Update deps (#24623)

* bump backend and frontend dependencies

Bumps every outdated dependency that passed testing, with the code changes each one needs.

- peewee 4.5 and peewee_migrate 2.3: use SqliteDatabase in place of the removed SqliteExtDatabase, and fix types for peewee's bundled stubs
- mypy 2.4.0: remove unused type ignores and add the annotations mypy 2 needs
- pandas 3.0: convert the motion activity index with as_unit("s"), because pandas 3 infers second resolution for whole-second timestamps and the old // 10**9 returned 1
- transformers 5.19: load Jina tokenizers from the saved directory with trust_remote_code off and use CLIPImageProcessor, since v5 removed CLIPFeatureExtractor and remote code pulled in torch
- tensorflow-cpu 2.21: pin protobuf to 7.36 in the TensorRT amd64 image, because the old 3.20.3 pin was installed over TensorFlow and broke its import
- pydantic 2.13 and google-genai 2.29: regenerate the API spec
- ruff 0.16: set an explicit lint select, since 0.16 widened the default rules
- react-router-dom 7: set useTransitions={false} on BrowserRouter to keep v6 update timing, which useSearchEffect relies on
- typescript 6: drop baseUrl and add node types in tsconfig
- radix: update to the latest release and remove the slot patch, which upstream now includes
- apexcharts 7.8: guard the tooltip formatter against null values
- cryptography 50, joserfc 1.7, pywebpush 2.5, openai 3.26, aiohttp, uvicorn, onvif-zeep-async, scipy, framer-motion 14, react-day-picker 10 and other minor and patch bumps

* silence httpx2 request logging

* redownload an incomplete jina tokenizer

An interrupted tokenizer download left the Hugging Face cache directory without the saved tokenizer files, and since the download is skipped whenever that directory exists, every restart failed to load the tokenizer. The Jina constructors now remove a tokenizer directory that has no tokenizer_config.json so the download runs again.

frigate/embeddings/onnx/jina_v1_embedding.py

@@ -2,10 +2,10 @@
 
 import logging
 import os
+import shutil
 import threading
-import warnings
 
-from transformers import AutoFeatureExtractor, AutoTokenizer
+from transformers import AutoTokenizer, CLIPImageProcessor
 from transformers.utils.logging import disable_progress_bar
 
 from frigate.comms.inter_process import InterProcessRequestor
@@ -21,12 +21,6 @@ from frigate.util.downloader import ModelDownloader
 
 from .base_embedding import BaseEmbedding
 
-warnings.filterwarnings(
-    "ignore",
-    category=FutureWarning,
-    message="The class CLIPFeatureExtractor is deprecated",
-)
-
 # disables the progress bar for downloading tokenizers and feature extractors
 disable_progress_bar()
 logger = logging.getLogger(__name__)
@@ -58,6 +52,13 @@ class JinaV1TextEmbedding(BaseEmbedding):
         self._lock = threading.Lock()
         files_names = list(self.download_urls.keys()) + [self.tokenizer_file]
 
+        # an interrupted download leaves the hub cache without the saved tokenizer
+        tokenizer_path = os.path.join(self.download_path, self.tokenizer_file)
+        if os.path.isdir(tokenizer_path) and not os.path.exists(
+            os.path.join(tokenizer_path, "tokenizer_config.json")
+        ):
+            shutil.rmtree(tokenizer_path)
+
         if not all(
             os.path.exists(os.path.join(self.download_path, n)) for n in files_names
         ):
@@ -92,7 +93,7 @@ class JinaV1TextEmbedding(BaseEmbedding):
 
                 tokenizer = AutoTokenizer.from_pretrained(
                     self.model_name,
-                    trust_remote_code=True,
+                    trust_remote_code=False,
                     cache_dir=f"{MODEL_CACHE_DIR}/{self.model_name}/tokenizer",
                     clean_up_tokenization_spaces=True,
                 )
@@ -123,9 +124,8 @@ class JinaV1TextEmbedding(BaseEmbedding):
                 f"{MODEL_CACHE_DIR}/{self.model_name}/tokenizer"
             )
             self.tokenizer = AutoTokenizer.from_pretrained(
-                self.model_name,
-                cache_dir=tokenizer_path,
-                trust_remote_code=True,
+                tokenizer_path,
+                trust_remote_code=False,
                 clean_up_tokenization_spaces=True,
             )
 
@@ -209,7 +209,7 @@ class JinaV1ImageEmbedding(BaseEmbedding):
             if self.downloader:
                 self.downloader.wait_for_download()
 
-            self.feature_extractor = AutoFeatureExtractor.from_pretrained(
+            self.feature_extractor = CLIPImageProcessor.from_pretrained(
                 f"{MODEL_CACHE_DIR}/{self.model_name}",
             )
 

frigate/embeddings/onnx/jina_v2_embedding.py

@@ -3,6 +3,7 @@
 import io
 import logging
 import os
+import shutil
 import threading
 
 import numpy as np
@@ -60,6 +61,14 @@ class JinaV2Embedding(BaseEmbedding):
 
         # download the model and tokenizer
         files_names = list(self.download_urls.keys()) + [self.tokenizer_file]
+
+        # an interrupted download leaves the hub cache without the saved tokenizer
+        tokenizer_path = os.path.join(self.download_path, self.tokenizer_file)
+        if os.path.isdir(tokenizer_path) and not os.path.exists(
+            os.path.join(tokenizer_path, "tokenizer_config.json")
+        ):
+            shutil.rmtree(tokenizer_path)
+
         if not all(
             os.path.exists(os.path.join(self.download_path, n)) for n in files_names
         ):
@@ -97,7 +106,7 @@ class JinaV2Embedding(BaseEmbedding):
 
                 tokenizer = AutoTokenizer.from_pretrained(
                     self.model_name,
-                    trust_remote_code=True,
+                    trust_remote_code=False,
                     cache_dir=os.path.join(
                         MODEL_CACHE_DIR, self.model_name, "tokenizer"
                     ),
@@ -129,9 +138,8 @@ class JinaV2Embedding(BaseEmbedding):
                 f"{MODEL_CACHE_DIR}/{self.model_name}/tokenizer"
             )
             self.tokenizer = AutoTokenizer.from_pretrained(
-                self.model_name,
-                cache_dir=tokenizer_path,
-                trust_remote_code=True,
+                tokenizer_path,
+                trust_remote_code=False,
                 clean_up_tokenization_spaces=True,
             )