Adding the pipeline for the task explanation and Llm

[Bepitic]

📝 Description

• I added the Task explanation and built the pipeline for the future LLM that will categorize and explain the image.
• I modified the visualization such the explanation can be seen in the image outputted.

✨ Changes

Select what type of change your PR is:

• 🐞 Bug fix (non-breaking change which fixes an issue)
• 🔨 Refactor (non-breaking change which refactors the code base)
• 🚀 New feature (non-breaking change which adds functionality)
• 💥 Breaking change (fix or feature that would cause existing functionality to not work as expected)
• 📚 Documentation update
• 🔒 Security update

✅ Checklist

Before you submit your pull request, please make sure you have completed the following steps:

• 📋 I have summarized my changes in the CHANGELOG and followed the guidelines for my type of change (skip for minor changes, documentation updates, and test enhancements).
• 📚 I have made the necessary updates to the documentation (if applicable).
• 🧪 I have written tests that support my changes and prove that my fix is effective or my feature works (if applicable).

For more information about code review checklists, see the Code Review Checklist.

[Bepitic]

Hello, I'm looking to make this contribution as effective as possible, so please feel free to share any suggestions, concerns, or ideas you might have.
Thanks in advance for your time and input!

[samet-akcay]

added my initial comments, will do another round of review

[codecov]

Codecov Report

Attention: Patch coverage is 63.49206% with 23 lines in your changes missing coverage. Please review.

Project coverage is 80.67%. Comparing base (e7e6cb8) to head (a463b5b).
Report is 2 commits behind head on main.

Files	Patch %	Lines
src/anomalib/utils/visualization/image.py	47.61%	22 Missing ⚠️
...anomalib/deploy/inferencers/openvino_inferencer.py	83.33%	1 Missing ⚠️

Additional details and impacted files

@@            Coverage Diff             @@
##             main    #2190      +/-   ##
==========================================
- Coverage   80.78%   80.67%   -0.12%     
==========================================
  Files         248      248              
  Lines       10859    10885      +26     
==========================================
+ Hits         8772     8781       +9     
- Misses       2087     2104      +17     

☔ View full report in Codecov by Sentry.
📢 Have feedback on the report? Share it here.

[djdameln]

Thanks for the PR.

I think it would be good to add the OpenAI model implementation to this PR, so that we can run the pipeline and generate some visualizations.

[ashwinvaidya17]

The PR looks good but I am not sure about the expected output. Maybe it would be a good idea to add tests for this is possible.
This is the code I used for visualization. Is this what you would expect? (ignore the noisy image)

from anomalib.utils.visualization.image import ImageResult, ImageVisualizer, VisualizationMode
import numpy as np
from anomalib import TaskType
import matplotlib.pyplot as plt

anomaly_map = np.zeros((100, 100), dtype=np.float64)
anomaly_map[10:20, 10:20] = 1.0
gt_mask = np.zeros((100, 100))
gt_mask[15:25, 15:25] = 1.0
image = np.random.randint(0, 255, size=(100, 100, 3), dtype=np.uint8)
image_result = ImageResult(
    image=image,
    pred_score=0.9,
    pred_label="abnormal",
    text_descr=("Some very long text to see how it is formatted in the image"
                " Some very long text to see how it is formatted in the image"),
    anomaly_map= anomaly_map,
    gt_mask = gt_mask,
    pred_mask = anomaly_map,
)

image_visualizer = ImageVisualizer(
    mode = VisualizationMode.FULL,
    task= TaskType.EXPLANATION,
)
result = image_visualizer.visualize_image(image_result)

plt.imshow(result)
plt.show()

[ashwinvaidya17]

Thanks! Looks fine overall. I just have a few minor comments.

[ashwinvaidya17]

Thanks looks good to me