Skip to main content
Langdock supports the following file types: Text-based files:
File TypeFile ExtensionFile Size Limit
PDF.pdf256 MB
Markdown.md10 MB
Text.txt10 MB
Word.docx, .doc, .dotx256 MB
PowerPoint.pptx, .ppt, .potx256 MB
JSON.json10 MB
SharePoint Site Pages.aspx256 MB
Outlook Email.msg256 MB
For text-based files, there’s an additional 8 million character limit that applies alongside the file size limit. So a PDF, for example, can be up to 256 MB in file size or hit the 8 million character limit. Knowledge bases accept supported text based formats such as PDF, DOCX, TXT, Markdown, and presentations. Tabular Files:
File TypeFile ExtensionFile Size Limit
Excel / Google Sheets.xlsx, .xls, .xlsm, .xltx, .xltm, .xlam, .xlsb30 MB
CSV.csv30 MB
TSV.tsv30 MB
Tabular files can be uploaded directly in chat, Agents, and Library Folders for active file work, and they sync from SharePoint or Google Drive folders via Folder Sync. They cannot be uploaded to Knowledge bases. Spreadsheets in Recent Files support preview with sheet tabs, zoom, column resizing, and formula inspection. For technical details, see tabular files in Knowledge bases. Images:
File TypeFile ExtensionFile Size Limit
JPG.jpg20 MB
PNG.png20 MB
WebP.webp20 MB
GIF.gif20 MB
TIFF.tiff20 MB
BMP.bmp20 MB
HEIF.heif20 MB
HEIC.heic20 MB
Images can be uploaded in chat conversations, Agent chats, and Library Folders. They cannot be uploaded to Knowledge bases or agent knowledge. Audio Files
File TypeFile ExtensionFile Size Limit
Audio files.mp3, .wav, .ogg, .mpeg, .mp4, .m4a, .vnd.wave200 MB
Audio files can be uploaded in chat conversations and Agent chats. They cannot be uploaded to Knowledge bases, Library Folders, or agent knowledge.

FAQ

A file type can be generally supported but still fail because of file size, corruption, password protection, scan quality, unusual encoding, or content that cannot be extracted reliably. Try a smaller or cleaner version of the file and check whether the file works as a direct upload or should be converted first.
No. Spreadsheets and tabular files often need different handling from text documents. If exact rows, formulas, or calculations matter, use the file directly in a chat or workflow designed for data analysis instead of assuming it will behave like a text document in retrieval.