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]>
150 lines
4.4 KiB
TypeScript
150 lines
4.4 KiB
TypeScript
import BunSQLite from "@moduletrace/bun-sqlite";
|
|
import type {
|
|
BUN_SQLITE_COBBLE_BOT_HARNESS_SETTINGS,
|
|
BUN_SQLITE_COBBLE_HARNESS_SETTINGS,
|
|
BUN_SQLITE_COBBLE_WORKSPACE_HARNESS_SETTINGS,
|
|
} from "@/db/types/db";
|
|
import { isInstallWideHarness, type HarnessKind } from "@/src/dict/harness-dict";
|
|
import parseJobJson from "@/src/bots-queue/parse-job-json";
|
|
import grabDefaultHarnessProviderId from "./grab-default-harness-provider-id";
|
|
|
|
export type HarnessSetting = {
|
|
harness: HarnessKind;
|
|
/**
|
|
* The picked `harness_models` row; undefined picks automatically.
|
|
*/
|
|
model_id?: number;
|
|
/**
|
|
* The `harness_providers` row the harness is limited to (its pick
|
|
* and its automatic picks); undefined: any provider.
|
|
*/
|
|
provider_id?: number;
|
|
fallback: boolean;
|
|
enabled: boolean;
|
|
options: Record<string, unknown>;
|
|
/**
|
|
* `workspace` when the call's workspace sets this harness, `bot` when a
|
|
* worker bot overrides the default for it.
|
|
*/
|
|
source: "default" | "bot" | "workspace";
|
|
};
|
|
|
|
type Params = {
|
|
harness: HarnessKind;
|
|
/**
|
|
* The bot the call is for. A worker bot's own setting wins over the
|
|
* default; the coordinator always uses the default.
|
|
*/
|
|
bot_id?: number | string;
|
|
/**
|
|
* The workspace the call is in. Its setting wins over the bot's, for
|
|
* the coordinator too.
|
|
*/
|
|
workspace_id?: number | string | null;
|
|
};
|
|
|
|
type SettingRow = Pick<
|
|
BUN_SQLITE_COBBLE_HARNESS_SETTINGS,
|
|
"model_id" | "provider_id" | "fallback" | "enabled" | "options"
|
|
>;
|
|
|
|
/**
|
|
* A harness's setting for a call: the workspace's, else the bot's, else
|
|
* the default. With no row it is automatic on the default provider
|
|
* (OpenRouter), on, with fallback. Text is always on. An install-wide
|
|
* harness (embeddings) always takes the default: rows a bot or workspace
|
|
* saved before it was one are ignored.
|
|
*/
|
|
export default async function grabHarnessSetting({
|
|
harness,
|
|
bot_id,
|
|
workspace_id,
|
|
}: Params): Promise<HarnessSetting> {
|
|
const install_wide = isInstallWideHarness({ harness });
|
|
|
|
const workspace_row = workspace_id && !install_wide
|
|
? await grabWorkspaceOverride({ harness, workspace_id })
|
|
: undefined;
|
|
|
|
if (workspace_row) {
|
|
return toSetting({ harness, row: workspace_row, source: "workspace" });
|
|
}
|
|
|
|
const bot_row = bot_id && !install_wide
|
|
? await grabBotOverride({ harness, bot_id })
|
|
: undefined;
|
|
|
|
if (bot_row) {
|
|
return toSetting({ harness, row: bot_row, source: "bot" });
|
|
}
|
|
|
|
const row = (
|
|
await BunSQLite.sql<BUN_SQLITE_COBBLE_HARNESS_SETTINGS>({
|
|
sql: `SELECT * FROM harness_settings WHERE harness = ? LIMIT 1`,
|
|
values: [harness],
|
|
})
|
|
).payload?.[0];
|
|
|
|
if (!row) {
|
|
return {
|
|
...toSetting({ harness, source: "default" }),
|
|
provider_id: await grabDefaultHarnessProviderId(),
|
|
};
|
|
}
|
|
|
|
return toSetting({ harness, row, source: "default" });
|
|
}
|
|
|
|
async function grabWorkspaceOverride({
|
|
harness,
|
|
workspace_id,
|
|
}: {
|
|
harness: HarnessKind;
|
|
workspace_id: number | string;
|
|
}) {
|
|
return (
|
|
await BunSQLite.sql<BUN_SQLITE_COBBLE_WORKSPACE_HARNESS_SETTINGS>({
|
|
sql: `SELECT * FROM workspace_harness_settings WHERE workspace_id = ? AND harness = ? LIMIT 1`,
|
|
values: [workspace_id, harness],
|
|
})
|
|
).payload?.[0];
|
|
}
|
|
|
|
async function grabBotOverride({
|
|
harness,
|
|
bot_id,
|
|
}: {
|
|
harness: HarnessKind;
|
|
bot_id: number | string;
|
|
}) {
|
|
return (
|
|
await BunSQLite.sql<BUN_SQLITE_COBBLE_BOT_HARNESS_SETTINGS>({
|
|
sql: `SELECT s.* FROM bot_harness_settings s
|
|
JOIN bots b ON b.id = s.bot_id
|
|
WHERE s.bot_id = ? AND s.harness = ? AND b.kind != 'coordinator'
|
|
LIMIT 1`,
|
|
values: [bot_id, harness],
|
|
})
|
|
).payload?.[0];
|
|
}
|
|
|
|
function toSetting({
|
|
harness,
|
|
row,
|
|
source,
|
|
}: {
|
|
harness: HarnessKind;
|
|
row?: SettingRow;
|
|
source: HarnessSetting["source"];
|
|
}): HarnessSetting {
|
|
return {
|
|
harness,
|
|
model_id: typeof row?.model_id == "number" ? row.model_id : undefined,
|
|
provider_id: typeof row?.provider_id == "number" ? row.provider_id : undefined,
|
|
fallback: row ? row.fallback != 0 : true,
|
|
enabled: harness == "text" || !row || row.enabled != 0,
|
|
options: parseJobJson({ text: row?.options }) || {},
|
|
source,
|
|
};
|
|
}
|