Quickstart - LandingAI

Use the Playground to explore and understand basic concepts without writing code. When you’re ready to scale intelligent document processing, follow the tutorial below to get started with code.

Prerequisites

An account
An API key

Tutorial: Parse and Extract a Document

This tutorial guides you through how to parse a sample bank statement and extract these fields: Account Holder Name and Number of Deposits.

cURL
Python
TypeScript

Install jq

Install jq, a free third-party command-line tool that will help you save files later in this procedure. Some common install instructions are below; to see all installation methods, go the the jq site.

brew install jq

Parse a document

Run the code below to parse a sample bank statement with the API. The > at the end of the command saves the response to a file called parse-output.json.Replace YOUR_API_KEY with your API key.

curl -X POST 'https://api.va.landing.ai/v1/ade/parse' \
  -H 'Authorization: Bearer YOUR_API_KEY' \
  -F 'document_url=https://docs.landing.ai/examples/bank-statement.pdf' \
  -F 'model=dpt-2-latest' > parse-output.json

Save the Markdown content

To extract data from the document, you need to pass the markdown field from parse-output.json to the API.Run the following command to save the markdown field to a file called markdown-bank-statement.md.

jq -r .markdown parse-output.json > markdown-bank-statement.md

Extract fields from a document

Now that the parsed output is in a Markdown file, run the code below to extract the Account Holder Name and Number of Deposits fields using the API.Replace YOUR_API_KEY with your API key.

curl -X POST 'https://api.va.landing.ai/v1/ade/extract' \
  -H 'Authorization: Bearer YOUR_API_KEY' \
  -F 'schema={"type": "object", "properties": {"name": {"type": "string", "description": "Account holder name"}, "number_deposits": {"type": "integer", "description": "The number of deposits"}}}' \
  -F 'markdown=@markdown-bank-statement.md' \
  -F 'model=extract-latest'

The API response includes the extracted fields:

Account Holder Name: Sarah J. Mitchell
Number of Deposits: 5

    {
    "extraction":{
      "name":"Sarah J. Mitchell",
      "number_deposits":5
    },
    "extraction_metadata":{
      "name":{
        "references":[
          "8b70276e-a3ee-4ed4-9f11-15439c50d603"
        ],
        "value":"Sarah J. Mitchell"
      },
      "number_deposits":{
        "references":[
          "d9d59d6d-cf43-4ed2-8632-5f48d08885c5"
        ],
        "value":5
      }
    },
    "metadata":{
      "filename":"markdown-bank-statement.md",
      "org_id":"lgy5xucm9xnq",
      "duration_ms":6516,
      "credit_usage":1.5188,
      "job_id":"1bdcf9c99a614d698f3b4aca65f27935",
      "version":"extract-20260314",
      "schema_violation_error":null,
      "fallback_model_version":null,
      "warnings":[
        
      ]
    }
  }

Set the API key as an environment variable

Get your API key and set it as an environment variable. For more details, go to API Key.

export VISION_AGENT_API_KEY=<your-api-key>

Install the Python library

Install the library.

pip install landingai-ade

Create your code

This example shows the complete workflow of parsing a sample bank statement and extracting the Account Holder Name and Number of Deposits fields. If you only need to parse documents, use just the parsing section.Save the code block below as quickstart.py.

import json
from landingai_ade import LandingAIADE

# Initialize the client
client = LandingAIADE()

##### Parse the document #####

# Parse the document
parse_response = client.parse(
    document_url="https://docs.landing.ai/examples/bank-statement.pdf",
    model="dpt-2-latest",
    save_to="./output"  # optional: saves the full response as JSON for later reference
)

print("Full Parse response saved to ./output/")

##### Extract fields from the parsed document #####

# Define which fields to extract. Each property specifies a field name and its expected data type.
schema_dict = {
    "type": "object",
    "properties": {
        "name": {
            "type": "string",
            "description": "Account holder name"
        },
        "number_deposits": {
            "type": "integer",
            "description": "The number of deposits"
        }
    }
}

# Convert schema dictionary to JSON string
schema_json = json.dumps(schema_dict)

# Extract fields using the parsed markdown
extract_response = client.extract(
    schema=schema_json,
    markdown=parse_response.markdown,  # Parse converts the document to Markdown; Extract uses it to identify and pull specific fields
    model="extract-latest",
    save_to="./output"  # optional: saves the full response as JSON for later reference
)

print("Full Extract response saved to ./output/")

# Print the extracted fields
print("\nExtracted fields:")
print(extract_response.extraction)

Run your code

Run the Python file you created.

python quickstart.py

The script parses the document and saves both responses to ./output/. The extracted fields returned are:

Account Holder Name: Sarah J. Mitchell
Number of Deposits: 5

Extracted fields:
{'name': 'Sarah J. Mitchell', 'number_deposits': 5}

Set the API key as an environment variable

Get your API key and set it as an environment variable. For more details, go to API Key.

export VISION_AGENT_API_KEY=<your-api-key>

Install the TypeScript library

Install the library.

npm install landingai-ade

Create your code

import LandingAIADE from "landingai-ade";

// Initialize the client
const client = new LandingAIADE();

///// Parse the document /////

// Parse the document
const parseResponse = await client.parse({
  document: await fetch("https://docs.landing.ai/examples/bank-statement.pdf"),
  model: "dpt-2-latest",
  saveTo: "./output"  // optional: saves the full response as JSON for later reference
});

console.log("Full Parse response saved to ./output/");

///// Extract fields from the parsed document /////

// Define which fields to extract. Each property specifies a field name and its expected data type.
const schemaDict = {
  type: "object",
  properties: {
    name: {
      type: "string",
      description: "Account holder name"
    },
    number_deposits: {
      type: "integer",
      description: "The number of deposits"
    }
  }
};

// Convert schema object to JSON string
const schemaJson = JSON.stringify(schemaDict);

// Extract fields using the parsed markdown
const extractResponse = await client.extract({
  schema: schemaJson,
  markdown: parseResponse.markdown,  // Parse converts the document to Markdown; Extract uses it to identify and pull specific fields
  model: "extract-latest",
  saveTo: "./output"  // optional: saves the full response as JSON for later reference
});

console.log("Full Extract response saved to ./output/");

// Print the extracted fields
console.log("\nExtracted fields:");
console.log(extractResponse.extraction);

Run your code

Run the TypeScript file you created.

npx tsx quickstart.ts

The script parses the document and saves both responses to ./output/. The extracted fields returned are:

Account Holder Name: Sarah J. Mitchell
Number of Deposits: 5

Extracted fields:
{ name: 'Sarah J. Mitchell', number_deposits: 5 }

Next Steps: Develop and Scale

Choose how you want to integrate into your workflow. Build with AI agents, call the API directly, or use our Python and TypeScript libraries.

Build with AI Agents

Use ADE skills, an MCP server, and llms.txt with your AI agents and coding tools.

API

Call the API directly for language flexibility and advanced customization.

Python Library

Use our Python library to build custom scripts.

TypeScript Library

Use our TypeScript library to build custom scripts.

Sample Scripts & Projects

Use these sample scripts and projects for real-world use cases as templates to develop your own custom document processing solutions.

Sample Projects

Explore end-to-end examples for common document processing workflows.

Sample Scripts in Documentation

Browse code samples with examples for the Python and TypeScript libraries.

​Prerequisites

​Tutorial: Parse and Extract a Document

​Next Steps: Develop and Scale