> For the complete documentation index, see [llms.txt](https://docs.docbits.com/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://docs.docbits.com/administration-and-setup/settings/global-settings/document-types/model-training/import-data-model-training.md).

# Import sample documents for model training

## Prepare, import and check sample documents

<figure><picture><source srcset="https://578966019-files.gitbook.io/~/files/v0/b/gitbook-x-prod.appspot.com/o/spaces%2FT2n2w4uDCJvv7CJ5zrdk%2Fuploads%2Fgit-blob-45a6d1bb45602aaa735927e2b1fc3f28bf459d96%2Fintro-process-04-trainingsimport-en-dark-20261029.png?alt=media" media="(prefers-color-scheme: dark)"><img src="https://578966019-files.gitbook.io/~/files/v0/b/gitbook-x-prod.appspot.com/o/spaces%2FT2n2w4uDCJvv7CJ5zrdk%2Fuploads%2Fgit-blob-59b8a574d2e66812185d1dd5c4c04feeba9763cf%2Fintro-process-04-trainingsimport-en-light-20261029.png?alt=media" alt="Prepare, import and check sample documents"></picture><figcaption><p>Prepare, import and check sample documents</p></figcaption></figure>

Choose representative sample documents, prepare the available import options and check the import status. Only successfully imported samples are ready for subsequent training. Resolve import errors before the next step and keep independent test documents separate from the training dataset.

Prepare documents that represent the formats, languages and document types your organization processes. Use only file formats accepted by your installation. Remove duplicates and keep training documents separate from documents reserved for evaluation.

## Open the import

Open model training in the relevant document type's settings and select the import function.

<figure><img src="https://578966019-files.gitbook.io/~/files/v0/b/gitbook-x-prod.appspot.com/o/spaces%2FT2n2w4uDCJvv7CJ5zrdk%2Fuploads%2Fgit-blob-5374234fac103950a70b38a121b6fefe7165f504%2Fsite-extra-model-training-overview-en.png?alt=media" alt="Model-training overview: available data and actions; no training or import was started."><figcaption><p>Model-training overview: available data and actions; no training or import was started.</p></figcaption></figure>

## Select formats and files

Choose the number and date formats that match the files, then select the documents to import. For example, `1.234,56` and `1,234.56` use different separators. A date such as `05/06/2026` must also be interpreted according to the selected format.

<figure><img src="https://578966019-files.gitbook.io/~/files/v0/b/gitbook-x-prod.appspot.com/o/spaces%2FT2n2w4uDCJvv7CJ5zrdk%2Fuploads%2Fgit-blob-9752817c990171e43260656386518882c0e26c53%2Fmodel-training-import-dialog-en.png?alt=media" alt="Document Uploader dialog opened from Train Model with the Amount &#x26; Date Format selector, the Drag and Drop file(s) here area and the Upload field; no files selected"><figcaption><p>The <strong>Document Uploader</strong> dialog: choose the amount and date format, then select the files.</p></figcaption></figure>

Check the selection before starting the import. Wait for processing to finish and review errors and assigned document types. Correct classification and extraction errors before using the examples for training.

## Train and evaluate

Train the model using the functions and permissions available in your version. Then evaluate it on a separate sample. Adding documents does not itself guarantee higher accuracy. See [Testing the model](https://docs.docbits.com/administration-and-setup/settings/global-settings/document-types/model-training/testing-the-model.md).


---

# Agent Instructions
This documentation is published with GitBook. GitBook is the documentation platform designed so that both humans and AI agents can read, navigate, and reason over technical content effectively. Learn more at gitbook.com.

## Querying This Documentation
If you need additional information that is not directly available in this page, you can query the documentation by asking a question.

Perform an HTTP GET request on the following URL with the `ask` and `goal` query parameters:

```
GET https://docs.docbits.com/administration-and-setup/settings/global-settings/document-types/model-training/import-data-model-training.md?ask=<question>&goal=<user_goal>
```

`ask` is the immediate question: it should be specific, self-contained, and written in natural language.
`goal` is what the user is ultimately trying to achieve, the reason they need the answer. Sharing it helps GitBook give you a better, more relevant answer. A goal is most helpful when it describes the outcome the user wants rather than restating the question. For example, with `ask=how do I create an API token`, a goal like `automate deployments from our CI pipeline` lets GitBook tailor the answer to that use case.

The response will contain a direct answer to the question and relevant excerpts and sources from the documentation.

Use this mechanism when the answer is not explicitly present in the current page, you need clarification or additional context, or you want to retrieve related documentation sections.
