Knowledge bases

Getting content in

• Upload files directly — documents, spreadsheets, PDFs.
• Paste URLs, or crawl a site to pull in a documentation set.
• Promote files from your library — the account-scoped file store — into any knowledge base.

Content is chunked and embedded into a vector index automatically. Indexing state is visible on every source — a knowledge base tells you when it's still processing rather than silently answering from half the corpus.

How retrieval works

Retrieval is hybrid: vector similarity and keyword search are fused, results expand to neighbouring passages for context, and re-ranking applies time decay so newer material outranks stale duplicates. You don't configure any of this — it's how every query runs.

Knowledge search is also available directly: passage-level results with similarity scores the interface explains honestly (cosine similarity between your query and the passage — not a percentage, and not comparable across different queries).

Citations

Grounded answers cite the passages they used. The correct way to evaluate this — or any — RAG system: upload documents you know well, ask a question they answer, and check a citation. If the platform can't show you where an answer came from, it's asking you to trust the vibe.

Plan limits

• Free: 3 knowledge bases, 50 documents each — enough to run a real evaluation.
• Paid plans raise knowledge base counts, document counts, and file storage.
• Team and Business add shared, org-wide knowledge bases governed by roles.