> For the complete documentation index, see [llms.txt](https://docs.telys.ai/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://docs.telys.ai/reference/glossary.md).

# Glossary

Core Telys terms. Each links to a page that goes deeper.

| Term                 | Definition                                                                                                                                             |
| -------------------- | ------------------------------------------------------------------------------------------------------------------------------------------------------ |
| **Collection**       | A named set of vectors plus metadata with a fixed `dim`, `dtype`, partition key, and embedder profile — the unit you create, query, and save.          |
| **Partition**        | A physical slice of a collection keyed by the `partition_by` column; searches and the IVF index are per-partition.                                     |
| **scope\_key**       | Helper that joins several parts into one partition-key string with the `\x1f` separator, since `partition_by` keys on one column.                      |
| **Embedder**         | An object that turns text into `(N, D)` float32 vectors and carries an `EmbeddingProfile` defining its vector space.                                   |
| **space\_id**        | A `sha256:`-prefixed fingerprint of an `EmbeddingProfile`; two embedders are interchangeable only when their `space_id` values match.                  |
| **EmbeddingProfile** | The frozen dataclass (`provider`, `model_id`, `dimension`, `normalization`, `distance`, …) that identifies a vector space and computes its `space_id`. |
| **IVF**              | Inverted-file index that clusters vectors into lists so search scans only the nearest lists instead of every row.                                      |
| **nprobe**           | How many IVF lists a query scans; higher raises recall and latency, lower lowers both.                                                                 |
| **target\_recall**   | The fraction of true nearest neighbours a query should return; tuning picks `nprobe` to meet it.                                                       |
| **exact-crossover**  | The row-count threshold below which the engine runs exact brute-force search instead of the approximate IVF path.                                      |
| **Runtime**          | The signed native engine that executes every collection operation; loaded lazily and not shipped in the thin SDK.                                      |
| **Kernel**           | The native library (`libame_kernel`) that computes the Algenta lexical embeddings; force its path with `$TELYS_KERNEL`.                                |
| **Signed bundle**    | The verified runtime install — libraries plus `telys_manifest.json`, its signature, and a license — checked offline before use.                        |
| **License**          | An offline RS256 JWT (`products.telys`, ver 2) proving your tier and features; verified on install and, optionally, at `serve` boot.                   |
| **Device-code**      | The RFC 8628 browser sign-in flow `telys login` uses to bind this machine to your account (`--token` for headless/CI).                                 |

## See also

<table data-view="cards"><thead><tr><th></th><th></th><th data-hidden data-card-target data-type="content-ref"></th></tr></thead><tbody><tr><td><strong>How Telys works</strong></td><td>The concepts above, in context.</td><td><a href="/pages/4dMaM8DFGDPl772eoH6B">/pages/4dMaM8DFGDPl772eoH6B</a></td></tr><tr><td><strong>Search internals (IVF)</strong></td><td>IVF, nprobe, and exact-crossover explained.</td><td><a href="/pages/34ekyTEaG3dG24136d0C">/pages/34ekyTEaG3dG24136d0C</a></td></tr><tr><td><strong>Embeddings &#x26; vector spaces</strong></td><td>Embedders, profiles, and space_id.</td><td><a href="/pages/RzDIZEyqpor8emxw5SUJ">/pages/RzDIZEyqpor8emxw5SUJ</a></td></tr><tr><td><strong>SDK API index</strong></td><td>The full public surface.</td><td><a href="/pages/noudKEHV7DgrGM5qy5p6">/pages/noudKEHV7DgrGM5qy5p6</a></td></tr></tbody></table>


---

# Agent Instructions
This documentation is published with GitBook. GitBook is the documentation platform designed so that both humans and AI agents can read, navigate, and reason over technical content effectively. Learn more at gitbook.com.

## Querying This Documentation
If you need additional information that is not directly available in this page, you can query the documentation dynamically by asking a question.

Perform an HTTP GET request on the current page URL with the `ask` query parameter, and the optional `goal` query parameter:

```
GET https://docs.telys.ai/reference/glossary.md?ask=<question>&goal=<endgoal>
```

`ask` is the immediate question: it should be specific, self-contained, and written in natural language.
`goal` is optional and describes the broader end goal you are ultimately trying to accomplish on behalf of the user. GitBook uses it to tailor the answer towards what is most useful for that goal.

The response will contain a direct answer to the question and relevant excerpts and sources from the documentation.

Use this mechanism when the answer is not explicitly present in the current page, you need clarification or additional context, or you want to retrieve related documentation sections.