Lookio Docs
Lookio websiteOpen Lookio
GuidesFile formats

File formats

The file formats Lookio reads, the size limit of each, how each one is read, and what to do with a format that is not supported.

Lookio reads each format with the reader that fits it best. The app, the API and the engine accept the same formats and the same sizes.

flowchart LR F["Your file"] --> E{"Extension"} E -- "pdf, images, pptx" --> O["OCR<br/>keeps page numbers"] E -- "docx, odt, xlsx, html" --> M["Conversion to Markdown<br/>keeps headings and tables"] E -- "csv, tsv" --> C["CSV parser<br/>finds the delimiter"] E -- "txt, md, json" --> T["Read as is"] O --> P["Passages Lookio searches"] M --> P C --> P T --> P
Which reader reads your file

Accepted formats

FormatExtensionsSize limitRead with
PDF, scans includedpdf50 MBOCR
Imagespng jpg jpeg webp gif bmp tif tiff avif20 MBOCR
PowerPointpptx ppsx30 MBOCR
Word and OpenDocument textdocx docm odt25 MBConversion to Markdown
Spreadsheetsxlsx xlsm xls xlsb ods numbers25 MBConversion to Markdown
CSVcsv tsv90 MBLookio’s own parser
Saved web pageshtml htm xml8 MBConversion to Markdown
Texttxt md markdown mdx json5 MBRead as is. A JSON file that lists rows is read as a table

The limit is per file. The extension sets the format. The first bytes of a binary file must match its extension: a text file renamed .pdf is refused.

How each reader behaves

  • OCR reads text from PDFs, including scans, from images and from slides. The text keeps page markers, so a citation can name the page.
  • Conversion to Markdown keeps headings, lists and tables of Word, OpenDocument, spreadsheet and HTML files.
  • CSV finds the delimiter and the encoding. An export with semicolons from a European tool works.
  • Text files are indexed as they are. Markdown headings become sections.

After an import, open the resource and choose View the text. You see what Lookio read and what it could not read. See Resources.

Formats Lookio does not read

Lookio refuses these formats before it stores anything, and says what to do.

FormatWhat to do
docOpen the file in Word and save it as docx.
pptSave it as pptx, or export it as PDF.
odpExport it as PDF or pptx.
rtfSave the document as docx.
pagesIn Pages, use File, Export To, Word or PDF.
keyIn Keynote, use File, Export To, PowerPoint or PDF.
epubNot supported yet. Export the book as PDF.
zipNot supported yet. Add the files one by one.
heicExport the photo as JPEG or PNG.

Lookio also refuses any other extension, an empty file, and a file over its limit. The error gives the file’s size and the limit for its format.

Upload

In the app, drop files on the Files tab of Add a resource, or click to choose them. You can add several files at once, with the same tags and source. Each file becomes one resource.

Over the API, send the file’s bytes as the request body to POST /v1/resources/file, with its name in file_name. With the CLI, run lookio resources add-file ./handbook.pdf. The CLI streams the file from the disk.

If an upload stops before the end, Lookio refuses it and creates nothing.

Use these docs with your AI tools

An AI agent can read this documentation directly. You do not need an account or an API key. Everything here is public and read-only.

Query these docs via MCP

Recommended

Add this server to Claude, Claude Code, Cursor, Mistral, or any tool that supports MCP. Your agent can then search Lookio Docs documentation and read it in full, instead of answering from memory.

https://lookio.app/docs/mcp
  • searchFind the passages that answer a question.
  • fetchRead one page in full, as Markdown.
  • list_pagesSee every page in this documentation.

Query these docs over HTTP

The same tools also work as plain web requests. Use this for scripts, or for any tool that does not support MCP. There is one endpoint per tool. Arguments go in the query string, and the answer comes back as JSON.

https://lookio.app/docs/api/docs/search?query=custom+domain

Read the OpenAPI description. It is built from the same definitions as the tools, so it always matches what the endpoints do.

Read these docs as Markdown

Add .md to any page URL to get its Markdown source. You can also send the headerAccept: text/markdown to the page URL itself.

To read the whole documentation in one file, open llms-full.txt. For a short index of every page, open llms.txt.