[BUG]: Default ingest pipeline via CLI skips OCR extract_text

[hwolff99]

Version

2026.8.7.dev20260807180251 commit: b3c8a37

Which installation method(s) does this occur on?

Source

Describe the bug.

When retriever ingest default pipeline runs with an image that contains just text it does not go into the lancedb. ocr_kwargs["extract_text"] never is set to True in the default pipeline, so the ingestion pipeline is like "since there are no tables, charts there's nothing in this image to ingest." But there is something to ingest.

On
2026.8.7.dev20260807180251 commit: b3c8a37363f5

Minimum reproducible example

Sample files to test are attached.

retriever ingest scanned_doc.png api_changelog.txt --lancedb-uri /tmp/b --table-name t

output is
Ingested 2 file(s) → 1 row(s) in LanceDB /tmp/b/t.

On the other hand, if you run

retriever ingest --method ocr scanned_doc.png api_changelog.txt --lancedb-uri /tmp/b --table-name t2

output is
Ingested 2 file(s) → 2 row(s) in LanceDB /tmp/b/t2.

Other/Misc.

api_changelog.txt

[iamdevdhanush]

Hi! I'd like to investigate and work on this issue. I can reproduce the default CLI ingestion behavior and will keep the fix scoped to the OCR configuration path, with a regression test. Please let me know if anyone is already working on this.