Add knowledge with uploaded files or live sources (XML, RSS, GitHub) and organize it into semantic search collections.

  • Knowledge Files: Upload documents (PDF, DOC, DOCX, XLS, XLSX) or plain text, source code, and markup (TXT, MD, CSV, XSD, XML, HTML, PAS, PHP, and more). All files are saved as .md. Documents get a converted-from marker; source/markup gets a plain-source marker, ## section headings where applicable, and fenced code blocks — indexed without stripping tags. Word uploads (DOC/DOCX) detect Heading styles and section titles as Markdown ## headings for better splitting when indexing a collection.
  • Output file naming: You can optionally rename the file during upload. Saved knowledge files use the .md extension.
  • Export for GPT / Gem: Use the export button on the Knowledge Files tab to download a ZIP of your knowledge files for Custom GPT or Gemini Gems.
  • Re-index after changes: After uploading or editing files, click Index. Re-index files uploaded before the plain-source change so the collection stores the full content (especially XSD/XML and source code).
  • Edit and structure content: Inside the file editor, you can separate content by paragraph markers, Markdown headings, or blank lines so the search index can split the content more accurately.
  • Per-file collections: Each knowledge file can use the default collection or a specific semantic search collection.
  • Links and images in knowledge: Put the exact product or page URLs (and image URLs) you want the assistant to share inside the indexed content for that topic. The chatbot may only reuse links and images that appear in the knowledge retrieved for the current question — it should not invent or guess URLs.
  • Knowledge Bases: Add live sources from XML, RSS, or GitHub. See the API Reference for XML format details.
  • GitHub sources: You can index public repositories without a token, or private repositories with a GitHub personal access token.
  • File masks: For GitHub sources, you can limit indexing to selected file extensions such as md, php, json, or txt.
  • Incremental updates: Enable this when your source supports modified timestamps and you want faster re-indexing of changed items only.
  • Split items: Leave this enabled for documentation and long-form knowledge. Disable it for catalogs or records that should stay as one indexed item.
  • Example exporters: The Knowledge Bases tab includes downloadable example scripts for WordPress, WooCommerce, OpenCart, WHMCS, and general XML export flows.

Table of contents · Previous: Configure Basic Behavior · Next: Set Up Routing and Search