Knowledge base
Ground the assistant's answers in your client's business instead of the model's guesses
Attach files and URLs so the assistant answers from your client's real content — we extract, chunk, embed, and retrieve only what's relevant per question.
Add sources
- Open the Knowledge tab inside an assistant.
- Files — PDF, DOCX, TXT, CSV, Markdown. PDF / DOCX up to 50 MB, TXT up to 10 MB.
- URLs — crawled on add, re-fetched on a schedule.
- Plain text — paste an FAQ, policy, or opening hours.
How it's used
- Every reply runs vector search over the knowledge base; only the top chunks enter the LLM context (top-3, dynamic score threshold).
- Short items (hours, policies) can be marked non-vector — inlined into the system prompt so the AI always sees them.
- Embeddings use
text-embedding-3-large, stored in Qdrant. The assistant calls the built-insearchKnowledgetool on demand. - System-managed entries (e.g. allergens, compliance text) are read-only and kept in sync centrally.
Next
- Tools & webhook actions — give it real actions, not just info
- AI control — when the AI hands off to a human
- Channels — wire it to Telegram, Instagram, WhatsApp, voice