> ## Documentation Index
> Fetch the complete documentation index at: https://docs.runpulse.com/llms.txt
> Use this file to discover all available pages before exploring further.

# Introduction

> Agentic document infrastructure for the enterprise.

Pulse is the document layer for enterprise AI. Agents, data platforms and your own applications use it to read the documents your company holds, from filings and scans to handwritten forms and workbooks.

Pulse turns those documents into AI-ready data: clean Markdown, structured JSON, tables, chart data and a bounding box for every element, so each value traces back to its place on the page.

> [card] [Quickstart](https://docs.runpulse.com/v2/quickstart.md)
>
> Parse a document and extract fields from it in Python, TypeScript or cURL.

> [card] [SDKs](https://docs.runpulse.com/v2/sdks.md)
>
> Install the Python or TypeScript SDK and call every step from your code.

> [card] [Pricing](https://docs.runpulse.com/v2/pricing.md)
>
> See what each step costs in credits, and what is free.

> [card] [API reference](https://docs.runpulse.com/v2/api-reference/overview.md)
>
> Look up every route, field and response.

Pulse reads PDFs, scans and photos, Word documents, PowerPoint decks, Excel workbooks, CSV files and HTML pages. See [Files and limits](https://docs.runpulse.com/v2/files.md) for every format and size limit.

***

## How it works

Every step except Classify reads a parse by its `parse_id`, so you parse a document once and then run as many steps on it as you need. Classify reads the file itself, before any parse.

```mermaid theme={null}
%%{init: {"themeVariables": {"fontSize": "14px"}, "flowchart": {"nodeSpacing": 24, "rankSpacing": 32, "padding": 8}}}%%
flowchart TD
    D[Your document] --> P[Parse]
    D -.->|mixed types| C[Classify]
    P --> M[Markdown and elements]
    P --> T[Tables]
    P --> H[Charts]
    P --> S[Split by topic]
    P --> X[Extract fields]
    S -->|each topic| X
```

Each step returns its own id, and you read the step's result with that id:

```mermaid theme={null}
%%{init: {"themeVariables": {"fontSize": "14px"}, "sequence": {"mirrorActors": false, "messageMargin": 28, "height": 44, "boxMargin": 6}}}%%
sequenceDiagram
    participant App as Your app
    participant Pulse
    App->>Pulse: POST /parse (file_url, config)
    Pulse-->>App: parse_id
    App->>Pulse: POST /extract (parse_id, schema)
    Pulse-->>App: extract_id
    App->>Pulse: GET /extract/{extract_id}/result
    Pulse-->>App: values with citations
```

***

## Endpoints

> [card] [Parse](https://docs.runpulse.com/v2/parse.md)
>
> Turn a document into Markdown and elements, with figures, footnotes or chunks.

> [card] [Extract](https://docs.runpulse.com/v2/extract.md)
>
> Fill a JSON Schema from a parse, with a citation for each value.

> [card] [Split](https://docs.runpulse.com/v2/split.md)
>
> Find each topic's pages, to route them or extract each one.

> [card] [Tables](https://docs.runpulse.com/v2/tables.md)
>
> Get every table as HTML, JSON or Markdown, merged across pages.

> [card] [Charts](https://docs.runpulse.com/v2/charts.md)
>
> Read each chart's series and points, and export them to Excel, CSV or LAS.

> [card] [Classify](https://docs.runpulse.com/v2/classify.md)
>
> Sort a document into the categories you name, before you parse it.

## Run at scale

> [card] [Pipelines](https://docs.runpulse.com/v2/pipelines.md)
>
> Parse a document and run up to 10 steps on it in one call.

> [card] [Batch](https://docs.runpulse.com/v2/batch.md)
>
> Parse up to 1,000 documents with one config.

> [card] [Saved configs](https://docs.runpulse.com/v2/saved-configs.md)
>
> Save an endpoint's config once, then send its `config_id`.

> [card] [Webhooks](https://docs.runpulse.com/v2/webhooks.md)
>
> Hear when your jobs change status, with signed deliveries.

## Cookbooks

> [card] [Split, then extract](https://docs.runpulse.com/v2/cookbooks/split-then-extract.md)
>
> Extract each section of a long report with its own small schema.

> [card] [Highlight sources](https://docs.runpulse.com/v2/cookbooks/highlight-sources.md)
>
> Draw an extracted value's exact words on the page.

> [card] [RAG ingestion](https://docs.runpulse.com/v2/cookbooks/rag-ingestion.md)
>
> Chunk a parse, with metadata that traces answers to pages.

> [card] [Cloud intake](https://docs.runpulse.com/v2/cookbooks/cloud-intake.md)
>
> Parse a bucket of documents as one batch.

***

## Base URL

Send every request to:

```
https://api.runpulse.com
```

Every request needs an API key. [Authentication](https://docs.runpulse.com/v2/authentication.md) shows how to create one and send it.

## Need help?

> [card] [Support](https://docs.runpulse.com/v2/support.md)
>
> How to reach Pulse, and what to send with a question.

> [card] [Moving from V1](https://docs.runpulse.com/v2/moving-from-v1.md)
>
> Map your version 1 calls to version 2.


This documentation is built and hosted on [Mintlify](https://mintlify.com), a developer documentation platform.