Quickstart

Get started with the Parse API by parsing a sample customer due diligence form. You submit the document as a Parse Job, then collect a structured Markdown rendering of it, ready for downstream workflows like RAG, search, or extraction. If you would rather not write the request yourself, the CLI Quickstart gets the same result in two commands.

Prerequisites

An Agentic Document Extraction account
An API key

Tutorial: Parse a Document

Python
TypeScript
cURL

Set the API key as an environment variable

The library reads your API key from the VISION_AGENT_API_KEY environment variable.

export VISION_AGENT_API_KEY="<your-api-key>"

set "VISION_AGENT_API_KEY=<your-api-key>"

$env:VISION_AGENT_API_KEY="<your-api-key>"

Install the Python library

Install the ade-python library.

pip install landingai-ade

Create your code

The wait method polls the job for you and returns it once it reaches a terminal state. Save the code block below as parse.py.

from landingai_ade import LandingAIADE

client = LandingAIADE()

job = client.v2.parse_jobs.create(
    document_url="https://docs.landing.ai/examples/kyc-form.pdf",
    service_tier="standard",
)
done = client.v2.parse_jobs.wait(job.job_id, raise_on_failure=True)

with open("markdown-kyc-form.md", "w") as f:
    f.write(done.result.markdown)

Run your code

Run the file you created. The script saves the parsed Markdown to markdown-kyc-form.md in the current directory.

python3 parse.py

Set the API key as an environment variable

The library reads your API key from the VISION_AGENT_API_KEY environment variable.

export VISION_AGENT_API_KEY="<your-api-key>"

set "VISION_AGENT_API_KEY=<your-api-key>"

$env:VISION_AGENT_API_KEY="<your-api-key>"

Install the TypeScript library

Install the ade-typescript library.

npm install landingai-ade

Create your code

The wait method polls the job for you and returns it once it reaches a terminal state. Save the code block below as parse.ts.

import fs from "fs";
import LandingAIADE from "landingai-ade";

const client = new LandingAIADE();

const job = await client.v2.parseJobs.create({
  document_url: "https://docs.landing.ai/examples/kyc-form.pdf",
  service_tier: "standard",
});
const done = await client.v2.parseJobs.wait(job.job_id, { raiseOnFailure: true });
const parsed = done.result as LandingAIADE.V2ParseResponse;

if (!parsed.markdown) {
  throw new Error(`Job ${job.job_id} returned no Markdown (status: ${done.status}).`);
}
fs.writeFileSync("markdown-kyc-form.md", parsed.markdown);

Run your code

Run the file you created. The script saves the parsed Markdown to markdown-kyc-form.md in the current directory.

npx tsx parse.ts

Install jq

Install jq, a free third-party command-line tool that reads values out of the JSON responses. Some common install instructions are below; to see all installation methods, go to the jq site.

brew install jq

winget install jqlang.jq

sudo apt-get install jq

Create the parse job

Submit the document and capture the job_id from the response into a shell variable. Replace YOUR_API_KEY with your API key.

JOB_ID=$(curl -s -X POST 'https://api.ade.landing.ai/v2/parse/jobs' \
  -H 'Authorization: Bearer YOUR_API_KEY' \
  -F 'document_url=https://docs.landing.ai/examples/kyc-form.pdf' \
  -F 'service_tier=standard' | jq -r .job_id)

The request returns a 202 response carrying the job_id, the job’s status, and its creation time:

{
  "job_id": "parse-01m1cn0y1k88schxxtgz97vpw2",
  "status": "pending",
  "created_at": "2026-08-31T19:34:01.015456+00:00"
}

Collect the result

Fetch the job and save the response to parse-output.json. Re-run this command until status reads completed. If it reads failed, stop and check the error field for the reason.

curl -s "https://api.ade.landing.ai/v2/parse/jobs/$JOB_ID" \
  -H 'Authorization: Bearer YOUR_API_KEY' > parse-output.json

jq -r .status parse-output.json

Save the Markdown content

A finished job nests the parse output under result, so the Markdown is at .result.markdown. Save it to a file called markdown-kyc-form.md.

jq -r .result.markdown parse-output.json > markdown-kyc-form.md

Use the Markdown

Open markdown-kyc-form.md. It holds the form as reading-order Markdown, ready for a RAG application, a search index, or an LLM prompt. To pull named fields out of it instead, pass it to Extract.

What’s Next

How Parse Works

Understand the response shape in depth: pages, blocks, and grounding.

Extract Data

Pull named fields out of this Markdown with a schema.

Credit Consumption

See how credit usage is calculated per page.

Troubleshoot

Status codes, errors, and how to resolve them.

Get Started

Client Libraries

Parsing

Extraction

Grounding

General

Security

Administration

Pricing & Credits

Prerequisites

Tutorial: Parse a Document

Use the Markdown

What’s Next

How Parse Works

Extract Data

Credit Consumption

Troubleshoot

​Prerequisites

​Tutorial: Parse a Document

​Use the Markdown

​What’s Next

How Parse Works

Extract Data

Credit Consumption

Troubleshoot

Prerequisites

Tutorial: Parse a Document

Use the Markdown

What’s Next