Feature/v3.1 replace UI add new plugins#108
Open
nb950 wants to merge 48 commits into
Open
Conversation
see README_UI.md for frontend details
Made-with: Cursor
chat area , fix job id , and other ui issues
update image_summary for batching ui fixes
cuda,cudnn,pgvector,onnxruntime , update to version 3.0.0
Updated README to include references for backend and UI server scripts.
seach-images update case-export
refactor scroll and log code test e2e concurrent user jobs use moondream model for image summary , much faster
remove apple dfn due to license and use another not too bad clip model
tasks reduce frontend logging
Updated README.md to clarify software capabilities and support information.
Adds an image_similarity plugin that finds the most visually similar images to a query image in a folder. Embeds images with SigLIP-2 via ONNX Runtime (no PyTorch at inference) and ranks them by cosine similarity in pgvector. Endpoint /search_similar_images, shows up in the chatbot tool menu as "Similar Images". Caches embeddings in their own image_similarity_embeddings table (keyed by path/content hash and model), separate from the text-to-image image_embeddings table. Benchmarks on a 503-image series set (RTX 5090): 93% top-1, 98% top-5, 99% top-10, ~14 img/sec, ~12 GB peak VRAM. Picked SigLIP-2 SO400M over LAION CLIP-H, DFN5B, and SigLIP-2-gopt for the best mix of accuracy, memory, speed, and an Apache-2.0 license. Tests cover schema, types, and CLI parsers: poetry run pytest src/image-similarity/tests.
Exclude integration tests from pytest run.
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
1 participant
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
replace frontend ui add 3 new plugins ,use granite llm for chat interface function calling
new plugins : image-similarity , image-search , text-search
add pgvector for clip embeddings
github-actions-workflow passed ok , unit rests ok