Refactor best shot engine handling and improve ETA calculations

- Removed best shot engine settings and related functions from app_settings.py.
- Updated SimilarityEngine to include ETA calculations during image processing.
- Simplified AppController by removing best shot engine retrieval and related signals.
- Removed best shot engine configuration from DialogManager and adjusted UI accordingly.
- Cleaned up WorkerManager by removing unused best shot engine parameters.
- Enhanced AiRatingWorker and BestShotWorker to manage threading and ETA calculations more effectively.
- Deleted obsolete tests related to best shot engine and model checking.
- Improved overall code readability and maintainability by consolidating logic and removing unnecessary complexity.

Author: duartebarbosadev

README.md

@@ -19,7 +19,7 @@ PhotoSort is a powerful desktop application focused on speed designed to streaml
   * **Fast Processing**: Intensive operations (scanning, thumbnailing, analysis) run once in batch to ensure fast image scrolling.
   * **Optimized Image Handling**: Supports a wide range of formats, including various RAW types, with efficient caching.
   * **Intelligent Image Rotation**: Smart rotation system that automatically tries lossless metadata rotation first, with optional fallback to pixel rotation when needed.
-  * **AI Best-Shot Ranking**: Compare stacks with either the bundled multi-model pipeline or an OpenAI-compatible vision model (e.g. Qwen3-VL).
+  * **AI Best-Shot Ranking**: Send stacks to an OpenAI-compatible vision model (e.g. Qwen3-VL) to pick the keeper frame automatically.
   * **AI Star Ratings**: Ask the configured AI engine to score individual photos with 1–5 stars.
 
 - **Update Notifications**: Automatically checks for new releases and notifies users when updates are available, with direct download links.
@@ -100,34 +100,14 @@ To use the **Auto Rotate Images** feature (`Ctrl+R`), you need to download the p
 
 The application will automatically detect and load the model when you use the rotation detection feature.
 
-### AI Best Shot Ranking & Engines
-
-PhotoSort can rank similar shots and assign AI ratings using either a local
-multi-model pipeline or an OpenAI-compatible vision model; switch engines in
-**Preferences → AI Rating Engine** (`F10`). Settings persist between sessions.
-
-**Local pipeline (default)**  
-Runs entirely offline with three Hugging Face checkpoints:
-BlazeFace face detector (`qualcomm/MediaPipe-Face-Detection`), eye-state classifier
-(`MichalMlodawski/open-closed-eye-classification-mobilev2`), and the aesthetic predictor
-(`shunk031/aesthetics-predictor-v2-sac-logos-ava1-l14-linearMSE`). Place each bundle
-under `models/` and choose **Local Pipeline** in preferences.
-
-Required downloads (install into `models/`):
-
-1. **Face detector** – [`qualcomm/MediaPipe-Face-Detection`](https://huggingface.co/qualcomm/MediaPipe-Face-Detection)  
-   Extract `model.onnx` to `models/job_*/model.onnx` (or e.g. `models/MediaPipe-Face-Detection_FaceDetector_float/model.onnx`).
-2. **Eye-state classifier** – [`MichalMlodawski/open-closed-eye-classification-mobilev2`](https://huggingface.co/MichalMlodawski/open-closed-eye-classification-mobilev2)  
-   Copy all files into `models/open-closed-eye-classification-mobilev2/`.
-3. **Aesthetic predictor** – [`shunk031/aesthetics-predictor-v2-sac-logos-ava1-l14-linearMSE`](https://huggingface.co/shunk031/aesthetics-predictor-v2-sac-logos-ava1-l14-linearMSE)  
-   Copy all files into `models/aesthetic_predictor/` (includes the CLIP backbone plus regression head).
-
-**LLM engine**  
-Connect PhotoSort to any OpenAI-compatible endpoint that accepts images
-—for example Qwen3-VL. Configure API key, base URL,
-model name, prompt templates, and timeouts directly in the preferences dialog.
-For local deployments that do not require authentication (e.g. LM Studio), leave
-the API key blank.
+### AI Best Shot Ranking & Ratings
+
+PhotoSort relies on an OpenAI-compatible vision model to rank
+similar shots and request AI star ratings. Configure the endpoint under
+**Preferences → AI Rating Engine** (`F10`) by providing the API key (optional for
+local deployments), base URL, model name, prompt templates, max tokens, timeout,
+and concurrency. Any server that implements the OpenAI Chat Completions API with
+vision support (for example, Qwen3-VL running in LM Studio) will work.
 
 **Using the results**  
 - **Similarity stacks**: After running **View → Analyze Similarity**, launch

src/core/ai/__init__.py

@@ -1,9 +1,14 @@
 """
 AI helper utilities for advanced ranking/scoring pipelines.
 
-Currently exposes the experimental best-photo selector which chains together
-multiple pre-trained models (face detection, eye-state classification, and
-image quality scoring) to rank similar shots.
+This package exposes the LLM-based best-shot pipeline used for ranking clusters
+and assigning AI star ratings.
 """
 
-from .best_photo_selector import BestPhotoSelector, BestShotResult  # noqa: F401
+from .best_shot_pipeline import BaseBestShotStrategy, LLMBestShotStrategy, LLMConfig
+
+__all__ = [
+    "BaseBestShotStrategy",
+    "LLMBestShotStrategy",
+    "LLMConfig",
+]