Added ingestor.store() support in NV-Ingest#446
Open
smasurekar wants to merge 1 commit intodevelopfrom
Open
Conversation
b2071c2 to
80c8ecc
Compare
Signed-off-by: Swapnil Masurekar <smasurekar@nvidia.com>
80c8ecc to
3151721
Compare
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
NV-Ingest
.store()for citation assets; read viasource_locationCitation images and structured assets are written by NV-Ingest
ingestor.store()(MinIO) instead of the ingestor’s__put_content_to_miniopath. The RAG server and VLM load them usingsource.source_locationandMinioOperator.get_object()(plusobject_key_from_storage_uri). Document summaries are unchanged (get_payload/ thumbnail IDs).Citation storage is not backward compatible: Citation media that was written to MinIO under unique-thumbnail object keys (JSON payloads) is no longer what the RAG server resolves at query time. NV-Ingest now persists assets through
.store(), and the server loads them viasource_location. Older vectors may still reference the thumbnail-based layout; re-ingesting aligns metadata and object paths so citation images resolve correctly.Checklist
git commit -s) and GPG signed (git commit -S).