> ## Documentation Index > Fetch the complete documentation index at: https://docs.meibel.ai/llms.txt > Use this file to discover all available pages before exploring further. # Submit a deep-transform extraction reusing a parsed document (async) > Submit an extraction that reuses an already-parsed document (by `document_job_id` from POST /documents) instead of re-parsing an upload. Returns immediately with a job id. Poll status via GET /documents/deep-transform/{job_id} and download artifacts once it succeeds. Submission is idempotent on the (document, schema) pair. ## OpenAPI ````yaml /api-v2.json post /documents/deep-transform/from-document openapi: 3.1.0 info: title: Meibel AI API summary: Meibel Gateway Service description: >- Our API allows you to interact with our services. Read the [docs](https://docs.meibel.ai) to learn how to use it. version: 0.6.4 servers: - url: https://api.meibel.ai/v2 description: Meibel API (v2) - url: https://api.dev.meibel.ai/v2 description: Meibel Dev API (v2) - url: http://localhost:8000/v2 description: Local Development security: [] tags: - name: Datasources description: v2 datasource management - name: Data Elements description: v2 data element CRUD and search - name: File Upload description: Upload files to a datasource and track upload progress - name: Ingest description: Trigger and monitor datasource ingestion - name: Datasource Downloads description: Export all datasource content as a zip archive - name: Table Descriptions description: v2 table and column descriptions - name: Metadata Model Catalog description: v2 metadata model catalog - name: Confidence Scoring description: v2 confidence scoring jobs and summaries - name: Documents description: Parse and transform documents into structured data - name: Agents description: Agent definition management - name: Sessions description: Agent session (execution) management and chat - name: Execution Policies description: Data access and tool usage constraints scoped to agent sessions - name: Artifact Schemas description: Agent artifact schema management paths: /documents/deep-transform/from-document: post: tags: - Documents summary: Submit a deep-transform extraction reusing a parsed document (async) description: >- Submit an extraction that reuses an already-parsed document (by `document_job_id` from POST /documents) instead of re-parsing an upload. Returns immediately with a job id. Poll status via GET /documents/deep-transform/{job_id} and download artifacts once it succeeds. Submission is idempotent on the (document, schema) pair. operationId: submitDeepTransformFromDocument requestBody: content: application/json: schema: $ref: '#/components/schemas/SubmitDeepTransformFromDocument' required: true responses: '202': description: Successful Response content: application/json: schema: $ref: '#/components/schemas/SubmitDeepTransformResponse' '422': description: Validation Error content: application/json: schema: $ref: '#/components/schemas/HTTPValidationError' security: - APIKeyHeader: [] x-codeSamples: - lang: Python label: Python source: |- import os from meibel import MeibelClient from meibel.models import SubmitDeepTransformFromDocument client = MeibelClient(api_key=os.environ["MEIBEL_API_KEY"]) schema = { "title": "Invoice", "type": "object", "properties": { "invoice_number": {"type": "string"}, "total_amount": {"type": "number"}, "due_date": {"type": "string", "format": "date"}, }, "required": ["invoice_number", "total_amount"], } response = client.documents.submit_deep_transform_from( SubmitDeepTransformFromDocument( document_job_id="docjob_8f3a1c2e9b", schema=schema, root_name="Invoice", guidance="Extract line items from the invoice's charges table", max_pages=10, ) ) print(f"Submitted deep-transform job: {response.job_id}") - lang: TypeScript label: TypeScript source: >- import { MeibelClient } from "meibel"; const client = new MeibelClient({ apiKey: process.env.MEIBEL_API_KEY }); const response = await client.documents.submitDeepTransformFrom({ document_job_id: "doc_job_9f8a7b6c5d", schema: { title: "Invoice", type: "object", properties: { invoice_number: { type: "string" }, total_amount: { type: "number" }, line_items: { type: "array", items: { type: "object", properties: { description: { type: "string" }, quantity: { type: "integer" }, unit_price: { type: "number" }, }, }, }, }, required: ["invoice_number", "total_amount"], }, root_name: "Invoice", guidance: "Extract line items exactly as they appear, preserving original ordering", max_pages: 10, }); console.log(`Submitted deep-transform job: ${response.job_id}`); - lang: Go label: Go source: "package main\n\nimport (\n\t\"context\"\n\t\"fmt\"\n\t\"os\"\n\n\tv2 \"github.com/meibel-ai/meibel-go/v2\"\n)\n\nfunc main() {\n\tclient := v2.NewClient(v2.WithAPIKey(os.Getenv(\"MEIBEL_API_KEY\")))\n\n\tschema := map[string]any{\n\t\t\"title\": \"Invoice\",\n\t\t\"type\": \"object\",\n\t\t\"properties\": map[string]any{\n\t\t\t\"invoice_number\": map[string]any{\"type\": \"string\"},\n\t\t\t\"total_amount\": map[string]any{\"type\": \"number\"},\n\t\t\t\"due_date\": map[string]any{\"type\": \"string\", \"format\": \"date\"},\n\t\t},\n\t\t\"required\": []string{\"invoice_number\", \"total_amount\"},\n\t}\n\n\tresp, err := client.Documents.SubmitDeepTransformFrom(context.Background(), v2.SubmitDeepTransformFromDocument{\n\t\tDocumentJobID: \"doc_job_9f8a7b6c5d4e\",\n\t\tSchema: schema,\n\t\tRootName: v2.String(\"Invoice\"),\n\t\tGuidance: v2.String(\"Extract totals from the final summary table, not line items\"),\n\t})\n\tif err != nil {\n\t\tpanic(err)\n\t}\n\n\tfmt.Printf(\"Submitted deep-transform job: %s\\n\", resp.JobID)\n}" components: schemas: SubmitDeepTransformFromDocument: properties: document_job_id: type: string title: Document Job Id description: >- A document job id returned by POST /documents. Reuses that parse so the document is not parsed again. The document must belong to the calling customer. schema: additionalProperties: true type: object title: Schema description: JSON Schema of the entities to extract root_name: anyOf: - type: string - type: 'null' title: Root Name description: >- Name of the root entity in the schema. Optional: when omitted it is resolved from the schema's `title` or inferred during extraction. guidance: anyOf: - type: string - type: 'null' title: Guidance description: Optional domain guidance for the extraction max_pages: anyOf: - type: integer - type: 'null' title: Max Pages description: Optional cap on the number of pages to process type: object required: - document_job_id - schema title: SubmitDeepTransformFromDocument description: Reuse an already-parsed document instead of re-parsing an upload. SubmitDeepTransformResponse: properties: job_id: type: string title: Job Id description: Poll status via GET /documents/deep-transform/{job_id} type: object required: - job_id title: SubmitDeepTransformResponse HTTPValidationError: properties: detail: items: $ref: '#/components/schemas/ValidationError' type: array title: Detail type: object title: HTTPValidationError ValidationError: properties: loc: items: anyOf: - type: string - type: integer type: array title: Location msg: type: string title: Message type: type: string title: Error Type input: title: Input ctx: type: object title: Context type: object required: - loc - msg - type title: ValidationError securitySchemes: APIKeyHeader: type: apiKey in: header name: Meibel-API-Key ````