> ## Documentation Index
> Fetch the complete documentation index at: https://docs.impellabs.tech/llms.txt
> Use this file to discover all available pages before exploring further.

# Knowledge

> What the assistant knows before it calls anything.

Knowledge is what the business has published: uploads, crawled pages, FAQs,
the company profile, and hand-written cards. Retrieval is hybrid — vector
search plus Postgres full-text, fused by reciprocal rank fusion — and runs once
per turn before the model sees anything.

## Knowledge is not your data

<Warning>
  **Never push your live records into knowledge.** Prices, stock and order
  status belong in tools, not in an index.

  Indexed text is a snapshot. A price embedded on Tuesday is quoted on Friday
  with total confidence and no way for the model to know it has changed. The
  assistant is explicitly told that knowledge is background and that live
  figures come from tools.
</Warning>

Use knowledge for what is *semantically* true and slow-moving:

| Belongs in knowledge               | Belongs in a tool      |
| ---------------------------------- | ---------------------- |
| Delivery and returns policy        | Where this order is    |
| Care instructions, size guides     | This design's price    |
| Who the business is, opening hours | Whether it is in stock |
| "How do I…" explanations           | This buyer's cart      |

## Searching from a turn

An assistant with knowledge sources gets `search_knowledge`, which it can call
mid-conversation like any other tool. You do not need to expose knowledge
yourself.

## The context budget

Everything competes for one budget: system prompt, knowledge, memory,
conversation history, and your tool results. When it overflows, the platform
drops in a fixed order — memory first, then knowledge, then it trims the
summary, then the oldest messages. The system prompt and the incoming message
are never dropped.

<Note>
  Long tool results consume that budget. A 4,000-character catalogue dump can
  push out the knowledge the assistant needed to answer the next question.
  Return what was asked for.
</Note>