feat(jobs): blob worker fans out to extract.pdf / extract.image

After creating a ref, the Node-side ingest.blob worker enqueues a
follow-up job for the Python void-workers (Plan 4) to OCR / extract
text. Other kinds (file) get no follow-up.

Co-Authored-By: Claude Opus 4.7 <noreply@anthropic.com>
This commit is contained in:
root
2026-06-01 09:34:06 +10:00
parent f2035c1de6
commit 3d82f0e5d5
2 changed files with 33 additions and 0 deletions

View File

@@ -1,6 +1,7 @@
import fs from 'node:fs/promises';
import * as refs from '../../db/repos/refs.js';
import { defaultStore } from '../../ingest/blob_store.js';
import * as queue from '../queue.js';
export const NAME = 'ingest.blob';
@@ -27,5 +28,12 @@ export async function handler(job) {
blob_path: path,
metadata: { sha, content_type, filename, size: buf.length, ...(meta.metadata || {}) }
}, { kind: 'system', id: null });
// Plan 4: hand off to the Python void-workers for OCR / extraction.
if (kind === 'pdf') {
await queue.enqueue('extract.pdf', { ref_id: row.id, blob_path: path });
} else if (kind === 'image') {
await queue.enqueue('extract.image', { ref_id: row.id, blob_path: path });
}
return { ref_id: row.id, sha };
}