chore: Updated source onnx_embedding.py

fastembed/common/model_management.py

@@ -1,13 +1,8 @@
-import os
-import shutil
-import tarfile
 from pathlib import Path
 from typing import List, Optional, Dict, Any
 
-import requests
 from huggingface_hub import snapshot_download
 from huggingface_hub.utils import RepositoryNotFoundError
-from tqdm import tqdm
 from loguru import logger
 
 
@@ -58,50 +53,6 @@ class ModelManagement:
 
         raise ValueError(f"Model {model_name} is not supported in {cls.__name__}.")
 
-    @classmethod
-    def download_file_from_gcs(cls, url: str, output_path: str, show_progress: bool = True) -> str:
-        """
-        Downloads a file from Google Cloud Storage.
-
-        Args:
-            url (str): The URL to download the file from.
-            output_path (str): The path to save the downloaded file to.
-            show_progress (bool, optional): Whether to show a progress bar. Defaults to True.
-
-        Returns:
-            str: The path to the downloaded file.
-        """
-
-        if os.path.exists(output_path):
-            return output_path
-        response = requests.get(url, stream=True)
-
-        # Handle HTTP errors
-        if response.status_code == 403:
-            raise PermissionError(
-                "Authentication Error: You do not have permission to access this resource. "
-                "Please check your credentials."
-            )
-
-        # Get the total size of the file
-        total_size_in_bytes = int(response.headers.get("content-length", 0))
-
-        # Warn if the total size is zero
-        if total_size_in_bytes == 0:
-            print(f"Warning: Content-length header is missing or zero in the response from {url}.")
-
-        show_progress = total_size_in_bytes and show_progress
-
-        with tqdm(
-            total=total_size_in_bytes, unit="iB", unit_scale=True, disable=not show_progress
-        ) as progress_bar:
-            with open(output_path, "wb") as file:
-                for chunk in response.iter_content(chunk_size=1024):
-                    if chunk:  # Filter out keep-alive new chunks
-                        progress_bar.update(len(chunk))
-                        file.write(chunk)
-        return output_path
-
     @classmethod
     def download_files_from_huggingface(
         cls, hf_source_repo: str, cache_dir: Optional[str] = None
@@ -128,77 +79,6 @@ class ModelManagement:
             cache_dir=cache_dir,
         )
 
-    @classmethod
-    def decompress_to_cache(cls, targz_path: str, cache_dir: str):
-        """
-        Decompresses a .tar.gz file to a cache directory.
-
-        Args:
-            targz_path (str): Path to the .tar.gz file.
-            cache_dir (str): Path to the cache directory.
-
-        Returns:
-            cache_dir (str): Path to the cache directory.
-        """
-        # Check if targz_path exists and is a file
-        if not os.path.isfile(targz_path):
-            raise ValueError(f"{targz_path} does not exist or is not a file.")
-
-        # Check if targz_path is a .tar.gz file
-        if not targz_path.endswith(".tar.gz"):
-            raise ValueError(f"{targz_path} is not a .tar.gz file.")
-
-        try:
-            # Open the tar.gz file
-            with tarfile.open(targz_path, "r:gz") as tar:
-                # Extract all files into the cache directory
-                tar.extractall(path=cache_dir)
-        except tarfile.TarError as e:
-            # If any error occurs while opening or extracting the tar.gz file,
-            # delete the cache directory (if it was created in this function)
-            # and raise the error again
-            if "tmp" in cache_dir:
-                shutil.rmtree(cache_dir)
-            raise ValueError(f"An error occurred while decompressing {targz_path}: {e}")
-
-        return cache_dir
-
-    @classmethod
-    def retrieve_model_gcs(cls, model_name: str, source_url: str, cache_dir: str) -> Path:
-        fast_model_name = f"fast-{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
-
-        # check if the model_dir and the model files are both present for macOS
-        if model_dir.exists() and len(list(model_dir.glob("*"))) > 0:
-            return model_dir
-
-        if model_tmp_dir.exists():
-            shutil.rmtree(model_tmp_dir)
-
-        cache_tmp_dir.mkdir(parents=True, exist_ok=True)
-
-        model_tar_gz = Path(cache_dir) / f"{fast_model_name}.tar.gz"
-
-        if model_tar_gz.exists():
-            model_tar_gz.unlink()
-
-        cls.download_file_from_gcs(
-            source_url,
-            output_path=str(model_tar_gz),
-        )
-
-        cls.decompress_to_cache(targz_path=str(model_tar_gz), cache_dir=str(cache_tmp_dir))
-        assert model_tmp_dir.exists(), f"Could not find {model_tmp_dir} in {cache_tmp_dir}"
-
-        model_tar_gz.unlink()
-        # Rename from tmp to final name is atomic
-        model_tmp_dir.rename(model_dir)
-
-        return model_dir
-
     @classmethod
     def download_model(cls, model: Dict[str, Any], cache_dir: Path) -> Path:
         """
@@ -214,7 +94,6 @@ class ModelManagement:
                     "description": "Base English model, v1.5",
                     "size_in_GB": 0.44,
                     "sources": {
-                        "url": "https://storage.googleapis.com/qdrant-fastembed/fast-bge-base-en-v1.5.tar.gz",
                         "hf": "qdrant/bge-base-en-v1.5-onnx-q",
                     }
                 }
@@ -226,7 +105,6 @@ class ModelManagement:
         """
 
         hf_source = model.get("sources", {}).get("hf")
-        url_source = model.get("sources", {}).get("url")
 
         if hf_source:
             try:
@@ -239,7 +117,4 @@ class ModelManagement:
                     "Falling back to other sources."
                 )
 
-        if url_source:
-            return cls.retrieve_model_gcs(model["model"], url_source, str(cache_dir))
-
         raise ValueError(f"Could not download model {model['model']} from any source.")

fastembed/text/e5_onnx_embedding.py

@@ -12,7 +12,6 @@ supported_multilingual_e5_models = [
         "description": "Multilingual model, e5-large. Recommend using this model for non-English languages",
         "size_in_GB": 2.24,
         "sources": {
-            "url": "https://storage.googleapis.com/qdrant-fastembed/fast-multilingual-e5-large.tar.gz",
             "hf": "qdrant/multilingual-e5-large-onnx",
         },
     },

fastembed/text/onnx_embedding.py

@@ -14,7 +14,7 @@ supported_onnx_models = [
         "description": "Base English model",
         "size_in_GB": 0.42,
         "sources": {
-            "url": "https://storage.googleapis.com/qdrant-fastembed/fast-bge-base-en.tar.gz",
+            "hf": "yashvardhan7/bge-base-en-onnx",
         },
     },
     {
@@ -23,7 +23,6 @@ supported_onnx_models = [
         "description": "Base English model, v1.5",
         "size_in_GB": 0.21,
         "sources": {
-            "url": "https://storage.googleapis.com/qdrant-fastembed/fast-bge-base-en-v1.5.tar.gz",
             "hf": "qdrant/bge-base-en-v1.5-onnx-q",
         },
     },
@@ -42,20 +41,9 @@ supported_onnx_models = [
         "description": "Fast English model",
         "size_in_GB": 0.13,
         "sources": {
-            "url": "https://storage.googleapis.com/qdrant-fastembed/BAAI-bge-small-en.tar.gz",
+            "hf": "ggrn/bge-small-en",
         },
     },
-    # {
-    #     "model": "BAAI/bge-small-en",
-    #     "dim": 384,
-    #     "description": "Fast English model",
-    #     "size_in_GB": 0.2,
-    #     "hf_sources": [],
-    #     "compressed_url_sources": [
-    #         "https://storage.googleapis.com/qdrant-fastembed/fast-bge-small-en.tar.gz",
-    #         "https://storage.googleapis.com/qdrant-fastembed/BAAI-bge-small-en.tar.gz"
-    #     ]
-    # },
     {
         "model": "BAAI/bge-small-en-v1.5",
         "dim": 384,
@@ -71,7 +59,7 @@ supported_onnx_models = [
         "description": "Fast and recommended Chinese model",
         "size_in_GB": 0.09,
         "sources": {
-            "url": "https://storage.googleapis.com/qdrant-fastembed/fast-bge-small-zh-v1.5.tar.gz",
+            "hf": "Xenova/bge-small-zh-v1.5",
         },
     },
     {
@@ -80,7 +68,6 @@ supported_onnx_models = [
         "description": "Sentence Transformer model, MiniLM-L6-v2",
         "size_in_GB": 0.09,
         "sources": {
-            "url": "https://storage.googleapis.com/qdrant-fastembed/sentence-transformers-all-MiniLM-L6-v2.tar.gz",
             "hf": "qdrant/all-MiniLM-L6-v2-onnx",
         },
     },
@@ -120,19 +107,6 @@ supported_onnx_models = [
             "hf": "qdrant/gte-large-onnx",
         },
     },
-    # {
-    #     "model": "sentence-transformers/all-MiniLM-L6-v2",
-    #     "dim": 384,
-    #     "description": "Sentence Transformer model, MiniLM-L6-v2",
-    #     "size_in_GB": 0.09,
-    #     "hf_sources": [
-    #         "qdrant/all-MiniLM-L6-v2-onnx"
-    #     ],
-    #     "compressed_url_sources": [
-    #         "https://storage.googleapis.com/qdrant-fastembed/fast-all-MiniLM-L6-v2.tar.gz",
-    #         "https://storage.googleapis.com/qdrant-fastembed/sentence-transformers-all-MiniLM-L6-v2.tar.gz"
-    #     ]
-    # }
     {
         "model": "mixedbread-ai/mxbai-embed-large-v1",
         "dim": 1024,

poetry.lock

@@ -3446,4 +3446,4 @@ testing = ["big-O", "jaraco.functools", "jaraco.itertools", "more-itertools", "p
 [metadata]
 lock-version = "2.0"
 python-versions = ">=3.8.0,<3.13"
-content-hash = "b71c2e05a840cee62f4d1a11c0377e93d735f473e13f684246c021e01c5368c3"
+content-hash = "ace5b40bd629af8ec1a369f1cfb507db7bb6b18c1387357e0d029d9b50a66335"

pyproject.toml

@@ -15,7 +15,6 @@ python = ">=3.8.0,<3.13"
 onnx = "^1.15.0"
 onnxruntime = "^1.17.0"
 tqdm = "^4.66"
-requests = "^2.31"
 tokenizers = "^0.15.1"
 huggingface-hub = "^0.20"
 loguru = "^0.7.2"