> For the complete documentation index, see [llms.txt](https://gaffa.dev/docs/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://gaffa.dev/docs/features/browser-requests/actions/generate-markdown.md). # Generate Markdown Type: `generate_markdown` The Markdown output format exports page data (articles, tables, etc.) in a human- and LLM-readable format, removing unnecessary styling and other "junk" that is only relevant to the site's proper functioning. Gaffa exports [GitHub-flavoured markdown](https://github.github.com/gfm/) with comments removed and unknown tags ignored.
Tips for using generate_markdown * Use this as your default when sending page content to an LLM. It keeps headings, lists, tables and links, and drops the rest. * Add a `selector` to focus on a particular area of the page and cut out the noise. Pointing at `article` or `main` skips navigation, sidebars and footers. * Use `output_type: "inline"` to get the Markdown straight back in the response. Use `file` for long pages. * Use [`generate_simplified_dom`](/docs/features/browser-requests/actions/generate-simplified-dom.md) instead if you need selectors, because Markdown drops classes and attributes.
### Parameters
NameTypeRequiredDescription
selectorstringfalseThe selector that defines an element you want to generate markdown from. This is useful if you are only interested in the contents of a certain element.
output_typestringfalseShould the action output be saved to a file where a URL will be returned or should the output be included directly in the request.

Default: file
Accepted: ["file", "inline"]
See [universal parameters](/docs/features/browser-requests/actions.md#universal-parameters). ### Usage The following converts the current page to Markdown: ```json "actions": [ { "type": "generate_markdown" } ] ``` The following converts only a specific element to Markdown and returns it inline: ```json "actions": [ { "type": "generate_markdown", "selector": "article", "output_type": "inline" } ] ``` ### Example Output {% file src="/files/mTvssb40IQyvq8lyNhhG" %} ### FAQs #### When do I use generate\_markdown? Use it when you want the readable content of a page, article, listing, or documentation page, especially for sending to an LLM. It's the cleanest and smallest output Gaffa produces. #### What does generate\_markdown output? It outputs GitHub-flavoured Markdown of the page, with comments removed and unknown tags ignored. Headings, lists, links and tables are kept. Styling and scripts are stripped out. #### How do I convert only part of a page to Markdown? Set the `selector` parameter to the element you want, like `"article"` or `"main"`. Gaffa converts only that element's contents, so you skip navigation, sidebars and footers. #### Should I use file or inline output? Use `inline` to get the Markdown directly in the response, which suits agents and shorter pages. Use `file`, the default, when the page is long. #### **When should I use capture\_dom instead of generate\_markdown?** Use [`capture_dom`](/docs/features/browser-requests/actions/capture-dom.md) when you need the actual markup attributes, scripts, and full link URLs. Use `generate_markdown` when you only need the content, which is most of the time. #### When should I use parse\_json instead of generate\_markdown? Use [`parse_json`](/docs/features/browser-requests/actions/parse-json.md) when you need specific fields in a fixed structure. Use `generate_markdown` when you want the whole page as text and will handle the rest yourself. #### Does generate\_markdown keep tables? Yes, as Markdown tables. If you plan to process the table in code, use [`parse_table`](/docs/features/browser-requests/actions/parse-table.md) instead; it returns proper JSON rows rather than text. #### Should I use file or inline output for generate\_markdown? Use `inline` to get the Markdown directly in the action's `output` field, which suits agents and shorter pages. Use `file` (the default) when the page is long — that returns a storage URL instead. --- # 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 dynamically by asking a question. Perform an HTTP GET request on the current page URL with the `ask` query parameter, and the optional `goal` query parameter: ``` GET https://gaffa.dev/docs/features/browser-requests/actions/generate-markdown.md?ask=&goal= ``` `ask` is the immediate question: it should be specific, self-contained, and written in natural language. `goal` is optional and describes the broader end goal you are ultimately trying to accomplish on behalf of the user. GitBook uses it to tailor the answer towards what is most useful for that goal. 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.