LiyaSupport
AI & Knowledge Base

Supported content formats

Every file type and source Liya can index into your knowledge base.

3 min read Updated July 2026

File uploads

FormatExtensionMax sizeNotes
Plain text.txt10 MBUTF-8 encoding required
Markdown.md, .mdx10 MBHeadings, lists, code blocks preserved
PDF.pdf10 MBText extraction only; scanned PDFs require OCR (see below)
Microsoft Word.docx10 MBFormatting stripped; headings preserved as structure
Microsoft Excel.xlsx5 MBEach sheet indexed as a separate section; useful for FAQs in table form
CSV.csv5 MBBest for structured Q&A data; first row treated as header
HTML.html, .htm10 MBNavigation, scripts, and style tags stripped automatically
EPUB.epub10 MBChapters split into separate indexed sections
Scanned PDFs: If your PDF contains scanned images of text rather than actual text characters, Liya cannot extract content without OCR. Convert scanned documents to text-based PDFs using a tool like Adobe Acrobat or an online OCR service before uploading.

URL crawling

Source typeSupport levelNotes
Public HTML pagesFullBoilerplate, navigation, and ads stripped automatically
Public Notion pagesFullHeadings, lists, and callouts preserved
GitHub README / wikiFullPublic repos only
Intercom help centerFullCrawls all public article URLs
Zendesk help centerFullCrawls all public article URLs
HubSpot knowledge baseFullPublic articles only
Pages behind loginNoneUse file upload or native integration instead
JavaScript-rendered SPAsPartialServer-rendered content only; client-only content may be missed
PDFs served via URLFullDownloaded and processed as a file upload

Native integrations

These integrations sync content automatically — no manual uploads needed:

IntegrationWhat syncsSync frequency
NotionSelected pages and databasesReal-time via webhook
Google DocsSelected documents and foldersReal-time via webhook
ConfluenceSelected spaces and pagesEvery 30 minutes
Intercom ArticlesAll published articlesEvery 24 hours
Zendesk Help CenterAll published articlesEvery 24 hours
HubSpot Knowledge BaseAll published articlesEvery 24 hours
GitbookSelected spacesEvery 6 hours

Content that works best

Regardless of format, the content quality matters more than the file type. These characteristics produce the highest AI accuracy:

  • Short, focused articles — one topic per article, 100–400 words
  • Plain language — write as if explaining to a new customer
  • Specific answers — include concrete steps, timelines, and thresholds (e.g. "refunds take 5–7 business days")
  • Question-formatted titles — "How do I cancel my subscription?" rather than "Cancellation policy"
  • No stale content — outdated pricing or deprecated features confuse the AI; archive old articles

Content size limits

When a single file exceeds the optimal chunk size, Liya splits it into sections for indexing. Splitting happens automatically at heading boundaries (h1, h2, h3) or at 1,000-word intervals when no headings are present.

Very large documents (e.g. a 200-page policy manual) are better split manually into topic-specific articles before uploading. This gives Liya finer retrieval precision.