved against that user's account.

Parse Document inputs
Property Type Description
filePath File Path or URL string
The file to process. Provide either a file URL or a path to a file in the /tmp directory (for example, /tmp/myFile.txt).
Required
contentType Content Type string
The content type of the document
Required
name Name string
Name of the document
Optional
description Description string
Description of the document
Optional
datasetId Dataset ID string
The ID of the dataset to use
Optional Dynamic
syncDir SyncDir dir
Optional
modelId Model ID string
The ID of the model to be used for parsing
Required Dynamic

REFERENCE

Tool details

Behavior hints are published with the component in the Pipedream registry and surface as MCP tool annotations, so an agent can reason about a tool before it calls it.

Registry key
cradl_ai-parse-document
Version
0.1.2
App
Cradl AI
Authentication
OAuth
Read-only
No
Destructive
No
Open world
Yes