feat: add support for multimodal indexing#286
Draft
kyteinsky wants to merge 28 commits into
Draft
Conversation
Signed-off-by: Anupam Kumar <kyteinsky@gmail.com>
Signed-off-by: Anupam Kumar <kyteinsky@gmail.com>
Signed-off-by: Anupam Kumar <kyteinsky@gmail.com>
Signed-off-by: Anupam Kumar <kyteinsky@gmail.com>
Signed-off-by: Anupam Kumar <kyteinsky@gmail.com>
Signed-off-by: Anupam Kumar <kyteinsky@gmail.com>
Signed-off-by: Anupam Kumar <kyteinsky@gmail.com>
Signed-off-by: Anupam Kumar <kyteinsky@gmail.com>
Signed-off-by: Anupam Kumar <kyteinsky@gmail.com>
Signed-off-by: Anupam Kumar <kyteinsky@gmail.com>
Signed-off-by: Anupam Kumar <kyteinsky@gmail.com>
Signed-off-by: Anupam Kumar <kyteinsky@gmail.com>
Signed-off-by: Anupam Kumar <kyteinsky@gmail.com>
Signed-off-by: Anupam Kumar <kyteinsky@gmail.com>
Signed-off-by: Anupam Kumar <kyteinsky@gmail.com>
for images (OCR) and audio (Speech-to-text) files Signed-off-by: Anupam Kumar <kyteinsky@gmail.com>
marcelklehr
approved these changes
Mar 16, 2026
3459ba5 to
85d29f1
Compare
Signed-off-by: Anupam Kumar <kyteinsky@gmail.com>
1dc89e7 to
073f9d0
Compare
44867af to
7337d17
Compare
Signed-off-by: Anupam Kumar <kyteinsky@gmail.com>
f59454c to
fc00630
Compare
591ab8e to
87d1057
Compare
Signed-off-by: Anupam Kumar <kyteinsky@gmail.com>
87d1057 to
64f311d
Compare
Signed-off-by: Anupam Kumar <kyteinsky@gmail.com>
59bf2bb to
3b77c9f
Compare
Signed-off-by: kyteinsky <kyteinsky@gmail.com>
Signed-off-by: kyteinsky <kyteinsky@gmail.com>
- do not OCR images in PDF - fetch task type availability in the fork process - log as warning if subprocess emits stderr - mark items are retryable if task type is absent - other minor fixes Signed-off-by: kyteinsky <kyteinsky@gmail.com>
Signed-off-by: kyteinsky <kyteinsky@gmail.com>
Signed-off-by: kyteinsky <kyteinsky@gmail.com>
Signed-off-by: kyteinsky <kyteinsky@gmail.com>
Contributor
Author
|
maybe we can pick it up later again |
Contributor
Author
|
OCR task type supports pdfs natively so they can be directly sent in task processing task with the NC file id without parsing it locally, just like the image files. |
Contributor
Author
|
investigate if sending the pdf as images is better even when the pdf is partilly or fully text |
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
for images (OCR) and audio (Speech-to-text) files
some rough edges and optimisation left on the table for now, will be fixed eventually, it seems to be working for now.