Parse - NDI Platform API

import { NdiClient, isParseResult } from "ndi-sdk";

const client = new NdiClient();
const upload = await client.documents.createUpload("report.pdf");
const job = await client.jobs.wait(
  (await client.documents.parse(upload, { wait_seconds: 30 })).job_id,
  { timeout: 600 },
);
if (isParseResult(job.result)) {
  console.log(job.result.markdown);
}

ocr_applied on the result says whether OCR ran.

Method signature

parse(
  source: DocumentSource | UploadResponse,
  opts?: {
    page_ranges?: PageRange[];
    quality?: "auto";
    ocr?: ParseOcrOptions;
    output?: ParseOutputOptions;
    figures?: ParseFiguresOptions;
    diagrams?: ParseDiagramsOptions;
    chunking?: ParseChunkingOptions;
    spreadsheet?: ParseSpreadsheetOptions;
    password?: string;
    wait_seconds?: number;
    idempotency_key?: string;
  },
): Promise<Job>

Parameters

Parameter	Type	Required	Description
`source`	`DocumentSource` or `UploadResponse`	Yes	Upload handle, URL, workspace file, or prior parse
`opts.page_ranges`	`PageRange[]`	No	Inclusive 1-indexed ranges
`opts.quality`	`"auto"`	No	Only accepted value
`opts.ocr`	`ParseOcrOptions`	No	`mode`: `auto` / `force` / `disabled`
`opts.output`	`ParseOutputOptions`	No	`formats`, `table_format`, `include_images`
`opts.figures`	`ParseFiguresOptions`	No	Default `describe`; also `omit` / `include`
`opts.diagrams`	`ParseDiagramsOptions`	No	`omit` or `mermaid`
`opts.chunking`	`ParseChunkingOptions`	No	`none` / `page` / `section`
`opts.spreadsheet`	`ParseSpreadsheetOptions`	No	Sheet, row, and column filters
`opts.password`	`string`	No	Encrypted PDF; write-only
`opts.wait_seconds`	`number`	No	Hold the HTTP response open (max 300)
`opts.idempotency_key`	`string`	No	Override the minted header

Returns

A Job. Narrow with isParseResult(job.result). result.markdown is a convenience alias for result.document.markdown.

Options

import { NdiClient, isParseResult } from "ndi-sdk";

const client = new NdiClient();
const upload = await client.documents.createUpload("report.pdf");
const job = await client.jobs.wait(
  (
    await client.documents.parse(upload, {
      page_ranges: [{ start: 1, end: 1 }],
      output: { formats: ["markdown", "blocks"], table_format: "html" },
      chunking: { strategy: "page" },
      wait_seconds: 30,
    })
  ).job_id,
);
if (isParseResult(job.result)) {
  console.log(job.result.document.chunks?.length);
}

Reuse a parse with { type: "parse_result", job_id }. Page selection and include_images are not available on that source. See Parse guide and Parse response.