Re-activate pytests (#208)

Author: jgbradley1

Diff for: .azdo/azure-pipeline.yaml

@@ -30,11 +30,12 @@ extends:
         jobs:
         - job: CG_Prep
           steps:
-            # Component Governance does not support pyproject.toml yet.
-            # for this reason, use toml-to-requirements to export dependencies into a requirements.txt file.
+            # Component Governance (CG) does not support pyproject.toml yet.
+            # For this reason, use toml-to-requirements to export dependencies into a requirements.txt file.
+            # CG will auto-detect the requirements.txt file and use it to scan for dependencies.
             - script: |
                 pip install toml-to-requirements
-                toml-to-req --toml-file pyproject.toml --poetry --optional-lists dev,test,backend,frontend
+                toml-to-req --toml-file backend/pyproject.toml --poetry --optional-lists dev,test,backend,frontend
                 # toml-to-req is not perfect. It will leave wildcard characters in the requirements.txt file which we remove
                 sed -i 's/\*//g' requirements.txt
               displayName: 'Export python dependencies to requirements.txt for CG'

Diff for: .devcontainer/Dockerfile

@@ -1,15 +1,15 @@
-FROM python:3.10
+# For more information about the base image visit:
+# https://mcr.microsoft.com/en-us/artifact/mar/devcontainers/python/about
+FROM mcr.microsoft.com/devcontainers/python:3.10-bookworm
 
-# avoid common warnings
+# disable common warning messages
 ENV DEBIAN_FRONTEND=noninteractive
 ENV PIP_ROOT_USER_ACTION=ignore
 ENV PIP_DISABLE_PIP_VERSION_CHECK=1
 
 # configure environment
 ARG ENVNAME="GraphRAG"
 ARG USERNAME=vscode
-ARG USER_UID=1001
-ARG USER_GID=$USER_UID
 ARG WORKDIR=/${ENVNAME}
 
 # install python, pip, git, and other required tools
@@ -53,13 +53,11 @@ RUN rm -rf /var/lib/apt/lists/* \
 # set the location for the virtual environments to be outside the project directory
 ENV POETRY_VIRTUALENVS_IN_PROJECT=true
 
-# set up non-root user
-RUN useradd -ms /bin/bash -u ${USER_GID} ${USERNAME} \
-    && echo "${USERNAME}:${USERNAME}" | chpasswd \
-    # add user to sudo group and docker group
+# a non-root user (vscode) already exist in the base image. Add it to sudo group and docker group
+RUN echo "${USERNAME}:${USERNAME}" | chpasswd \
     && adduser ${USERNAME} sudo \
-    && echo '%sudo ALL=(ALL) NOPASSWD:ALL' >> /etc/sudoers \
-    && usermod -aG docker ${USERNAME}
+    && adduser ${USERNAME} docker \
+    && echo '%sudo ALL=(ALL) NOPASSWD:ALL' >> /etc/sudoers
 
 # switch to non-root user
 USER ${USERNAME}
@@ -73,13 +71,13 @@ ENV PATH="/home/${USERNAME}/.local/bin:${PATH}"
 ENV PATH=/graphrag-accelerator/.venv/bin:$PATH
 
 # copy the project files into the container and set ownership
-COPY --chown=${USERNAME}:${USER_GID} . ${WORKDIR}
+COPY --chown=${USERNAME}:${USERNAME} . ${WORKDIR}
 
 COPY entrypoint.sh /usr/local/bin/entrypoint.sh
 
 # Create directories for vscode server and extensions
-RUN mkdir -p /home/$USERNAME/.vscode-server/extensions \
-    && chown -R $USER_UID:$USER_GID /home/$USERNAME/.vscode-server
+RUN mkdir -p ~/.vscode-server/extensions \
+    && chown -R $USERNAME:$USERNAME ~/.vscode-server
 
 ENTRYPOINT [ "/usr/local/bin/entrypoint.sh" ]
 CMD ["bash"]

Diff for: .github/workflows/tests.yaml

@@ -0,0 +1,66 @@
+name: Testing
+on:
+  workflow_dispatch: # triggered manually via the GitHub UI
+  pull_request:      # triggered when a PR is created or updated
+    types:
+      - opened
+      - reopened
+      - synchronize
+      - ready_for_review
+    paths:             # only trigger on changes in specific directories
+      - '.github/**/*.yaml'
+      - 'backend/**'
+      - 'docker/**'
+      - 'backend/poetry.lock'
+      - 'backend/pyproject.toml'
+
+env:
+  PYTHON_VERSION: '3.10'
+
+jobs:
+  tests:
+    runs-on: windows-latest
+    steps:
+      - name: Checkout repository
+        uses: actions/checkout@v4
+
+      - name: Install python
+        uses: actions/setup-python@v5
+        with:
+          python-version: '3.10'
+
+      - name: Install Azurite
+        shell: bash
+        run: |
+          npm install -g azurite
+          azurite --silent &
+
+      # For more information on installation/setup of Azure Cosmos DB Emulator
+      # https://learn.microsoft.com/en-us/azure/cosmos-db/how-to-develop-emulator?tabs=docker-linux%2Cpython&pivots=api-nosql
+      # Note: the emulator is only available on Windows runners. It can take longer than the default to initially startup so we increase the default timeout.
+      # If a job fails due to timeout, restarting the cicd job usually resolves the problem.
+      - name: Install Azure Cosmos DB emulator
+        run: |
+          Write-Host "Launching Cosmos DB Emulator"
+          Import-Module "$env:ProgramFiles\Azure Cosmos DB Emulator\PSModules\Microsoft.Azure.CosmosDB.Emulator"
+          Start-CosmosDbEmulator -Timeout 500
+
+      - name: Install dependencies
+        working-directory: ${{ github.workspace }}/backend
+        run: |
+          pip install poetry
+          poetry config virtualenvs.create false
+          poetry install --with test
+
+      - name: Run pytests
+        working-directory: ${{ github.workspace }}/backend
+        run: |
+          pytest --cov=src --junitxml=test-results.xml tests/
+
+      - name: Upload test results
+        uses: actions/upload-artifact@v4
+        with:
+          name: pytest-results
+          path: ${{ github.workspace }}/backend/test-results.xml
+        # Use always() to always run this step to publish test results when there are test failures
+        if: ${{ always() }}