> For clean Markdown of any page, append .md to the page URL.
> For a complete documentation index, see https://docs.emtelligent.com/llms.txt.
> For AI client integration (Claude Code, Cursor, etc.), connect to the MCP server at https://docs.emtelligent.com/_mcp/server.

# emtelligent Documentation

emtelligent provides a set of APIs for working with unstructured clinical
documents. Each one is complete in itself: use a single API for a specific job,
or combine several as your requirements grow.

#### [OCR API](/ocr/overview)

Make documents machine-readable, preserving tables and layout — PDFs,
images and multi-page TIFFs, with reading order intact.

#### [Prep API](/prep/overview)

Break a large bundle into its constituent documents, classify them against
a document-type ontology, OCR and extract metadata.

#### [NLP API](/nlp/overview)

Code and structure data from clinical documents: medical terms, assertions
and relationships, mapped to standard ontologies.

#### [Extract API](/extract/overview)

Run complex, multi-step extraction pipelines, including cross-document data
aggregation, returning structured clinical data.

#### [Platform](/platform/overview)

Accounts and sign-in, API keys and OAuth clients, billing and usage, and
Chart Review seats.

## Choosing an API

| If you need to…                                                                              | Use                              |
| -------------------------------------------------------------------------------------------- | -------------------------------- |
| Make documents machine-readable, preserving tables and layout                                | [OCR API](/ocr/overview)         |
| Break a large bundle into its constituent documents, classify them, OCR and extract metadata | [Prep API](/prep/overview)       |
| Code and structure data from clinical documents                                              | [NLP API](/nlp/overview)         |
| Run complex, multi-step extraction pipelines including cross-document data aggregation       | [Extract API](/extract/overview) |

## How the APIs relate

Every API can be called directly. Some also use others internally, so you do not
have to coordinate the pieces yourself:

* The **Prep API** uses the OCR API behind the scenes, so documents are made
  machine-readable as part of splitting and classification.
* The **Extract API** orchestrates all of our pipelines as needed, returning
  structured clinical data without your having to run those stages yourself.

There is more than one route to the same outcome. If you want coded clinical
data out of a set of documents, the Extract API will do it end to end. If you
need control over an individual stage, or only need one of them, call that API
directly.

## Getting started

Each API's overview covers what it does, its inputs and outputs, and how a
request works. Beyond that:

|                    |                                                                                 |
| ------------------ | ------------------------------------------------------------------------------- |
| **API references** | [OCR](/ocr/api) · [Prep](/prep/api) · [NLP](/nlp/api) · [Extract](/extract/api) |
| **Python**         | [NLP SDK](/nlp/python/overview) · [Prep SDK](/prep/sdk/overview)                |
| **Command line**   | [Prep client](/prep/client/overview)                                            |

To call any API you need a credential from your organization on the emtelligent
platform; click on the Platform link above for further details.

## Support

Email `support@emtelligent.com` for technical support, or `info@emtelligent.com`
for anything commercial.