> ## 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 Build Extract Schema > Generate a JSON schema from Markdown using AI. This endpoint analyzes Markdown content and generates a JSON schema suitable for use with the extract endpoint. It can also refine an existing schema based on new documents or iterate on a schema based on prompt instructions. For EU users, use this endpoint: `https://api.va.eu-west-1.landing.ai/v1/ade/extract/build-schema`. ## OpenAPI ````yaml /ade/va_openapi_ade2.json post /v1/ade/extract/build-schema openapi: 3.1.0 info: title: >- LandingAI Agentic Document Extraction (ADE) Gen1 API: Parse, Extract, Classify, Split, Section version: 0.1.0 description: >- Convert documents such as PDFs, images, and Office files into structured data with LandingAI's Agentic Document Extraction (ADE) v1 endpoints. Includes Parse (documents to Markdown and structured chunks with grounding), Extract (schema-based field extraction), Classify (page-level classification), Split (separate multi-document files), and Section (hierarchical table of contents), plus asynchronous jobs for parsing and extraction. Documentation: https://docs.landing.ai servers: - url: https://api.va.landing.ai description: Production API security: [] paths: /v1/ade/extract/build-schema: post: tags: - Tools summary: ADE Build Extract Schema description: |- Generate a JSON schema from Markdown using AI. This endpoint analyzes Markdown content and generates a JSON schema suitable for use with the extract endpoint. It can also refine an existing schema based on new documents or iterate on a schema based on prompt instructions. For EU users, use this endpoint: `https://api.va.eu-west-1.landing.ai/v1/ade/extract/build-schema`. operationId: tool_ade_build_schema_v1_ade_extract_build_schema_post requestBody: content: multipart/form-data: schema: $ref: '#/components/schemas/BuildSchemaRequest' required: true responses: '200': description: Successful Response content: application/json: schema: $ref: '#/components/schemas/BuildSchemaResponse' '422': description: Validation Error content: application/json: schema: $ref: '#/components/schemas/HTTPValidationError' security: - Basic Auth: [] x-codeSamples: - lang: cURL label: cURL source: >- curl -X POST 'https://api.va.landing.ai/v1/ade/extract/build-schema' \ -H 'Authorization: Bearer YOUR_API_KEY' \ -F 'markdowns=@markdown.md' \ -F 'model=extract-latest' \ -F 'prompt=Extract invoice fields including vendor, date, and total amount' - lang: Python label: Python source: >- import requests headers = { 'Authorization': 'Bearer YOUR_API_KEY' } url = 'https://api.va.landing.ai/v1/ade/extract/build-schema' # Prepare files and data files = [('markdowns', open('markdown.md', 'rb'))] data = { 'model': 'extract-latest', 'prompt': 'Extract invoice fields including vendor, date, and total amount' } response = requests.post(url, files=files, data=data, headers=headers) 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('markdowns', fs.createReadStream('markdown.md')); form.append('model', 'extract-latest'); form.append('prompt', 'Extract invoice fields including vendor, date, and total amount'); axios.post('https://api.va.landing.ai/v1/ade/extract/build-schema', form, { headers: { 'Authorization': 'Bearer YOUR_API_KEY', ...form.getHeaders() } }) .then(response => console.log(response.data)) .catch(error => console.error(error)); components: schemas: BuildSchemaRequest: properties: model: anyOf: - type: string - type: 'null' title: Model description: >- The version of the model to use for schema generation. Use `extract-latest` to use the latest version. markdowns: anyOf: - items: anyOf: - type: string format: binary - type: string type: array - type: 'null' title: Markdowns description: >- Markdown files or inline content strings to analyze for schema generation. Multiple documents can be provided for better schema coverage. markdown_urls: anyOf: - items: type: string type: array - type: 'null' title: Markdown Urls description: URLs to Markdown files to analyze for schema generation. prompt: anyOf: - type: string - type: 'null' title: Prompt description: Instructions for how to generate or modify the schema. schema: anyOf: - type: string - type: 'null' title: Schema description: Existing JSON schema to iterate on or refine. type: object title: BuildSchemaRequest BuildSchemaResponse: properties: extraction_schema: type: string title: Extraction Schema description: The generated JSON schema as a string. metadata: $ref: '#/components/schemas/BuildSchemaMetadata' description: The metadata for the schema generation process. type: object required: - extraction_schema - metadata title: BuildSchemaResponse HTTPValidationError: properties: detail: items: $ref: '#/components/schemas/ValidationError' type: array title: Detail type: object title: HTTPValidationError BuildSchemaMetadata: properties: filename: anyOf: - type: string - type: 'null' title: Filename org_id: anyOf: - type: string - type: 'null' title: Org Id duration_ms: type: integer title: Duration Ms default: 0 credit_usage: type: number title: Credit Usage default: 0 job_id: type: string title: Job Id default: '' version: anyOf: - type: string - type: 'null' title: Version warnings: items: $ref: '#/components/schemas/ExtractWarning' type: array title: Warnings description: >- Structured warnings from the extraction process. Each warning is an instance of ExtractWarning with 'code' (e.g. 'nonconformant_schema') and 'msg' (human-readable description). Present only for extract versions from extract-20260314 and above that support structured warnings. type: object title: BuildSchemaMetadata ValidationError: properties: loc: items: anyOf: - type: string - type: integer type: array title: Location msg: type: string title: Message type: type: string title: Error Type type: object required: - loc - msg - type title: ValidationError ExtractWarning: properties: code: $ref: '#/components/schemas/ExtractWarningCode' description: The type of warning, used to translate to a status code downstream msg: type: string title: Msg description: Human-readable description of the warning with more details type: object required: - code - msg title: ExtractWarning ExtractWarningCode: type: string enum: - nonconformant_schema - nonconformant_output title: ExtractWarningCode securitySchemes: Basic Auth: type: http description: >- Your unique API key for authentication. Get your API key here: https://va.landing.ai/settings/api-key. If using the EU endpoint, get your API key here: https://va.eu-west-1.landing.ai/settings/api-key. scheme: bearer bearerFormat: Basic ```` This documentation is built and hosted on [Mintlify](https://mintlify.com), a developer documentation platform.