> ## 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.

# Document Pre-Trained Transformers (Parsing Models)

> Choose a parsing model (DPT) and set it when parsing files.

export const adePythonLibrary = 'ade-python';

export const dpt2 = 'DPT-2';

export const dpt1 = 'DPT-1';

export const dpt = 'Document Pre-Trained Transformer';

export const companyName = 'LandingAI';

export const extract = 'ADE Extract';

export const parse = 'ADE Parse';

export const ade = 'Agentic Document Extraction';

## Parsing Models Overview

A **{dpt}** (DPT) is the model that powers the parsing capabilities of the ADE Parsing APIs. The DPT identifies document layouts and chunks, then generates descriptive explanations (captions) for those chunks.

## Availability

The ability to select a {dpt} is available:

* in the [Playground](#set-the-model-in-the-playground)
* when calling the [{parse}](#set-the-model-in-the-api) or [Parse Jobs](https://docs.landing.ai/api-reference/tools/ade-parse-jobs) APIs
* when using the [Python](https://github.com/landing-ai/ade-python) and [TypeScript](https://github.com/landing-ai/ade-typescript) libraries

## Model Versions and Snapshots

The following table lists the available `model` values for the {parse} and ADE Async Parse API:

| Model Values   | Description                                                                             |
| -------------- | --------------------------------------------------------------------------------------- |
| dpt-2          | The latest snapshot of {dpt2}.                                                          |
| dpt-2-latest   | The latest snapshot of {dpt2}.                                                          |
| dpt-2-20250919 | The snapshot of {dpt2} released on September 19, 2025.                                  |
| dpt-2-20251103 | The snapshot of {dpt2} released on November 3, 2025.                                    |
| dpt-2-20260302 | The snapshot of {dpt2} released on March 2, 2026. [See improvements.](#dpt-2-20260302)  |
| dpt-2-20260410 | The snapshot of {dpt2} released on April 10, 2026. [See improvements.](#dpt-2-20260410) |

<Info>
  The `dpt-2-mini` model is deprecated. Use `dpt-2` instead.
</Info>

### Why Model Versioning Matters

When integrating the API, you have two options for specifying the model:

1. **Use a general model name** (like `dpt-2` or `dpt-2-latest`) to always get the newest version. This automatically give you improvements and updates, but parsing results may change when new model versions are released
2. **Use a specific snapshot** (like `dpt-2-20250919`) to pin to an exact model version. This ensures consistent parsing results over time, but you won't receive improvements.

If you use only a general model name like `dpt-2` in production, your application may produce different results when we release model updates. Consider whether you need consistent results or prefer to receive the latest improvements.

### Understanding Snapshots and -latest

**Snapshots** are frozen versions of a model released on specific dates. Each snapshot maintains the same parsing behavior indefinitely, making your results predictable.

The **latest** suffix always points to the most recent snapshot of that model.

## DPT-2

{dpt2} was introduced in September 2025.

It builds upon an earlier model, and offers these advanced features:

* **Agentic Table Captioning**: {dpt2} can parse large, complex, no-gridline, and merged-cell tables with unprecedented fidelity. Every cell is preserved, aligned, and made accessible—enabling cell-level grounding so you know exactly where values came from.
* **Refined Figure Captioning**: Logos, seals, and small figures are now identified precisely and concisely, eliminating the noise of verbose descriptions.
* **Smarter Layout Detection**: Fewer chunks are missed, even in messy scans. {dpt2} can even detect stamps inside tables and process them separately—critical for compliance workflows.
* **Expanded Chunk Ontology**: Beyond text, tables, and figures, {dpt2} now recognizes attestation (signatures, stamps, seals), ID cards, logos, barcodes, and QR codes—ensuring all document elements are classified consistently. To learn more, go to [Chunk Types](./ade-chunk-types).

### dpt-2-20260410

The `dpt-2-20260410` snapshot builds on previous {dpt2} snapshots with these improvements:

* **Improved cell parsing in forms and tables**: Text positioned at different locations within a cell is now captured more completely.
* **Improved column alignment in complex tables**: Cell data now more accurately aligns with its corresponding column headers.

### dpt-2-20260302

The `dpt-2-20260302` snapshot builds on previous {dpt2} snapshots with several improvements, including:

* **Table boundary detection**: Tables that were previously split into multiple chunks are now correctly identified as a single table.
* **Improved large table accuracy**: Large tables are now parsed more accurately.
* **Special characters returned as Unicode**: Characters such as asterisks are now returned as their Unicode characters (for example, `*`) rather than as spelled-out strings like `asterisk`.

### DPT-2 Availability

The {dpt2} can be used in these API endpoints:

* [{parse}](https://docs.landing.ai/api-reference/tools/ade-parse)
* [ADE Parse Jobs](https://docs.landing.ai/api-reference/tools/ade-parse-jobs)

## Set the Model in the API

When calling the [{parse}](https://docs.landing.ai/api-reference/tools/ade-parse) or [ADE Parse Jobs](https://docs.landing.ai/api-reference/tools/ade-parse-jobs) endpoint, you can set the model using the `model` parameter.

If you omit the `model` parameter, the API will use the latest snapshot of the `dpt-2` model.

For example, run the command below to use the latest snapshot of {dpt2}.

```shell theme={null}
curl -X POST 'https://api.va.landing.ai/v1/ade/parse' \
  -H 'Authorization: Bearer YOUR_API_KEY' \
  -F 'document=@document.pdf' \
  -F 'model=dpt-2-latest'
```

## Set the Model with the Library

When using the [{adePythonLibrary}](https://github.com/landing-ai/ade-python) library, you can set the model using the `model` parameter in the `parse()` function.

If you omit the `model` parameter, the library will use the latest snapshot of the `dpt-2` model.

For example, use this code to parse a document with the latest snapshot of {dpt2}:

```python theme={null}
from pathlib import Path
from landingai_ade import LandingAIADE

client = LandingAIADE()

response = client.parse(
    document=Path("/path/to/document.pdf"),
    model="dpt-2-latest"
)
```

## Set the Model in the Playground

To select the parsing model in the Playground:

1. Open a project in the [Playground](https://ade.landing.ai/).
2. Click the **Parse** tab.
3. In the top-right corner of the parse result panel, click **Config**.
4. From the **Model** drop-down, select the model you want to use.
5. Click **Re-run all files**.
   <img src="https://mintcdn.com/landingaitest/GuvdNoFKBmKF6N1M/images/parse-config.png?fit=max&auto=format&n=GuvdNoFKBmKF6N1M&q=85&s=423227618e5e037a0865d1f439391d8f" alt="Configure Parse Settings" className="bordered-image" width="1250" height="734" data-path="images/parse-config.png" />

<Info>Switching the model re-parses every file in the project. If you switch back to a model that was already applied to the project, the Playground reuses the cached parse results instead of re-parsing.</Info>