Added multimodal query support for VLM Embed#362
Open
smasurekar wants to merge 1 commit intodevelopfrom
Open
Conversation
smasurekar
force-pushed
the
dev/smasurekar/vlm-embed-multimodal-query
branch
from
5bda440 to
4564039
Compare
nv-pranjald
reviewed
Feb 17, 2026
nv-pranjald
approved these changes
Feb 17, 2026
smasurekar
force-pushed
the
dev/smasurekar/vlm-embed-multimodal-query
branch
from
4564039 to
7487c01
Compare
smasurekar
force-pushed
the
dev/smasurekar/vlm-embed-multimodal-query
branch
from
7487c01 to
95f7dcd
Compare
Signed-off-by: Swapnil Masurekar <smasurekar@nvidia.com>
smasurekar
force-pushed
the
dev/smasurekar/vlm-embed-multimodal-query
branch
from
95f7dcd to
4a78d0d
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
3 participants
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Concatenate multimodal content for VLM Embed
Multimodal retriever queries (text + image) are now concatenated into a single string for VLM embedding instead of returning only the image URL, so the embed model receives both text and image in one query. Text is joined with
\n\n, then the image URL is appended (one image supported). Unit tests updated for the new concatenated format.