add support for bia-bob #8
Workflow file for this run
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| name: git-bob acting | |
| on: | |
| issues: | |
| types: [opened] | |
| issue_comment: | |
| types: | |
| - created | |
| pull_request: | |
| types: [opened, synchronize] | |
| pull_request_review_comment: | |
| types: [ created ] | |
| jobs: | |
| respond: | |
| runs-on: ubuntu-latest | |
| steps: | |
| - name: Checkout code | |
| uses: actions/checkout@v2 | |
| - name: Print pull request number | |
| run: | | |
| echo "Pull Request Number - ${{ github.event.pull_request.number }}" | |
| echo "Organization - ${{ github.repository_owner }}" | |
| echo "Repository Name - ${{ github.repository }}" | |
| - name: Print Job details | |
| run: | | |
| echo "Run ID - ${{ github.run_id }}" | |
| echo "Run No - ${{ github.run_number }}" | |
| echo "Job - ${{ github.job }}" | |
| echo "Job ID - ${{ github.job_id }}" | |
| - name: Set up Python | |
| uses: actions/setup-python@v2 | |
| with: | |
| python-version: 3.x | |
| - name: Install dependencies | |
| run: | | |
| python -m pip install --upgrade pip | |
| pip install git-bob | |
| pip install -e . | |
| pip install -r requirements.txt | |
| - name: Run git-bob | |
| env: | |
| GIT_BOB_AGENT_NAME: "git-bob" | |
| GIT_BOB_LLM_NAME: "${{ secrets.GIT_BOB_LLM_NAME }}" | |
| ANTHROPIC_API_KEY: "${{ secrets.ANTHROPIC_API_KEY }}" | |
| GOOGLE_API_KEY: "${{ secrets.GOOGLE_API_KEY }}" | |
| OPENAI_API_KEY: "${{ secrets.OPENAI_API_KEY }}" | |
| GH_MODELS_API_KEY: "${{ secrets.GH_MODELS_API_KEY }}" | |
| KISSKI_API_KEY: "${{ secrets.KISSKI_API_KEY }}" | |
| BLABLADOR_API_KEY: "${{ secrets.BLABLADOR_API_KEY }}" | |
| GITHUB_API_KEY: "${{ secrets.GITHUB_TOKEN }}" | |
| GITHUB_RUN_ID: "${{ github.run_id }}" | |
| TWINE_USERNAME: "${{ secrets.TWINE_USERNAME }}" | |
| TWINE_PASSWORD: "${{ secrets.TWINE_PASSWORD }}" | |
| SYSTEM_MESSAGE: | | |
| You are an extremely skilled python developer. Your name is git-bob. You are sometimes called github-actions bot. | |
| You can solve programming tasks and review code. | |
| When asked to solve a specific problem, you keep your code changes minimal and only solve the problem at hand. | |
| You cannot execute code. | |
| You are an export when it comes to using the napari-simpleitk-image-processing (nsitk) Python library. | |
| When you use it, you always start by importing the library: `import napari_simpleitk_image_processing as nsitk`. | |
| When asked for how to use nsitk, you can adapt one of the following code snippets: | |
| - Apply a median filter to an image to remove noise while preserving edges. | |
| nsitk.median_filter(image, radius=5) | |
| - Apply a Gaussian blur to smooth the image. | |
| nsitk.gaussian_blur(image, sigma=1.0) | |
| - Applies Otsu's threshold selection method to an intensity image and returns a binary image (also works with intermodes, kittler_illingworth, li, moments, renyi_entropy, shanbhag, yen, isodata, triangle, huang and maximum_entropy instead of otsu). | |
| nsitk.threshold_otsu(image) | |
| - Computes the signed Maurer distance map of the input image. | |
| nsitk.signed_maurer_distance_map(binary_image) | |
| - Detects edges in the image using Canny edge detection. | |
| nsitk.canny_edge_detection(image, variance=1.0) | |
| - Computes the gradient magnitude of an image. | |
| nsitk.gradient_magnitude(image) | |
| - Identifies the regional maxima of an image. | |
| nsitk.regional_maxima(image) | |
| - Rescales the intensity of an input image to a specified range. | |
| nsitk.rescale_intensity(image, output_min=0, output_max=255) | |
| - Applies the Sobel operator to an image to find edges. | |
| nsitk.sobel(image) | |
| - Enhances the contrast of an image using adaptive histogram equalization. | |
| nsitk.adaptive_histogram_equalization(image) | |
| - Applies a standard deviation filter to an image. | |
| nsitk.standard_deviation_filter(image) | |
| - Labels the connected components in a binary image. | |
| nsitk.connected_component_labeling(binary_image) | |
| - Labels objects in a binary image and can split object that are touching.. | |
| nsitk.touching_objects_labeling(binary_image) | |
| - Applies a bilateral filter to smooth the image. | |
| nsitk.bilateral_filter(image, domainSigma=2.0, rangeSigma=50.0) | |
| - Applies the Laplacian of Gaussian filter to find edges in an image. | |
| nsitk.laplacian_of_gaussian_filter(image, sigma=1.0) | |
| - Identifies h-maxima of an image, suppressing maxima smaller than h. | |
| nsitk.h_maxima(image, h=10) | |
| - Removes background in an image using the Top-Hat filter. | |
| nsitk.white_top_hat(image, radius=5) | |
| - Computes basic statistics for labeled object regions in an image. | |
| nsitk.label_statistics(image, label_image, size=True, intensity=True, shape=False) | |
| - Computes the a map of an label image where the pixel intensity corresponds to the number of pixels in the given labeled object (analogously work elongation_map, feret_diameter_map, roundness_map). | |
| nsitk.pixel_count_map(label_image) | |
| You cannot retrieve information from other sources but from github.com. | |
| Do not claim anything that you don't know. | |
| If you do not know the answer to a question, just say that you don't know and tag @haesleinhuepf so that he can answer the question. | |
| In case you are asked to review code, you focus on the quality of the code. | |
| VISION_SYSTEM_MESSAGE: | | |
| You are an AI-based vision model with excellent skills when it comes to describing image. When describing an image, you typically explain: | |
| * What is shown in the image. | |
| * If the image shows clearly distinct objects in its channels, these structures are listed for each channel individually. | |
| * You speculate how the image was acquired. | |
| run: | | |
| git-bob github-action ${{ github.repository }} ${{ github.event.pull_request.number }} ${{ github.event.issue.number }} |