Import files
Your workspace is the set of documents Olyvr can search and cite. Documents arrive through sources: uploaded files, a folder on your computer, or a connected account.
Supported files
Section titled “Supported files”| Type | Extensions | What is read |
|---|---|---|
| Word | .docx |
Paragraphs and tables |
| PowerPoint | .pptx |
Each slide’s text boxes, tables, grouped shapes and speaker notes |
| Excel | .xlsx, .xlsm, .xls |
Every sheet, as rows. A formula reads as the value Excel last calculated for it. Macros are never run. |
.pdf |
The text of every page. Scanned pages are read with OCR, and so is the text in large pictures on a page, such as a photo of a document pasted into a report. | |
| Text and data | .txt, .md, .csv, .tsv, .html, .htm, .json, .yaml, .yml, .xml, .log |
The text |
| Other | .eml (email), .ics (calendar), .py, .js, .ts |
The text |
Google Docs, Slides and Sheets in Google Drive come in through a connected Google account: Docs and Slides as their text, and Sheets with every tab.
Olyvr extracts and indexes the text. OCR runs on your computer, so scanned pages never leave it. It reads up to 50 scanned pages per PDF, within 3 minutes; the document notes any pages it left unread.
Some files can’t be read yet:
- Password-protected PDFs. Unlock them first.
- Images (
.png,.jpgand others) on their own. Put a scan in a PDF to have it read. - The older Word and PowerPoint formats,
.docand.ppt. Save them as.docxor.pptxfirst. Older Excel files (.xls) are read. - Other formats, such as
.rtf,.odt,.zipand files without an extension. - The Google Docs, Sheets and Slides shortcuts that Google Drive for desktop puts in a folder on your computer (
.gdoc,.gsheet,.gslides). They only point to the file online; connect the Google account to import it.
Add a source
Section titled “Add a source”-
Open Memory Data Sources from the sidebar.
-
Choose how to add documents:
- Files: pick one or more files. Olyvr keeps its own copy of each file.
- Folder: choose a folder, or enter its full path. Olyvr imports every supported file inside it, including subfolders, and reads it in place, so every refresh takes the files added, changed or deleted in it. (In a web browser rather than the desktop app, a chosen folder is uploaded as copies, which don’t change; enter the folder’s path to keep it in sync.)
- Account: connect Google, Microsoft or GitHub. See Connect accounts.
-
The source appears with its document count once it is ready.
Limits
Section titled “Limits”- 30 MB per file (up to 120 MB uncompressed for Office files)
- 1,000 pages per PDF, 100,000 rows per worksheet
- 5 million characters of text per file
- No limit on files per folder. A large folder comes in 5,000 files at a time, and the rest follow on their own, even with auto-refresh off.
- Hidden files, links and empty files are skipped, and so are files of a type Olyvr can’t read. When you pick files and one can’t be read, Olyvr names it and says why, such as the file is damaged or invalid for its declared format. A source’s row shows how many of its files could not be imported; Update tries them again.
Keep sources up to date
Section titled “Keep sources up to date”Sources refresh on their own while Olyvr is open, every 30 minutes by default. Change the interval for all sources under Auto-refresh, or for one source in its Refresh column.
A folder on this computer is compared with what was imported last time: only files that are new, or whose size or modified time changed, are read again, and files you deleted leave the workspace. A large folder where little changed refreshes in moments. The source’s row shows what the last refresh brought in, such as 2 new · 1 changed.
Changes made while Olyvr is closed come in at the first refresh after you open it.
Click Update on a source to import it now:
- Folder sources read every file in the folder again. Files whose content didn’t change are left as they are, and files you deleted from the folder are removed from the workspace.
- File sources re-extract their stored copies.
- Account sources collect what changed at the provider.
Each document keeps the same identity across refreshes, so existing citations stay valid.
Turn sources off or remove them
Section titled “Turn sources off or remove them”- Disable a source to hide its documents from search, reading and citations without deleting anything. Enable it again at any time.
- Remove a source to delete it from the workspace. Olyvr’s stored copies are deleted shortly afterwards, unless a chat or project still needs them. Files in your own folders are never touched.
Changing your sources marks generated memory notes as out of date, so you can rebuild them from the current workspace.
How search works
Section titled “How search works”Search is a fast keyword index across every enabled source. It first looks for documents containing all your words, with matches in the file name ranked higher. If nothing matches, it falls back to the most distinctive words in your query. Search does not need a model. It runs entirely on your machine.
The agent uses the same search, then reads the documents that look most relevant before answering.