> ## Documentation Index > Fetch the complete documentation index at: https://docs.landing.ai/llms.txt > Use this file to discover all available pages before exploring further. # ADE Classify > Classify each page of a document into classes you define. Accepts a PDF, an image, or an Office document, plus the list of candidate classes; returns one predicted class per page. Runs synchronously and returns the result inline. ## OpenAPI ````yaml /dpt3/openapi-adev2.json post /v1/ade/classify openapi: 3.1.0 info: title: >- LandingAI Agentic Document Extraction (ADE) Gen2 API: Parse, Extract, and Ground Documents with DPT-3 description: >- Parse and extract data from documents with DPT-3, a document parsing model from LandingAI, using the Agentic Document Extraction (ADE) v2 endpoints. Parse converts PDFs and images into structured Markdown and elements with per-element grounding (page numbers and coordinates) for RAG, search, and extraction pipelines. Extract pulls specific fields from parsed Markdown using a JSON schema. Ground maps extracted fields back to the source blocks, with page numbers and bounding boxes for each value. Documentation: https://docs.landing.ai version: 1.0.0 servers: - url: https://api.ade.landing.ai description: Production API security: [] paths: /v1/ade/classify: post: tags: - Classify summary: ADE Classify description: >- Classify each page of a document into classes you define. Accepts a PDF, an image, or an Office document, plus the list of candidate classes; returns one predicted class per page. Runs synchronously and returns the result inline. operationId: v1-ade-classify_run_sync requestBody: required: true content: multipart/form-data: schema: type: object properties: document: type: string format: binary description: >- The file to process. Provide either `document` or `document_url`, not both. document_url: type: string description: >- A publicly accessible URL to the file to process. Provide either `document` or `document_url`, not both. classes: type: string title: Classes description: >- The classes to assign to pages, as a JSON-encoded array of objects with `class` (required) and `description` keys. Each page receives one class, or `unknown` when no class fits. filename: default: '' title: Filename type: string description: Optional. Defaults to the document's own file name. content_type: default: '' title: Content Type type: string description: >- Optional. Defaults to the document's own detected media type. model: anyOf: - type: string - type: 'null' default: null description: >- The classify model version to use. Accepts `classify-latest` or a dated snapshot. Defaults to the latest version. title: Model required: - classes responses: '200': description: v1-ade-classify result content: application/json: schema: description: The Classify API response body. properties: classification: description: One classification result per page, in page order. items: properties: class: description: Predicted class label, or 'unknown'. type: string reason: description: Why the page was classified this way. type: string suggested_class: anyOf: - type: string - type: 'null' description: >- A class the model proposes when the prediction is 'unknown'. page: description: Page number, zero-indexed (the first page is 0). type: integer required: - class - reason - page title: ClassificationItem type: object title: Classification type: array metadata: $ref: '#/components/schemas/V1ClassifyMetadata' description: Metadata for the classification request. required: - classification - metadata title: V1ClassifyResponse type: object '422': description: Request validation failed. content: application/json: schema: $ref: '#/components/schemas/V1LegacyErrorResponse' x-codeSamples: - lang: cURL label: cURL source: |- curl -X POST 'https://api.ade.landing.ai/v1/ade/classify' \ -H 'Authorization: Bearer YOUR_API_KEY' \ -F 'document=@document.pdf' \ -F 'classes=[{"class":"invoice","description":"A commercial bill with line items, totals, and payment terms"},{"class":"bank_statement","description":"A monthly summary of account transactions"}]' - lang: Python label: Python source: >- import json import requests url = 'https://api.ade.landing.ai/v1/ade/classify' headers = {'Authorization': 'Bearer YOUR_API_KEY'} files = {'document': open('document.pdf', 'rb')} data = {'classes': json.dumps([{"class": "invoice", "description": "A commercial bill with line items, totals, and payment terms"}, {"class": "bank_statement", "description": "A monthly summary of account transactions"}])} response = requests.post(url, headers=headers, files=files, data=data) print(response.json()) - lang: JavaScript label: Node.js source: >- const axios = require('axios'); const FormData = require('form-data'); const fs = require('fs'); const form = new FormData(); form.append('document', fs.createReadStream('document.pdf')); form.append('classes', JSON.stringify([{"class": "invoice", "description": "A commercial bill with line items, totals, and payment terms"}, {"class": "bank_statement", "description": "A monthly summary of account transactions"}])); axios.post('https://api.ade.landing.ai/v1/ade/classify', form, { headers: { 'Authorization': 'Bearer YOUR_API_KEY', ...form.getHeaders() } }) .then(response => console.log(response.data)) .catch(error => console.error(error)); components: schemas: V1ClassifyMetadata: description: Response metadata for a classify call. properties: page_count: description: Number of pages classified. title: Page Count type: integer duration_ms: description: End-to-end request duration in milliseconds. title: Duration Ms type: integer filename: default: '' description: Name of the classified file. title: Filename type: string org_id: anyOf: - type: string - type: 'null' default: null description: Organization ID. title: Org Id credit_usage: default: 0 description: Credits billed for this request. title: Credit Usage type: number job_id: default: '' description: >- The job ID for this request. When present, it correlates with the request's entry in your billing dashboard. Empty when no usage entry was recorded for the request. title: Job Id type: string version: anyOf: - type: string - type: 'null' default: null description: Resolved classify pipeline version that produced this response. title: Version required: - page_count - duration_ms title: V1ClassifyMetadata type: object V1LegacyErrorResponse: title: V1LegacyErrorResponse description: >- The v1 error envelope: `message` for a request-validation failure and for an authentication, payment or permission rejection (401/402/403), `error` for every other rejection, never both. `code` is always present. oneOf: - type: object required: - code - message properties: code: type: string description: Stable snake_case error code. message: type: string description: Human-readable detail. - type: object required: - code - error properties: code: type: string description: Stable snake_case error code. error: type: string description: Human-readable detail. ```` This documentation is built and hosted on [Mintlify](https://mintlify.com), a developer documentation platform.