From 44f90d42f8d40d60ae43be5b0e4e8117b27aef0b Mon Sep 17 00:00:00 2001
From: mertalev <101130780+mertalev@users.noreply.github.com>
Date: Wed, 15 Oct 2025 14:35:52 -0400
Subject: [PATCH] linting

---
 machine-learning/immich_ml/models/ocr/recognition.py | 9 +++++----
 machine-learning/immich_ml/models/ocr/schemas.py     | 6 +++---
 machine-learning/uv.lock                             | 2 +-
 3 files changed, 9 insertions(+), 8 deletions(-)

diff --git a/machine-learning/immich_ml/models/ocr/recognition.py b/machine-learning/immich_ml/models/ocr/recognition.py
index 0f1394304c..0138ff9bdb 100644
--- a/machine-learning/immich_ml/models/ocr/recognition.py
+++ b/machine-learning/immich_ml/models/ocr/recognition.py
@@ -2,6 +2,7 @@ from typing import Any
 
 import cv2
 import numpy as np
+from numpy.typing import NDArray
 from PIL.Image import Image
 from rapidocr.ch_ppocr_rec import TextRecInput
 from rapidocr.ch_ppocr_rec import TextRecognizer as RapidTextRecognizer
@@ -84,7 +85,7 @@ class TextRecognizer(InferenceModel):
             "textScore": text_scores[valid_text_score_idx],
         }
 
-    def get_crop_img_list(self, img: np.ndarray, boxes: np.ndarray) -> list[np.ndarray]:
+    def get_crop_img_list(self, img: NDArray[np.float32], boxes: NDArray[np.float32]) -> list[NDArray[np.float32]]:
         img_crop_width = np.maximum(
             np.linalg.norm(boxes[:, 1] - boxes[:, 0], axis=1), np.linalg.norm(boxes[:, 2] - boxes[:, 3], axis=1)
         ).astype(np.int32)
@@ -96,16 +97,16 @@ class TextRecognizer(InferenceModel):
         pts_std[:, 2:4, 1] = img_crop_height[:, None]
 
         img_crop_sizes = np.stack([img_crop_width, img_crop_height], axis=1).tolist()
-        imgs = []
+        imgs: list[NDArray[np.float32]] = []
         for box, pts_std, dst_size in zip(list(boxes), list(pts_std), img_crop_sizes):
             M = cv2.getPerspectiveTransform(box, pts_std)
-            dst_img = cv2.warpPerspective(
+            dst_img: NDArray[np.float32] = cv2.warpPerspective(
                 img,
                 M,
                 dst_size,
                 borderMode=cv2.BORDER_REPLICATE,
                 flags=cv2.INTER_CUBIC,
-            )
+            )  # type: ignore
             dst_height, dst_width = dst_img.shape[0:2]
             if dst_height * 1.0 / dst_width >= 1.5:
                 dst_img = np.rot90(dst_img)
diff --git a/machine-learning/immich_ml/models/ocr/schemas.py b/machine-learning/immich_ml/models/ocr/schemas.py
index 4acf1b1eb9..14a7d3cea0 100644
--- a/machine-learning/immich_ml/models/ocr/schemas.py
+++ b/machine-learning/immich_ml/models/ocr/schemas.py
@@ -1,4 +1,4 @@
-from typing import Iterable
+from typing import Any, Iterable
 
 import numpy as np
 import numpy.typing as npt
@@ -20,8 +20,8 @@ class TextRecognitionOutput(TypedDict):
 
 
 # RapidOCR expects `engine_type`, `lang_type`, and `font_path` to be attributes
-class OcrOptions(dict):
-    def __init__(self, **options):
+class OcrOptions(dict[str, Any]):
+    def __init__(self, **options: Any) -> None:
         super().__init__(**options)
         self.engine_type = EngineType.ONNXRUNTIME
         self.lang_type = LangRec.CH
diff --git a/machine-learning/uv.lock b/machine-learning/uv.lock
index 9dcc58684c..caaa1e4467 100644
--- a/machine-learning/uv.lock
+++ b/machine-learning/uv.lock
@@ -1082,7 +1082,7 @@ wheels = [
 
 [[package]]
 name = "immich-ml"
-version = "1.129.0"
+version = "2.0.1"
 source = { editable = "." }
 dependencies = [
     { name = "aiocache" },