Commit Graph

2 Commits

Author SHA1 Message Date
Poornachandra.A.N
7d0127b376 feat(embeddings): add siglip embedding support to lancedb (#2499)
###  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
![WhatsApp Image 2025-07-10 at 18 00
27_a3368163](https://github.com/user-attachments/assets/e5582ee1-80a3-43d7-a7a1-26ceecce9f4d)


####  `test_siglip_vs_openclip_vs_imagebind_benchmark_full`

* Benchmarks:

  * **Recall\@1 / 5 / 10**
  * **mAP (Mean Average Precision)**
  * **Embedding & Search Latency**
  * Dimensionality reporting
![WhatsApp Image 2025-07-10 at 18 12
13_22c67a84](https://github.com/user-attachments/assets/455bf30f-62b7-4684-a3f3-ad52e2a1ffe5)


###  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!
2025-08-04 11:42:39 -07:00
Weston Pace
c269524b2f feat!: refactor ConnectionInternal into a Database trait (#2067)
This opens up the door for more custom database implementations than the
two we have today. The biggest change should be inivisble:
`ConnectionInternal` has been renamed to `Database`, made public, and
refactored

However, there are a few breaking changes. `data_storage_version` and
`enable_v2_manifest_paths` have been moved from options on
`create_table` to options for the database which are now set via
`storage_options`.

Before:
```
db = connect(uri)
tbl = db.create_table("my_table", data, data_storage_version="legacy", enable_v2_manifest_paths=True)
```

After:
```
db = connect(uri, storage_options={
  "new_table_enable_v2_manifest_paths": "true",
  "new_table_data_storage_version": "legacy"
})
tbl = db.create_table("my_table", data)
```

BREAKING CHANGE: the data_storage_version, enable_v2_manifest_paths
options have moved from options to create_table to storage_options.
BREAKING CHANGE: the use_legacy_format option has been removed,
data_storage_version has replaced it for some time now
2025-02-04 14:35:14 -08:00