Merge pull request #27 from qdrant/add-bge-small-zh

* feat(embedding.py): add "BAAI/bge-small-zh-v1.5" model
qdrant · Oct 18, 2023 · 72591fe · 72591fe
2 parents 911b51d + f28087c
commit 72591fe
Show file tree

Hide file tree

Showing 2 changed files with 7 additions and 0 deletions.
diff --git a/fastembed/embedding.py b/fastembed/embedding.py
@@ -196,6 +196,12 @@ def list_supported_models(cls) -> List[Dict[str, Union[str, Union[int, float]]]]
                 "description": "Fast and Default English model",
                 "size_in_GB": 0.13
             },
+            {
+                "model": "BAAI/bge-small-zh-v1.5",
+                "dim": 512,
+                "description": "Fast and recommended Chinese model",
+                "size_in_GB": 0.1
+            },
             {
                 "model": "BAAI/bge-base-en",
                 "dim": 768,

diff --git a/tests/test_onnx_embeddings.py b/tests/test_onnx_embeddings.py
@@ -8,6 +8,7 @@
 CANONICAL_VECTOR_VALUES = {
     "BAAI/bge-small-en": np.array([-0.0232, -0.0255,  0.0174, -0.0639, -0.0006]),
     "BAAI/bge-small-en-v1.5": np.array([0.01522374, -0.02271799,  0.00860278, -0.07424029,  0.00386434]),
+    "BAAI/bge-small-zh-v1.5": np.array([-0.01023294,  0.07634465,  0.0691722 , -0.04458365, -0.03160762]),
     "BAAI/bge-base-en": np.array([0.0115,  0.0372,  0.0295,  0.0121,  0.0346]),
     "BAAI/bge-base-en-v1.5": np.array([0.01129394, 0.05493144, 0.02615099, 0.00328772, 0.02996045]),
     "sentence-transformers/all-MiniLM-L6-v2": np.array([0.0259,  0.0058,  0.0114,  0.0380, -0.0233]),