Devops

.github/workflows/deploy.yml

@@ -9,10 +9,12 @@ on:
 env:
   REGISTRY: crretoxmas2024.azurecr.io
   NAMESPACE: reto-xmas-2025-goland-ia-backend
+  DEPLOY_TIMEOUT: 3m
 
 jobs:
   build-and-deploy:
     runs-on: ubuntu-latest
+    timeout-minutes: 15
     strategy:
       fail-fast: false
       matrix:
@@ -51,6 +53,7 @@ jobs:
           ${{ env.REGISTRY }}/${{ matrix.service.image }}:${{ github.sha }}
         cache-from: type=registry,ref=${{ env.REGISTRY }}/${{ matrix.service.image }}:buildcache
         cache-to: type=registry,ref=${{ env.REGISTRY }}/${{ matrix.service.image }}:buildcache,mode=max
+        provenance: false
 
     - name: Set up kubectl
       uses: azure/setup-kubectl@v3
@@ -63,28 +66,66 @@ jobs:
         echo "${{ secrets.KUBECONFIG }}" | base64 -d > $HOME/.kube/config
         chmod 600 $HOME/.kube/config
 
-    - name: Restart deployment
+    - name: Update deployment image
       run: |
-        kubectl rollout restart deployment/${{ matrix.service.deployment }} -n ${{ env.NAMESPACE }}
-        kubectl rollout status deployment/${{ matrix.service.deployment }} -n ${{ env.NAMESPACE }} --timeout=5m
+        kubectl set image deployment/${{ matrix.service.deployment }} \
+          api=${{ env.REGISTRY }}/${{ matrix.service.image }}:${{ github.sha }} \
+          -n ${{ env.NAMESPACE }}
+
+    - name: Wait for rollout
+      timeout-minutes: 5
+      run: |
+        kubectl rollout status deployment/${{ matrix.service.deployment }} \
+          -n ${{ env.NAMESPACE }} \
+          --timeout=${{ env.DEPLOY_TIMEOUT }} || {
+            echo "Deployment failed or timed out"
+            kubectl get pods -n ${{ env.NAMESPACE }} -l app=${{ matrix.service.deployment }}
+            exit 1
+          }
 
     - name: Verify deployment
+      if: success()
       run: |
-        echo "✅ Deployment successful for ${{ matrix.service.name }}"
+        echo "Deployment successful for ${{ matrix.service.name }}"
         kubectl get pods -n ${{ env.NAMESPACE }} -l app=${{ matrix.service.deployment }}
 
+    - name: Get logs on failure
+      if: failure()
+      run: |
+        echo "=== Pod Logs ==="
+        kubectl logs -n ${{ env.NAMESPACE }} \
+          -l app=${{ matrix.service.deployment }} \
+          --tail=100 \
+          --all-containers=true \
+          --prefix=true || echo "Could not fetch logs"
+
+    - name: Rollback on failure
+      if: failure()
+      run: |
+        echo "Rolling back deployment"
+        kubectl rollout undo deployment/${{ matrix.service.deployment }} -n ${{ env.NAMESPACE }}
+
     - name: Deployment Summary
       if: always()
       run: |
-        echo "### 🚀 Deployment Summary" >> $GITHUB_STEP_SUMMARY
+        STATUS="${{ job.status }}"
+
+        echo "### Deployment - ${{ matrix.service.name }}" >> $GITHUB_STEP_SUMMARY
         echo "" >> $GITHUB_STEP_SUMMARY
-        echo "**Service:** ${{ matrix.service.name }}" >> $GITHUB_STEP_SUMMARY
-        echo "**Image:** ${{ env.REGISTRY }}/${{ matrix.service.image }}:${{ github.sha }}" >> $GITHUB_STEP_SUMMARY
-        echo "**Status:** ${{ job.status }}" >> $GITHUB_STEP_SUMMARY
+        echo "| Property | Value |" >> $GITHUB_STEP_SUMMARY
+        echo "|----------|-------|" >> $GITHUB_STEP_SUMMARY
+        echo "| Image | \`${{ env.REGISTRY }}/${{ matrix.service.image }}:${{ github.sha }}\` |" >> $GITHUB_STEP_SUMMARY
+
+        if [ "$STATUS" == "success" ]; then
+          echo "| Status | Success |" >> $GITHUB_STEP_SUMMARY
+        else
+          echo "| Status | Failed |" >> $GITHUB_STEP_SUMMARY
+        fi
+
         echo "" >> $GITHUB_STEP_SUMMARY
         echo "#### Pods:" >> $GITHUB_STEP_SUMMARY
         echo '```' >> $GITHUB_STEP_SUMMARY
-        kubectl get pods -n ${{ env.NAMESPACE }} -l app=${{ matrix.service.deployment }} >> $GITHUB_STEP_SUMMARY
+        kubectl get pods -n ${{ env.NAMESPACE }} -l app=${{ matrix.service.deployment }} >> $GITHUB_STEP_SUMMARY || true
         echo '```' >> $GITHUB_STEP_SUMMARY
 
   notify-success:
@@ -95,8 +136,20 @@ jobs:
     steps:
     - name: Success Summary
       run: |
-        echo "### ✅ Deployment Successful!" >> $GITHUB_STEP_SUMMARY
+        echo "### ll Services Deployed!" >> $GITHUB_STEP_SUMMARY
+        echo "" >> $GITHUB_STEP_SUMMARY
+        echo "**Live URLs:**" >> $GITHUB_STEP_SUMMARY
+        echo "- [DocsManager](https://goland-ia-backend-docs-manager.reto-ucu.net/docs)" >> $GITHUB_STEP_SUMMARY
+        echo "- [RAGManager](https://goland-ia-backend-rag-manager.reto-ucu.net/docs)" >> $GITHUB_STEP_SUMMARY
+
+  notify-failure:
+    name: Deployment Failed
+    runs-on: ubuntu-latest
+    needs: [build-and-deploy]
+    if: failure()
+    steps:
+    - name: Failure Summary
+      run: |
+        echo "### Deployment Failed" >> $GITHUB_STEP_SUMMARY
         echo "" >> $GITHUB_STEP_SUMMARY
-        echo "All services deployed successfully:" >> $GITHUB_STEP_SUMMARY
-        echo "- 🌐 DocsManager: https://goland-ia-backend-docs-manager.reto-ucu.net" >> $GITHUB_STEP_SUMMARY
-        echo "- 🌐 RAGManager: https://goland-ia-backend-rag-manager.reto-ucu.net" >> $GITHUB_STEP_SUMMARY
+        echo "Automatic rollback initiated" >> $GITHUB_STEP_SUMMARY

DocsManager/Dockerfile

@@ -1,13 +1,22 @@
-FROM ghcr.io/astral-sh/uv:python3.13-bookworm-slim
+FROM python:3.12-slim
 
 WORKDIR /app
 
-COPY pyproject.toml uv.lock* ./
+RUN apt-get update && apt-get install -y \
+    curl \
+    && rm -rf /var/lib/apt/lists/*
 
-RUN uv sync --frozen --no-cache || uv sync --no-cache
+RUN curl -LsSf https://astral.sh/uv/install.sh | sh && \
+    mv /root/.local/bin/uv /usr/local/bin/uv && \
+    mv /root/.local/bin/uvx /usr/local/bin/uvx
 
 COPY . .
 
+RUN uv sync --no-dev --no-cache
+
 EXPOSE 8000
 
-CMD ["uv", "run", "uvicorn", "main:app", "--host", "0.0.0.0", "--port", "8000"]
+HEALTHCHECK --interval=30s --timeout=10s --start-period=40s --retries=3 \
+    CMD curl -f http://localhost:8000/health || exit 1
+
+CMD ["uv", "run", "--no-sync", "uvicorn", "app:main", "--host", "0.0.0.0", "--port", "8000"]

DocsManager/pyproject.toml

@@ -3,10 +3,12 @@ name = "goland-ia"
 version = "0.1.0"
 description = "Add your description here"
 readme = "README.md"
-requires-python = ">=3.14"
+requires-python = ">=3.13"
 dependencies = [
     "fastapi>=0.124.2",
-    "ipython>=9.8.0",
+    "sqlalchemy>=2.0.35",
+    "asyncpg>=0.29.0",
+    "psycopg2-binary>=2.9.9",
     "langgraph>=1.0.4",
     "typing-extensions>=4.15.0",
     "uvicorn>=0.38.0",
@@ -23,7 +25,7 @@ dev = [
 
 [tool.ruff]
 # Enable pyproject.toml support
-target-version = "py314"
+target-version = "py313"
 line-length = 120
 
 # Enable auto-fix

RAGManager/Dockerfile

@@ -1,13 +1,22 @@
-FROM ghcr.io/astral-sh/uv:python3.12-bookworm-slim
+FROM python:3.12-slim
 
 WORKDIR /app
 
-COPY pyproject.toml uv.lock* ./
+RUN apt-get update && apt-get install -y \
+    curl \
+    && rm -rf /var/lib/apt/lists/*
 
-RUN uv sync --frozen --no-cache || uv sync --no-cache
+RUN curl -LsSf https://astral.sh/uv/install.sh | sh && \
+    mv /root/.local/bin/uv /usr/local/bin/uv && \
+    mv /root/.local/bin/uvx /usr/local/bin/uvx
 
 COPY . .
 
+RUN uv sync --no-dev --no-cache
+
 EXPOSE 8000
 
-CMD ["uv", "run", "uvicorn", "main:app", "--host", "0.0.0.0", "--port", "8000"]
+HEALTHCHECK --interval=30s --timeout=10s --start-period=40s --retries=3 \
+    CMD curl -f http://localhost:8000/health || exit 1
+
+CMD ["uv", "run", "--no-sync", "uvicorn", "app:main", "--host", "0.0.0.0", "--port", "8000"]

RAGManager/pyproject.toml

@@ -1,11 +1,11 @@
 [project]
-name = "goland-ia"
+name = "rag-manager"
 version = "0.1.0"
-description = "Add your description here"
+description = "RAG Manager for document processing"
 readme = "README.md"
-requires-python = ">=3.14"
+requires-python = ">=3.12,<3.14"
 dependencies = [
-    "fastapi>=0.124.2",
+   "fastapi>=0.124.2",
     "ipython>=9.8.0",
     "langgraph>=1.0.4",
     "langchain-core>=0.3.0",
@@ -15,8 +15,6 @@ dependencies = [
     "psycopg2-binary>=2.9.0",
     "pgvector>=0.3.0",
     "pydantic-settings>=2.0.0",
-    "typing-extensions>=4.15.0",
-    "uvicorn>=0.38.0",
     "guardrails-ai>=0.5.10",
 ]
 
@@ -26,14 +24,9 @@ dev = [
 ]
 
 [tool.ruff]
-# Enable pyproject.toml support
-target-version = "py314"
+target-version = "py312"
 line-length = 120
-
-# Enable auto-fix
 fix = true
-
-# Exclude directories
 exclude = [
     ".git",
     ".venv",
@@ -45,7 +38,6 @@ exclude = [
 ]
 
 [tool.ruff.lint]
-# Enable a comprehensive set of rules
 select = [
     "E",   # pycodestyle errors
     "W",   # pycodestyle warnings
@@ -57,27 +49,15 @@ select = [
     "C4",  # flake8-comprehensions
     "SIM", # flake8-simplify
 ]
-
 ignore = [
-    "E501",  # Line too long (handled by formatter)
+    "E501",  # Line too long
 ]
-
-# Allow autofix for all enabled rules
 fixable = ["ALL"]
 unfixable = []
-
-# Allow unused variables when underscore-prefixed
 dummy-variable-rgx = "^(_+|(_+[a-zA-Z0-9_]*[a-zA-Z0-9]+?))$"
 
 [tool.ruff.format]
-# Use double quotes for strings (like Black)
 quote-style = "double"
-
-# Indent with spaces
 indent-style = "space"
-
-# Respect magic trailing commas
 skip-magic-trailing-comma = false
-
-# Automatically detect line ending
 line-ending = "auto"