mirror of
https://github.com/lancedb/lancedb.git
synced 2025-12-22 21:09:58 +00:00
7d0127b376
### Summary This PR adds **SigLIP** (Sigmoid Loss Image Pretraining) as a new embedding model in the LanceDB embedding registry. SigLIP improves image-text alignment performance using sigmoid-based contrastive loss and offers robust zero-shot generalization. Fixes #2498 ### What’s Implemented #### 1. `SigLIP` Embedding Class * Added `SigLIP` support under `python/lancedb/embeddings/siglip.py` * Implements: * `compute_source_embeddings` * `_batch_generate_embeddings` * Normalization logic * Batch-wise progress logging for image embedding #### 2. Registry Integration * Registered `SigLIP` in `embeddings/__init__.py` * `SigLIP` now usable via `connect(..., embedding="siglip")` #### 3. Evaluation Benchmark Support * Added SigLIP to `test_embeddings_slow.py` for side-by-side benchmarking with OpenCLIP and ImageBind ### New Test Methods #### `test_siglip` * End-to-end test to verify embeddings table creation and vector shape for SigLIP  #### `test_siglip_vs_openclip_vs_imagebind_benchmark_full` * Benchmarks: * **Recall\@1 / 5 / 10** * **mAP (Mean Average Precision)** * **Embedding & Search Latency** * Dimensionality reporting  ### Notes * SigLIP outputs 768D embeddings (vs 512D for OpenCLIP) * Benchmark shows competitive performance despite higher dimensionality * I'm still new to contributing to open-source and learning as I go. Please feel free to suggest any improvements — I'm happy to make changes!
4 lines
61 B
Plaintext
4 lines
61 B
Plaintext
# Test data created by some example tests
|
|
data/
|
|
_lancedb.pyd
|