Deprecate archive struct (#490)

* bump version to 0.6.0

* new: deprecate gcp archive structure

Author: joein

fastembed/common/model_description.py

@@ -7,6 +7,11 @@
 class ModelSource:
     hf: Optional[str] = None
     url: Optional[str] = None
+    _deprecated_tar_struct: bool = False
+
+    @property
+    def deprecated_tar_struct(self) -> bool:
+        return self._deprecated_tar_struct
 
     def __post_init__(self) -> None:
         if self.hf is None and self.url is None:

fastembed/common/model_management.py

@@ -330,9 +330,10 @@ def retrieve_model_gcs(
         model_name: str,
         source_url: str,
         cache_dir: str,
+        deprecated_tar_struct: bool = False,
         local_files_only: bool = False,
     ) -> Path:
-        fast_model_name = f"fast-{model_name.split('/')[-1]}"
+        fast_model_name = f"{'fast-' if deprecated_tar_struct else ''}{model_name.split('/')[-1]}"
         cache_tmp_dir = Path(cache_dir) / "tmp"
         model_tmp_dir = cache_tmp_dir / fast_model_name
         model_dir = Path(cache_dir) / fast_model_name
@@ -438,6 +439,7 @@ def download_model(cls, model: T, cache_dir: str, retries: int = 3, **kwargs: An
                         model.model,
                         str(url_source),
                         str(cache_dir),
+                        deprecated_tar_struct=model.sources.deprecated_tar_struct,
                         local_files_only=local_files_only,
                     )
                 except Exception:

fastembed/text/onnx_embedding.py

@@ -21,6 +21,7 @@
         sources=ModelSource(
             hf="Qdrant/fast-bge-base-en",
             url="https://storage.googleapis.com/qdrant-fastembed/fast-bge-base-en.tar.gz",
+            _deprecated_tar_struct=True,
         ),
         model_file="model_optimized.onnx",
     ),
@@ -36,6 +37,7 @@
         sources=ModelSource(
             hf="qdrant/bge-base-en-v1.5-onnx-q",
             url="https://storage.googleapis.com/qdrant-fastembed/fast-bge-base-en-v1.5.tar.gz",
+            _deprecated_tar_struct=True,
         ),
         model_file="model_optimized.onnx",
     ),
@@ -63,6 +65,7 @@
         sources=ModelSource(
             hf="Qdrant/bge-small-en",
             url="https://storage.googleapis.com/qdrant-fastembed/BAAI-bge-small-en.tar.gz",
+            _deprecated_tar_struct=True,
         ),
         model_file="model_optimized.onnx",
     ),
@@ -90,6 +93,7 @@
         sources=ModelSource(
             hf="Qdrant/bge-small-zh-v1.5",
             url="https://storage.googleapis.com/qdrant-fastembed/fast-bge-small-zh-v1.5.tar.gz",
+            _deprecated_tar_struct=True,
         ),
         model_file="model_optimized.onnx",
     ),

fastembed/text/pooled_embedding.py

@@ -82,6 +82,7 @@
         sources=ModelSource(
             hf="qdrant/multilingual-e5-large-onnx",
             url="https://storage.googleapis.com/qdrant-fastembed/fast-multilingual-e5-large.tar.gz",
+            _deprecated_tar_struct=True,
         ),
         model_file="model.onnx",
         additional_files=["model.onnx_data"],

fastembed/text/pooled_normalized_embedding.py

@@ -22,6 +22,7 @@
         sources=ModelSource(
             url="https://storage.googleapis.com/qdrant-fastembed/sentence-transformers-all-MiniLM-L6-v2.tar.gz",
             hf="qdrant/all-MiniLM-L6-v2-onnx",
+            _deprecated_tar_struct=True,
         ),
         model_file="model.onnx",
     ),