[Automating Model Tracing and Uploading] PR 1 Model Auto-tracing & Up…

…loading (#209) * Initiate PR #1 Model Auto-tracing & Uploading Signed-off-by: Thanawan Atchariyachanvanit <latchari@amazon.com> * Improve update_changelog_md.py & sentencetransformermodel.py scraping Signed-off-by: Thanawan Atchariyachanvanit <latchari@amazon.com> * Change default to N/A Signed-off-by: Thanawan Atchariyachanvanit <latchari@amazon.com> * Update update_models_upload_history_md.py Signed-off-by: Thanawan Atchariyachanvanit <latchari@amazon.com> * Update delete_model_uploader_branch.yml Signed-off-by: Thanawan Atchariyachanvanit <latchari@amazon.com> * Correct linting & Update CHANGELOG.md Signed-off-by: Thanawan Atchariyachanvanit <latchari@amazon.com> * Revert "Correct demo_ml_commons_integration.ipynb (#208)" This reverts commit 664e447. Signed-off-by: Thanawan Atchariyachanvanit <latchari@amazon.com> * Update CHANGELOG.md Signed-off-by: Thanawan Atchariyachanvanit <latchari@amazon.com> * Small fix Signed-off-by: Thanawan Atchariyachanvanit <latchari@amazon.com> * Add model_type Signed-off-by: Thanawan Atchariyachanvanit <latchari@amazon.com> * Removed a modified file from pull request Signed-off-by: Thanawan Atchariyachanvanit <latchari@amazon.com> * Removed a modified file from pull request Signed-off-by: Thanawan Atchariyachanvanit <latchari@amazon.com> * Update model_autotracing.py Signed-off-by: Thanawan Atchariyachanvanit <latchari@amazon.com> * Update model_autotracing.py Signed-off-by: Thanawan Atchariyachanvanit <latchari@amazon.com> * Update model_autotracing.py Signed-off-by: Thanawan Atchariyachanvanit <latchari@amazon.com> --------- Signed-off-by: Thanawan Atchariyachanvanit <latchari@amazon.com>
thanawan-atc · Aug 19, 2023 · 20223e6 · 20223e6
1 parent 9b558c7
commit 20223e6
Show file tree

Hide file tree

Showing 14 changed files with 1,585 additions and 15 deletions.
diff --git a/.ci/run-repository.sh b/.ci/run-repository.sh
@@ -1,6 +1,6 @@
 #!/usr/bin/env bash
 
-# Called by entry point `run-test` use this script to add your repository specific test commands
+# Called by entry point `run-test` use this script to add your repository specific task commands
 # Once called opensearch is up and running and the following parameters are available to this script
 
 # OPENSEARCH_VERSION -- version e.g Major.Minor.Patch(-Prelease)
@@ -16,7 +16,7 @@ set -e
 echo -e "\033[34;1mINFO:\033[0m URL ${opensearch_url}\033[0m"
 echo -e "\033[34;1mINFO:\033[0m EXTERNAL OS URL ${external_opensearch_url}\033[0m"
 echo -e "\033[34;1mINFO:\033[0m VERSION ${OPENSEARCH_VERSION}\033[0m"
-echo -e "\033[34;1mINFO:\033[0m IS_DOC: ${IS_DOC}\033[0m"
+echo -e "\033[34;1mINFO:\033[0m TASK_TYPE: ${TASK_TYPE}\033[0m"
 echo -e "\033[34;1mINFO:\033[0m TEST_SUITE ${TEST_SUITE}\033[0m"
 echo -e "\033[34;1mINFO:\033[0m PYTHON_VERSION ${PYTHON_VERSION}\033[0m"
 echo -e "\033[34;1mINFO:\033[0m PYTHON_CONNECTION_CLASS ${PYTHON_CONNECTION_CLASS}\033[0m"
@@ -33,7 +33,8 @@ docker build \
 echo -e "\033[1m>>>>> Run [opensearch-project/opensearch-py-ml container] >>>>>>>>>>>>>>>>>>>>>>>>>>>>>\033[0m"
 
 
-if [[ "$IS_DOC" == "false" ]]; then
+if [[ "$TASK_TYPE" == "test" ]]; then
+  # Set up OpenSearch cluster & Run integration and unit tests (Invoked by integration.yml workflow)
   docker run \
   --network=${network_name} \
   --env "STACK_VERSION=${STACK_VERSION}" \
@@ -45,10 +46,11 @@ if [[ "$IS_DOC" == "false" ]]; then
   --name opensearch-py-ml-test-runner \
   opensearch-project/opensearch-py-ml \
   nox -s "test-${PYTHON_VERSION}(pandas_version='${PANDAS_VERSION}')"
+
   docker cp opensearch-py-ml-test-runner:/code/opensearch-py-ml/junit/ ./junit/
-
   docker rm opensearch-py-ml-test-runner
-else
+elif [[ "$TASK_TYPE" == "doc" ]]; then
+  # Set up OpenSearch cluster & Run docs (Invoked by build_deploy_doc.yml workflow)
   docker run \
   --network=${network_name} \
   --env "STACK_VERSION=${STACK_VERSION}" \
@@ -60,7 +62,31 @@ else
   --name opensearch-py-ml-doc-runner \
   opensearch-project/opensearch-py-ml \
   nox -s docs
+
   docker cp opensearch-py-ml-doc-runner:/code/opensearch-py-ml/docs/build/ ./docs/
-
   docker rm opensearch-py-ml-doc-runner
-fi
+elif [[ "$TASK_TYPE" == "trace" ]]; then
+  # Set up OpenSearch cluster & Run model autotracing (Invoked by model_uploader.yml workflow)
+  echo -e "\033[34;1mINFO:\033[0m MODEL_ID: ${MODEL_ID}\033[0m"
+  echo -e "\033[34;1mINFO:\033[0m MODEL_VERSION: ${MODEL_VERSION}\033[0m"
+  echo -e "\033[34;1mINFO:\033[0m TRACING_FORMAT: ${TRACING_FORMAT}\033[0m"
+  echo -e "\033[34;1mINFO:\033[0m EMBEDDING_DIMENSION: ${EMBEDDING_DIMENSION:-N/A}\033[0m"
+  echo -e "\033[34;1mINFO:\033[0m POOLING_MODE: ${POOLING_MODE:-N/A}\033[0m"
+  echo -e "\033[34;1mINFO:\033[0m MODEL_DESCRIPTION: ${MODEL_DESCRIPTION:-N/A}\033[0m"
+
+  docker run \
+  --network=${network_name} \
+  --env "STACK_VERSION=${STACK_VERSION}" \
+  --env "OPENSEARCH_URL=${opensearch_url}" \
+  --env "OPENSEARCH_VERSION=${OPENSEARCH_VERSION}" \
+  --env "TEST_SUITE=${TEST_SUITE}" \
+  --env "PYTHON_CONNECTION_CLASS=${PYTHON_CONNECTION_CLASS}" \
+  --env "TEST_TYPE=server" \
+  --name opensearch-py-ml-trace-runner \
+  opensearch-project/opensearch-py-ml \
+  nox -s trace -- ${MODEL_ID} ${MODEL_VERSION} ${TRACING_FORMAT} -ed ${EMBEDDING_DIMENSION} -pm ${POOLING_MODE} -md ${MODEL_DESCRIPTION:+"$MODEL_DESCRIPTION"}
+
+  docker cp opensearch-py-ml-trace-runner:/code/opensearch-py-ml/upload/ ./upload/
+  docker cp opensearch-py-ml-trace-runner:/code/opensearch-py-ml/trace_output/ ./trace_output/
+  docker rm opensearch-py-ml-trace-runner
+fi
diff --git a/.ci/run-tests b/.ci/run-tests
@@ -10,7 +10,7 @@ export PYTHON_CONNECTION_CLASS="${PYTHON_CONNECTION_CLASS:=Urllib3HttpConnection
 export CLUSTER="${1:-opensearch}"
 export SECURE_INTEGRATION="${2:-true}"
 export OPENSEARCH_VERSION="${3:-latest}"
-export IS_DOC="${4:-false}"
+export TASK_TYPE="${4:-test}"
 if [[ "$SECURE_INTEGRATION" == "true" ]]; then
     export OPENSEARCH_URL_EXTENSION="https"
 else

diff --git a/.github/workflows/build_deploy_doc.yml b/.github/workflows/build_deploy_doc.yml
@@ -20,7 +20,7 @@ jobs:
       - name: Checkout Repository
         uses: actions/checkout@v2
       - name: Integ ${{ matrix.cluster }} secured=${{ matrix.secured }} version=${{matrix.entry.opensearch_version}}
-        run: "./.ci/run-tests ${{ matrix.cluster }} ${{ matrix.secured }} ${{ matrix.entry.opensearch_version }} true"
+        run: "./.ci/run-tests ${{ matrix.cluster }} ${{ matrix.secured }} ${{ matrix.entry.opensearch_version }} doc"
       - name: Deploy
         uses: peaceiris/actions-gh-pages@v3
         with:

diff --git a/.github/workflows/delete_model_uploader_branch.yml b/.github/workflows/delete_model_uploader_branch.yml
@@ -0,0 +1,18 @@
+name: Delete merged branch for model-uploader & model-listing-uploader 
+on: 
+  pull_request:
+    types:
+      - closed
+
+jobs:
+  delete-branch:
+    runs-on: ubuntu-latest
+    if: startsWith(github.event.pull_request.head.ref,'model-uploader/') || startsWith(github.event.pull_request.head.ref,'model-listing-uploader/')
+    steps:
+      # Compared to backport.yml, this GitHub action will delete branch
+      # of a PR that is closed, but not merged as well.
+      - name: Delete closed PR branch
+        uses: dawidd6/action-delete-branch@v3
+        with:
+          GITHUB_TOKEN: ${{github.token}}
+          numbers: ${{github.event.pull_request.number}}
diff --git a/.github/workflows/integration.yml b/.github/workflows/integration.yml
@@ -18,7 +18,7 @@ jobs:
       - name: Checkout
         uses: actions/checkout@v2
       - name: Integ ${{ matrix.cluster }} secured=${{ matrix.secured }} version=${{matrix.entry.opensearch_version}}
-        run: "./.ci/run-tests ${{ matrix.cluster }} ${{ matrix.secured }} ${{ matrix.entry.opensearch_version }}"
+        run: "./.ci/run-tests ${{ matrix.cluster }} ${{ matrix.secured }} ${{ matrix.entry.opensearch_version }} test"
       - name: Upload coverage to Codecov
         uses: codecov/codecov-action@v2
         with: