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]>
37 lines
1.1 KiB
TypeScript
37 lines
1.1 KiB
TypeScript
import BunSQLite from "@moduletrace/bun-sqlite";
|
|
import extractBotFileText from "../bot-files/extract-bot-file-text";
|
|
|
|
type Params = {
|
|
document: {
|
|
source?: string | null;
|
|
content?: string | null;
|
|
media_id?: number | null;
|
|
name?: string | null;
|
|
mime_type?: string | null;
|
|
};
|
|
};
|
|
|
|
/**
|
|
* A knowledgebase document's whole text: what was written in, or what its
|
|
* file holds (the text pulled out at upload, else unpacked now).
|
|
*/
|
|
export default async function grabKnowledgebaseDocumentText({ document }: Params) {
|
|
if (document.source == "text") return document.content || "";
|
|
|
|
if (!document.media_id) return "";
|
|
|
|
const media = await BunSQLite.sql<{ media_write_path?: string; text_content?: string }>({
|
|
sql: `SELECT media_write_path, text_content FROM media WHERE id = ? LIMIT 1`,
|
|
values: [document.media_id],
|
|
}).then((res) => res.payload?.[0]);
|
|
|
|
return (
|
|
(await extractBotFileText({
|
|
write_path: media?.media_write_path,
|
|
text_content: media?.text_content,
|
|
name: document.name,
|
|
mime_type: document.mime_type,
|
|
})) || ""
|
|
);
|
|
}
|