docker/main/requirements-wheels.txt

@@ -47,7 +47,7 @@ onnxruntime == 1.22.*
 # Embeddings
 transformers == 4.45.*
 # Generative AI
-google-genai == 1.58.*
+google-generativeai == 0.8.*
 ollama == 0.6.*
 openai == 1.65.*
 # push notifications

frigate/embeddings/onnx/jina_v1_embedding.py

@@ -2,7 +2,6 @@
 
 import logging
 import os
-import threading
 import warnings
 
 from transformers import AutoFeatureExtractor, AutoTokenizer
@@ -55,7 +54,6 @@ class JinaV1TextEmbedding(BaseEmbedding):
         self.tokenizer = None
         self.feature_extractor = None
         self.runner = None
-        self._lock = threading.Lock()
         files_names = list(self.download_urls.keys()) + [self.tokenizer_file]
 
         if not all(
@@ -136,18 +134,17 @@ class JinaV1TextEmbedding(BaseEmbedding):
             )
 
     def _preprocess_inputs(self, raw_inputs):
-        with self._lock:
-            max_length = max(len(self.tokenizer.encode(text)) for text in raw_inputs)
-            return [
-                self.tokenizer(
-                    text,
-                    padding="max_length",
-                    truncation=True,
-                    max_length=max_length,
-                    return_tensors="np",
-                )
-                for text in raw_inputs
-            ]
+        max_length = max(len(self.tokenizer.encode(text)) for text in raw_inputs)
+        return [
+            self.tokenizer(
+                text,
+                padding="max_length",
+                truncation=True,
+                max_length=max_length,
+                return_tensors="np",
+            )
+            for text in raw_inputs
+        ]
 
 
 class JinaV1ImageEmbedding(BaseEmbedding):
@@ -177,7 +174,6 @@ class JinaV1ImageEmbedding(BaseEmbedding):
         self.download_path = os.path.join(MODEL_CACHE_DIR, self.model_name)
         self.feature_extractor = None
         self.runner: BaseModelRunner | None = None
-        self._lock = threading.Lock()
         files_names = list(self.download_urls.keys())
         if not all(
             os.path.exists(os.path.join(self.download_path, n)) for n in files_names
@@ -220,9 +216,8 @@ class JinaV1ImageEmbedding(BaseEmbedding):
             )
 
     def _preprocess_inputs(self, raw_inputs):
-        with self._lock:
-            processed_images = [self._process_image(img) for img in raw_inputs]
-            return [
-                self.feature_extractor(images=image, return_tensors="np")
-                for image in processed_images
-            ]
+        processed_images = [self._process_image(img) for img in raw_inputs]
+        return [
+            self.feature_extractor(images=image, return_tensors="np")
+            for image in processed_images
+        ]

frigate/genai/gemini.py

@@ -3,8 +3,8 @@
 import logging
 from typing import Optional
 
-from google import genai
-from google.genai import errors, types
+import google.generativeai as genai
+from google.api_core.exceptions import GoogleAPICallError
 
 from frigate.config import GenAIProviderEnum
 from frigate.genai import GenAIClient, register_genai_provider
@@ -16,51 +16,44 @@ logger = logging.getLogger(__name__)
 class GeminiClient(GenAIClient):
     """Generative AI client for Frigate using Gemini."""
 
-    provider: genai.Client
+    provider: genai.GenerativeModel
 
     def _init_provider(self):
         """Initialize the client."""
-        # Merge provider_options into HttpOptions
-        http_options_dict = {
-            "api_version": "v1",
-            "timeout": int(self.timeout * 1000),  # requires milliseconds
-        }
-
-        if isinstance(self.genai_config.provider_options, dict):
-            http_options_dict.update(self.genai_config.provider_options)
-
-        return genai.Client(
-            api_key=self.genai_config.api_key,
-            http_options=types.HttpOptions(**http_options_dict),
+        genai.configure(api_key=self.genai_config.api_key)
+        return genai.GenerativeModel(
+            self.genai_config.model, **self.genai_config.provider_options
         )
 
     def _send(self, prompt: str, images: list[bytes]) -> Optional[str]:
         """Submit a request to Gemini."""
-        contents = [
-            types.Part.from_bytes(data=img, mime_type="image/jpeg") for img in images
+        data = [
+            {
+                "mime_type": "image/jpeg",
+                "data": img,
+            }
+            for img in images
         ] + [prompt]
         try:
             # Merge runtime_options into generation_config if provided
             generation_config_dict = {"candidate_count": 1}
             generation_config_dict.update(self.genai_config.runtime_options)
 
-            response = self.provider.models.generate_content(
-                model=self.genai_config.model,
-                contents=contents,
-                config=types.GenerateContentConfig(
-                    **generation_config_dict,
+            response = self.provider.generate_content(
+                data,
+                generation_config=genai.types.GenerationConfig(
+                    **generation_config_dict
+                ),
+                request_options=genai.types.RequestOptions(
+                    timeout=self.timeout,
                 ),
             )
-        except errors.APIError as e:
+        except GoogleAPICallError as e:
             logger.warning("Gemini returned an error: %s", str(e))
             return None
-        except Exception as e:
-            logger.warning("An unexpected error occurred with Gemini: %s", str(e))
-            return None
-
         try:
             description = response.text.strip()
-        except (ValueError, AttributeError):
+        except ValueError:
             # No description was generated
             return None
         return description

frigate/log.py

@@ -89,7 +89,6 @@ def apply_log_levels(default: str, log_levels: dict[str, LogLevel]) -> None:
         "ws4py": LogLevel.error,
         "PIL": LogLevel.warning,
         "numba": LogLevel.warning,
-        "google_genai.models": LogLevel.warning,
         **log_levels,
     }
 

web/src/components/timeline/DetailStream.tsx

@@ -887,10 +887,7 @@ function LifecycleItem({
                       </span>
                       <span className="font-medium text-foreground">
                         {attributeAreaPx}{" "}
-                        {t("information.pixels", {
-                          ns: "common",
-                          area: attributeAreaPx,
-                        })}{" "}
+                        {t("information.pixels", { ns: "common" })}{" "}
                         <span className="text-secondary-foreground">·</span>{" "}
                         {attributeAreaPct}%
                       </span>

web/src/views/classification/ModelTrainingView.tsx

@@ -75,7 +75,6 @@ import SearchDetailDialog, {
 } from "@/components/overlay/detail/SearchDetailDialog";
 import { SearchResult } from "@/types/search";
 import { HiSparkles } from "react-icons/hi";
-import { capitalizeFirstLetter } from "@/utils/stringUtil";
 
 type ModelTrainingViewProps = {
   model: CustomClassificationModelConfig;
@@ -89,7 +88,7 @@ export default function ModelTrainingView({ model }: ModelTrainingViewProps) {
   // title
 
   useEffect(() => {
-    document.title = `${capitalizeFirstLetter(model.name)} - ${t("documentTitle")}`;
+    document.title = `${model.name.toUpperCase()} - ${t("documentTitle")}`;
   }, [model.name, t]);
 
   // model state