tbenandClaude Opus 5.5
e7b23b7454
Knowledgebases give bots RAG over documents, scoped like extensions: to particular bots, to a workspace, or to every bot, with their own button beside Tools in the composer. Documents are chunked and embedded by the file-ingest worker with the install's embedding model, which is now an install-wide setting rather than a per-bot one. - Word search runs on an FTS5 index ranked by BM25, with a scored LIKE fallback for scripts written without spaces. - Changing the embedding model re-indexes documents automatically. - Ingest jobs wait without spending attempts while every embedding model rests, fail at once on errors retrying can't fix, and keep passages searchable by words when the model refuses. - Settings > Knowledgebases shows each knowledgebase's and document's index state: spinner, warning, grey check (words only) or green check. Co-Authored-By: Claude Opus 5.5 <[email protected]>
106 lines
3.4 KiB
TypeScript
106 lines
3.4 KiB
TypeScript
/**
|
|
* The harnesses: what a model is used for. Each harness has one model
|
|
* setting (`harness_settings`). Text is the brain and can't be turned off;
|
|
* the others are helpers it calls on. `automatic` ones pick a free model
|
|
* themselves when none is picked; the rest (transcription, speech,
|
|
* embeddings) are not available until one is, since free picks there
|
|
* rarely work. `install_wide` ones take only the default setting (Settings
|
|
* > Models): no bot or workspace can pick its own, since every vector they
|
|
* write must come from the same model to be compared.
|
|
*/
|
|
export const Harnesses = [
|
|
{
|
|
title: "Text",
|
|
value: "text",
|
|
automatic: true,
|
|
description: `Chats, plans and works on computers. Every bot thinks with it.`,
|
|
required: true,
|
|
install_wide: false,
|
|
},
|
|
{
|
|
title: "Media reading",
|
|
value: "vision",
|
|
automatic: true,
|
|
description: `Reads images, scans and screenshots for the text model when it can't see them itself.`,
|
|
required: false,
|
|
install_wide: false,
|
|
},
|
|
{
|
|
title: "Transcription",
|
|
value: "transcription",
|
|
automatic: false,
|
|
description: `Turns voice messages and recordings into text.`,
|
|
required: false,
|
|
install_wide: false,
|
|
},
|
|
{
|
|
title: "Speech",
|
|
value: "speech",
|
|
automatic: false,
|
|
description: `Reads bot replies aloud.`,
|
|
required: false,
|
|
install_wide: false,
|
|
},
|
|
{
|
|
title: "Image generation",
|
|
value: "image",
|
|
automatic: true,
|
|
description: `Makes images when a bot is asked for one.`,
|
|
required: false,
|
|
install_wide: false,
|
|
},
|
|
{
|
|
title: "Embeddings",
|
|
value: "embedding",
|
|
automatic: false,
|
|
description: `Turns the files bots save and every knowledgebase into vectors, so bots search them by meaning. One model for the whole install. Without one, searching falls back to plain text matching.`,
|
|
required: false,
|
|
install_wide: true,
|
|
},
|
|
] as const;
|
|
|
|
export type HarnessKind = (typeof Harnesses)[number]["value"];
|
|
|
|
/**
|
|
* Whether a harness takes only the install's default setting.
|
|
*/
|
|
export function isInstallWideHarness({ harness }: { harness: HarnessKind }) {
|
|
return Boolean(Harnesses.find((h) => h.value == harness)?.install_wide);
|
|
}
|
|
|
|
/**
|
|
* The `app_settings` key holding the install's own limit on model turns in
|
|
* one run (a task). Unset means `AppData.HarnessMaxToolSteps`.
|
|
*/
|
|
export const HarnessMaxToolStepsSettingKey = "harness_max_tool_steps";
|
|
|
|
/**
|
|
* Vendors preferred for automatic picks, best first. Free models from any
|
|
* other vendor come after these, and only if they look competent.
|
|
*/
|
|
export const AutoModelVendorPreference = [
|
|
"deepseek",
|
|
"qwen",
|
|
"nvidia",
|
|
"liquid",
|
|
] as const;
|
|
|
|
/**
|
|
* Routers that pick a model themselves (e.g. `openrouter/free`). Used as
|
|
* the last automatic pick, after every named model.
|
|
*/
|
|
export const AutoModelRouterSlugs = ["openrouter/free"];
|
|
|
|
/**
|
|
* Models with one narrow job (moderation, embeddings, ranking). Never
|
|
* picked automatically.
|
|
*/
|
|
export const SpecialistModelPattern =
|
|
/guard|safety|moderation|embed|rerank|classif/i;
|
|
|
|
/**
|
|
* Names of small variants, ranked after their bigger siblings.
|
|
*/
|
|
export const SmallModelPattern =
|
|
/(?:^|[-_.:/])(nano|mini|small|lite|lightning|tiny|micro|xs)(?=$|[-_.:])/i;
|