RememberStackremember.dev/docs

Supported file types

RememberStack reads text. Every document is turned into Markdown before anything else happens, so what a deployment accepts depends on which formats it can turn into Markdown.

At a glance

On a self-hosted deployment:

FormatAs installedWith converters configured
Markdown, plain text, subtitles (.md, .rst, .txt, .srt, .vtt, …)Read; claims extractedSame
Chat logs and transcripts, as Markdown or textRead; claims extractedSame
HTML, EPUBRead; claims extractedSame
Word (.docx, .docm, .dotx), PowerPoint (.pptx, .pptm, .ppsx, .potx)Read; claims extractedSame
Spreadsheets (.xlsx, .xlsm, .xltx, .xls), CSV/TSV, data files (Parquet, Arrow, SPSS, SAS, Stata, SQLite)Profile: sheets, columns, counts and the first 5 rows; searchable, no claimsSame
.odsProfiled through LibreOffice (in the published image); stored and parked when the engine runs without itSame
.doc, .odt, .rtf, .ppt, .odpRead through LibreOffice (in the published image); stored and parked when the engine runs without itSame
PDF (digital, scanned or mixed)Stored and parked without a Mistral OCR keyEvery page is read with OCR when the key is configured; claims extracted
Email (.eml)Read; attachments listed, not readSame
Jupyter notebooks (.ipynb)Markdown cells read (claims extracted); code cells searchable, no claims; outputs droppedSame
Code, configuration, logs (.py, .ts, .json, .yaml, .log, Dockerfile, …)Read and searchable; no claimsSame
Text files of unknown kindRead and searchable; no claimsSame
ImagesFile card (name, path, size, dimensions)Read with image_ocr_description (PNG and JPEG; OCR plus a written description)
Audio and videoFile cardSame
Archives (.zip, .tar, .tar.gz, .7z, …)File card; zip and tar list their membersSame
Other binary filesFile cardSame
Web addresses (URLs)NoNo: download the page and send the HTML

A Word or PowerPoint file over 100 MB, or a spreadsheet over 200 MB, gets a file card instead of a reading. A PDF over its 100 MB family limit fails conversion without a card (a PDF larger than the OCR provider accepts in one request, about 50 MB or 1,000 pages, is OCR'd in page batches); a spreadsheet over 50 MB is profiled from its sheet list and dimensions only. A text file over 1 MB is described by its size, line count, first 50 and last 20 lines instead of read in full.

The 100 MB and 200 MB limits protect the engine process, which reads the file itself. A deployment whose converter fetches files by a signed URL from S3 storage reads nothing in the engine, so it sends these files to that converter instead; only the converter's own input limit applies.

Formats and converters

A new self-hosted deployment reads the formats above locally, with no API key, and describes images, media and archives with a card. Formats it cannot read yet are accepted and stored, but they wait unprocessed. The upload response tells you: its parked field is "no_route", and remember ingest prints a warning.

To read PDFs, set REMEMBERSTACK_MISTRAL_OCR_API_KEY; every PDF page then uses OCR. To read images, map their type to a converter in REMEMBERSTACK_SELFHOST_CONVERSION_ROUTES. File formats and converters shows the setting, what each converter does and costs, and how to release files that were stored before you added a route.

The image description may quote a small number of clearly legible titles, names or labels as visual observations. OCR remains an independent text reading. Visual quotes do not replace or correct OCR, and image text is evidence rather than instructions. When readings conflict or a detail is unclear, inspect the original image. A new description-prompt version requires a fresh visual reading; completed OCR work can be reused.

Send the right type

A self-hosted deployment checks recognizable bytes before it uses the extension or sent MIME as a format hint. A type that contradicts the bytes is refused with HTTP 422. A text file with no recognizable family is searchable but no claims are extracted from it. The remember CLI, Python client and MCP ingest tool send a hint taken from the extension (the full table). A file whose extension does not say what it is needs the type passed explicitly:

client.ingest("notes/standup", mime="text/markdown")
remember ingest notes/standup --mime text/markdown

Conversations

There is no separate conversation format. Write each conversation as one Markdown document with one line per turn, and send it like any other file. Ingest conversations and transcripts shows the layout.