Model Upload Workflow: Tracing-Uploading-Releasing #34
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: Model Auto-tracing & Uploading | |
| on: | |
| workflow_dispatch: | |
| inputs: | |
| model_id: | |
| description: "Model ID for auto-tracing and uploading (e.g. sentence-transformers/msmarco-distilbert-base-tas-b)" | |
| required: true | |
| type: string | |
| model_version: | |
| description: "Model version number (e.g. 1.0.1)" | |
| required: true | |
| type: string | |
| tracing_format: | |
| description: "Model format for auto-tracing (torch_script/onnx)" | |
| required: true | |
| type: choice | |
| options: | |
| - "BOTH" | |
| - "TORCH_SCRIPT" | |
| - "ONNX" | |
| allow_overwrite: | |
| description: "Allow overwrites on model hub" | |
| required: true | |
| type: choice | |
| default: "False" | |
| options: | |
| - "False" | |
| - "True" | |
| embedding_dimension: | |
| description: "(Optional) Embedding Dimension (Specify here if it does not exist in original config.json file. Else, it will use 768)" | |
| required: false | |
| type: int | |
| pooling_mode: | |
| description: "(Optional) Pooling Mode (Specify here if it does not exist in original config.json file)" | |
| required: false | |
| type: choice | |
| options: | |
| - "" | |
| - "CLS" | |
| - "MEAN" | |
| - "MAX" | |
| - "MEAN_SQRT_LEN" | |
| jobs: | |
| checking-out-model-hub: | |
| runs-on: 'ubuntu-latest' | |
| permissions: | |
| id-token: write | |
| contents: read | |
| outputs: | |
| overwritting: ${{ steps.checking-out-model-hub.outputs.overwritting }} | |
| steps: | |
| - name: Checkout Repository | |
| uses: actions/checkout@v3 | |
| - name: Set Up Python | |
| uses: actions/setup-python@v2 | |
| with: | |
| python-version: '3.x' | |
| - name: Configure AWS credentials | |
| uses: aws-actions/configure-aws-credentials@v2 | |
| with: | |
| aws-region: ${{ secrets.MODEL_UPLOADER_AWS_REGION }} | |
| role-to-assume: ${{ secrets.MODEL_UPLOADER_ROLE }} | |
| role-session-name: GitHubActions | |
| - name: Initiate Overwriting Variable | |
| run: echo "OVERWRITING=false" >> $GITHUB_OUTPUT | |
| - name: Check if TORCH_SCRIPT Model Exists | |
| if: ${{ github.event.inputs.model_version == 'TORCH_SCRIPT'}} || ${{ github.event.inputs.model_version == 'BOTH'}} | |
| run: | | |
| TORCH_FILE_PATH=$(python utils/model_uploader/save_model_file_path_to_env.py ${{ github.event.inputs.model_id }} ${{ github.event.inputs.model_version }} TORCH_SCRIPT) | |
| aws s3api head-object --bucket opensearch-exp --key $TORCH_FILE_PATH || TORCH_MODEL_NOT_EXIST=true | |
| if [[ !$TORCH_MODEL_NOT_EXIST && ${{ github.event.inputs.allow_overwrite == 'False' }} ]]; | |
| then | |
| echo "TORCH_SCRIPT Model already exists on model hub. (allow_overwrite=false)" | |
| exit 1 | |
| elif [[ !$TORCH_MODEL_NOT_EXIST && ${{ github.event.inputs.allow_overwrite == 'True' }} ]]; | |
| then | |
| echo "OVERWRITING=true" >> $GITHUB_OUTPUT | |
| fi | |
| - name: Check if ONNX Model Exists | |
| if: ${{ github.event.inputs.model_version == 'ONNX'}} || ${{ github.event.inputs.model_version == 'BOTH'}} | |
| run: | | |
| ONNX_FILE_PATH=$(python utils/model_uploader/save_model_file_path_to_env.py ${{ github.event.inputs.model_id }} ${{ github.event.inputs.model_version }} ONNX) | |
| aws s3api head-object --bucket opensearch-exp --key $ONNX_FILE_PATH || ONNX_MODEL_NOT_EXIST=true | |
| if [[ !$ONNX_MODEL_NOT_EXIST && ${{ github.event.inputs.allow_overwrite == 'False' }} ]]; | |
| then | |
| echo "TORCH_SCRIPT Model already exists on model hub. (allow_overwrite=false)" | |
| exit 1; | |
| elif [[ !$ONNX_MODEL_NOT_EXIST && ${{ github.event.inputs.allow_overwrite == 'True' }} ]]; | |
| then | |
| echo "OVERWRITING=true" >> $GITHUB_OUTPUT | |
| fi | |
| model-auto-tracing: | |
| needs: checking-out-model-hub | |
| name: model-auto-tracing | |
| runs-on: ubuntu-latest | |
| strategy: | |
| fail-fast: false | |
| matrix: | |
| cluster: ["opensearch"] | |
| secured: ["true"] | |
| entry: | |
| - { opensearch_version: 2.7.0 } | |
| steps: | |
| - name: Checkout | |
| uses: actions/checkout@v2 | |
| - name: Export Arguments | |
| run: | | |
| echo "MODEL_ID=${{ github.event.inputs.model_id }}" >> $GITHUB_ENV | |
| echo "MODEL_VERSION=${{ github.event.inputs.model_version }}" >> $GITHUB_ENV | |
| echo "TRACING_FORMAT=${{ github.event.inputs.tracing_format }}" >> $GITHUB_ENV | |
| echo "ALLOW_OVERWRITE=${{ github.event.inputs.allow_overwrite }}" >> $GITHUB_ENV | |
| echo "EMBEDDING_DIMENSION=${{ github.event.inputs.embedding_dimension }}" >> $GITHUB_ENV | |
| echo "POOLING_MODE=${{ github.event.inputs.pooling_mode }}" >> $GITHUB_ENV | |
| - name: Autotracing ${{ matrix.cluster }} secured=${{ matrix.secured }} version=${{matrix.entry.opensearch_version}} | |
| run: "./.ci/run-tests ${{ matrix.cluster }} ${{ matrix.secured }} ${{ matrix.entry.opensearch_version }} trace" | |
| - name: Upload Artifact | |
| uses: actions/upload-artifact@v3 | |
| with: | |
| name: upload | |
| path: ./upload/ | |
| retention-days: 5 | |
| manual-approval: | |
| needs: [checking-out-model-hub, model-auto-tracing] | |
| runs-on: 'ubuntu-latest' | |
| permissions: | |
| issues: write | |
| steps: | |
| - name: Checkout Repository | |
| uses: actions/checkout@v3 | |
| - id: get_approvers | |
| run: | | |
| echo "approvers=$(cat .github/CODEOWNERS | grep @ | tr -d '* ' | sed 's/@/,/g' | sed 's/,//1')" >> $GITHUB_OUTPUT | |
| - uses: trstringer/manual-approval@v1 | |
| with: | |
| secret: ${{ github.TOKEN }} | |
| approvers: ${{ steps.get_approvers.outputs.approvers }} | |
| minimum-approvals: 1 | |
| issue-title: "Upload opensearch-py-ml model to Amazon S3 Bucket (${{ github.event.inputs.model_id }})" | |
| issue-body: > | |
| Please approve or deny opensearch-py-ml model uploading | |
| - Model ID: ${{ github.event.inputs.model_id }} | |
| - Model Version: ${{ github.event.inputs.model_version }} | |
| - Tracing Format: ${{ github.event.inputs.tracing_format }} | |
| - Allow Overwrite: ${{ github.event.inputs.allow_overwrite }} | |
| - Overwriting: {{ needs.checking-out-model-hub.outputs.overwritting }} | |
| - Embedding Dimension: ${{ github.event.inputs.embedding_dimension }} | |
| - Pooling Mode: ${{ github.event.inputs.pooling_mode }} | |
| exclude-workflow-initiator-as-approver: false | |
| model-uploading: | |
| needs: manual-approval | |
| runs-on: 'ubuntu-latest' | |
| permissions: | |
| id-token: write | |
| contents: read | |
| steps: | |
| - name: Download artifact | |
| uses: actions/download-artifact@v2 | |
| with: | |
| name: upload | |
| path: ./upload/ | |
| - name: Configure AWS credentials | |
| uses: aws-actions/configure-aws-credentials@v2 | |
| with: | |
| aws-region: ${{ secrets.MODEL_UPLOADER_AWS_REGION }} | |
| role-to-assume: ${{ secrets.MODEL_UPLOADER_ROLE }} | |
| role-session-name: GitHubActions | |
| - name: Copy files to the bucket | |
| run: | | |
| aws s3 sync ./upload/ s3://opensearch-exp/sentence-transformers/ |