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]>
33 lines
1.1 KiB
TypeScript
33 lines
1.1 KiB
TypeScript
import BunSQLite from "@moduletrace/bun-sqlite";
|
|
import enqueueDocumentIngest from "@/src/file-ingest/enqueue-document-ingest";
|
|
import grabKnowledgebase from "./grab-knowledgebase";
|
|
|
|
type Params = {
|
|
knowledgebase_id: number | string;
|
|
};
|
|
|
|
/**
|
|
* Reads every document of a knowledgebase again (after the install's
|
|
* embedding model changed, or one failed). Each keeps its old passages
|
|
* until its new ones are in. Returns how many were queued.
|
|
*/
|
|
export default async function reindexKnowledgebase({ knowledgebase_id }: Params) {
|
|
const knowledgebase = await grabKnowledgebase({ knowledgebase_id });
|
|
|
|
const documents = await BunSQLite.sql<{ id: number }>({
|
|
sql: `SELECT id FROM knowledgebase_documents WHERE knowledgebase_id = ?`,
|
|
values: [knowledgebase.id],
|
|
});
|
|
|
|
await BunSQLite.sql({
|
|
sql: `UPDATE knowledgebase_documents SET ingest_error = NULL WHERE knowledgebase_id = ?`,
|
|
values: [knowledgebase.id],
|
|
});
|
|
|
|
for (const document of documents.payload || []) {
|
|
await enqueueDocumentIngest({ document_id: document.id });
|
|
}
|
|
|
|
return documents.payload?.length || 0;
|
|
}
|