chore: xenova jina

Author: Anush008

fastembed/embedding.py

@@ -95,13 +95,26 @@ def __init__(
         model_path = self.path / "model.onnx"
         optimized_model_path = self.path / "model_optimized.onnx"
 
+        xenova_model_path = self.path / "onnx" / "model.onnx"
+        xenova_optimized_model_path = self.path / "onnx" / "model_optimized.onnx"
+
         # List of Execution Providers: https://onnxruntime.ai/docs/execution-providers
         onnx_providers = ["CPUExecutionProvider"]
 
         if not model_path.exists():
             # Rename file model_optimized.onnx to model.onnx if it exists
             if optimized_model_path.exists():
                 optimized_model_path.rename(model_path)
+
+            # Patch for inconsistent repo structure at
+            # - https://huggingface.co/Xenova/jina-embeddings-v2-small-en
+            # - https://huggingface.co/Xenova/jina-embeddings-v2-base-en
+            elif xenova_model_path.exists():
+                model_path = xenova_model_path
+
+            elif xenova_optimized_model_path.exists():
+                model_path = xenova_optimized_model_path
+
             else:
                 raise ValueError(f"Could not find model.onnx in {self.path}")
 

fastembed/models.json

@@ -83,7 +83,7 @@
         "description": " English embedding model supporting 8192 sequence length",
         "size_in_GB": 0.55,
         "hf_sources": [
-            "jinaai/jina-embeddings-v2-base-en"
+            "xenova/jina-embeddings-v2-base-en"
         ],
         "compressed_url_sources": []
     },
@@ -93,7 +93,7 @@
         "description": " English embedding model supporting 8192 sequence length",
         "size_in_GB": 0.13,
         "hf_sources": [
-            "jinaai/jina-embeddings-v2-small-en"
+            "xenova/jina-embeddings-v2-small-en"
         ],
         "compressed_url_sources": []
     },