Moduletrace/cobble
2
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases 32 Wiki Activity

Keep searchable text only in knowledgebases

Browse Source 
Every bot file was chunked into bot_file_chunks and embedded into
bot_file_vectors, and uploads kept their extracted text in
media.text_content, which together took most of the database. Bot
files are no longer indexed: bots find them by name or path with
list_files and read them with read_file, and search_files, ingest_file
and the files modal's re-read button are gone. Attachments keep no
text; a reply reads a document from the file. Only knowledgebase
documents keep text.

The schema drops both tables and the ingest columns. At boot,
dropStoredFileText removes what older versions stored (file jobs,
upload text) and vacuums once much of the database is free. The
media:prune-text script it replaces is removed.

Co-Authored-By: Claude Opus 5.5 <[email protected]>
This commit is contained in:
tben
2026-10-28 04:44:46 +01:00
co-authored by Claude Opus 5.5
parent 2896e76256
commit ac3ebc43d4
55 changed files with 271 additions and 1712 deletions
Download Patch File Download Diff File Expand all files Collapse all files
src/file-ingest/process-ingest-job.ts
+7 -34
View File
@@ -1,6 +1,5 @@
import BunSQLite from "@moduletrace/bun-sqlite";
import type { BUN_SQLITE_COBBLE_FILE_INGEST_QUEUE } from "@/db/types/db";
import ingestBotFile from "@/src/functions/backend/db/bot-files/ingest-bot-file";
import ingestKnowledgebaseDocument from "@/src/functions/backend/db/knowledgebases/ingest-knowledgebase-document";
import { logError } from "@/src/functions/backend/logger";
import settleFailedIngestJob from "./settle-failed-ingest-job";
@@ -10,56 +9,30 @@ type Params = {
};
/**
* Ingests one queued file (or knowledgebase document) and completes (or
* fails) its job. One that was deleted meanwhile is simply done.
* Ingests one queued knowledgebase document and completes (or fails) its
* job. One that was deleted meanwhile is simply done, and so is a job
* without a document (bot files are no longer indexed).
*/
export default async function processIngestJob({ job }: Params) {
if (!job.id) return;
if (job.document_id) return await processDocumentJob({ job_id: job.id, document_id: job.document_id });
if (!job.file_id) {
if (!job.document_id) {
await BunSQLite.queue.complete({ table: "file_ingest_queue", id: job.id }).catch(() => {});
return;
}
try {
const result = await ingestBotFile({ file_id: job.file_id });
await ingestKnowledgebaseDocument({ document_id: job.document_id });
await BunSQLite.queue.complete({ table: "file_ingest_queue", id: job.id });
if (result.status == "ingested") {
BunSQLite.sql({
sql: `UPDATE bot_files SET ingest_error = NULL WHERE id = ?`,
values: [job.file_id],
}).catch(() => {});
}
} catch (error) {
const { deferred } = await settleFailedIngestJob({ job_id: job.id, error });
if (deferred) return;
await logError({
title: `Bot file #${job.file_id} couldn't be ingested`,
title: `Knowledgebase document #${job.document_id} couldn't be ingested`,
error,
metadata: { file_id: job.file_id },
}).catch(() => {});
}
}
async function processDocumentJob({ job_id, document_id }: { job_id: number; document_id: number }) {
try {
await ingestKnowledgebaseDocument({ document_id });
await BunSQLite.queue.complete({ table: "file_ingest_queue", id: job_id });
} catch (error) {
const { deferred } = await settleFailedIngestJob({ job_id, error });
if (deferred) return;
await logError({
title: `Knowledgebase document #${document_id} couldn't be ingested`,
error,
metadata: { document_id },
metadata: { document_id: job.document_id },
}).catch(() => {});
}
}