Add a Streamlit UI and Docker Compose for text analysis and OCR

.dockerignore

@@ -0,0 +1,20 @@
+.git
+.github
+.venv
+venv
+env
+ocrenv
+__pycache__
+**/__pycache__
+.pytest_cache
+.mypy_cache
+.coverage
+htmlcov
+.env
+*.pyc
+*.pyo
+.idea
+.vscode
+tests
+README.md
+PRODUCTIONIZING.md

.env.example

@@ -0,0 +1,15 @@
+# Copy this file to .env and fill in real values. .env is gitignored.
+# Leave the values empty to boot the UI and API anyway: text analysis
+# returns a clear "credentials are not configured" message, and OCR still runs.
+
+# Endpoint of an Azure AI Language resource, without a path.
+# Example: https://my-language.cognitiveservices.azure.com
+AZURE_LANGUAGE_ENDPOINT=
+
+# Key for that same resource (Keys and Endpoint blade in the Azure portal).
+AZURE_LANGUAGE_KEY=
+
+# Optional. The Streamlit service uses this to find the API.
+# Docker Compose sets it to http://api:8000 for the ui container.
+# A local `streamlit run` defaults to http://localhost:8000 when this is unset.
+# API_BASE_URL=http://localhost:8000

.github/workflows/main_text-analytics-fastapi.yml

@@ -1,6 +1,7 @@
-# Docs for the Azure Web Apps Deploy action: https://github.com/Azure/webapps-deploy
-# More GitHub Actions for Azure: https://github.com/Azure/actions
-# More info on Python, GitHub Actions, and Azure App Service: https://aka.ms/python-webapps-actions
+# Deploy the API (not the Streamlit UI) to the existing Azure App Service.
+# Text analysis stays dark until the App Service has AZURE_LANGUAGE_ENDPOINT
+# and AZURE_LANGUAGE_KEY configured. See PRODUCTIONIZING.md for the Container
+# Apps, Key Vault, and identity-based setup that should replace this file.
 
 name: Build and deploy Python app to Azure Web App - text-analytics-fastapi
 
@@ -15,49 +16,50 @@ jobs:
     runs-on: ubuntu-latest
 
     steps:
-      - uses: actions/checkout@v2
+      - uses: actions/checkout@v4
 
       - name: Set up Python version
-        uses: actions/setup-python@v1
+        uses: actions/setup-python@v5
         with:
-          python-version: '3.7'
+          python-version: "3.12"
+
+      - name: Install Tesseract
+        run: sudo apt-get update && sudo apt-get install -y tesseract-ocr
 
-      - name: Create and start virtual environment
-        run: |
-          python -m venv venv
-          source venv/bin/activate
-
       - name: Install dependencies
-        run: pip install -r requirements.txt
-
-      # Optional: Add step to run tests here (PyTest, Django test suites, etc.)
-
+        run: pip install -r requirements-dev.txt
+
+      - name: Run tests
+        run: pytest
+
       - name: Upload artifact for deployment jobs
-        uses: actions/upload-artifact@v2
+        uses: actions/upload-artifact@v4
         with:
           name: python-app
           path: |
-            . 
+            .
+            !.git/
+            !.venv/
             !venv/
 
   deploy:
     runs-on: ubuntu-latest
     needs: build
     environment:
-      name: 'Production'
+      name: "Production"
       url: ${{ steps.deploy-to-webapp.outputs.webapp-url }}
 
     steps:
       - name: Download artifact from build job
-        uses: actions/download-artifact@v2
+        uses: actions/download-artifact@v4
         with:
           name: python-app
           path: .
-          
-      - name: 'Deploy to Azure Web App'
-        uses: azure/webapps-deploy@v2
+
+      - name: Deploy to Azure Web App
+        uses: azure/webapps-deploy@v3
         id: deploy-to-webapp
         with:
-          app-name: 'text-analytics-fastapi'
-          slot-name: 'Production'
+          app-name: "text-analytics-fastapi"
+          slot-name: "Production"
           publish-profile: ${{ secrets.AZUREAPPSERVICE_PUBLISHPROFILE_F64BD7EE84E649C1930A5AA58F25A0D0 }}

.github/workflows/test.yml

@@ -0,0 +1,56 @@
+name: Tests
+
+on:
+  push:
+  pull_request:
+
+jobs:
+  pytest:
+    runs-on: ubuntu-latest
+    steps:
+      - uses: actions/checkout@v4
+
+      - uses: actions/setup-python@v5
+        with:
+          python-version: "3.12"
+
+      - name: Install Tesseract
+        run: sudo apt-get update && sudo apt-get install -y tesseract-ocr
+
+      - name: Install Python dependencies
+        run: pip install -r requirements-dev.txt
+
+      - name: Run tests
+        run: pytest
+
+  docker:
+    runs-on: ubuntu-latest
+    steps:
+      - uses: actions/checkout@v4
+
+      - name: Build images
+        run: docker compose build
+
+      - name: Boot the stack and smoke-test it
+        run: |
+          docker compose up -d
+          for _ in $(seq 1 30); do
+            curl -fsS http://localhost:8000/health && break
+            sleep 2
+          done
+          curl -fsS http://localhost:8000/health
+          code=$(curl -s -o /tmp/analyze.json -w "%{http_code}" \
+            -X POST http://localhost:8000/api/v1/analyze \
+            -H 'content-type: application/json' \
+            -d '{"text_to_analyze":["hello"]}')
+          test "$code" = "503"
+          grep -q "not configured" /tmp/analyze.json
+          curl -fsS -F "images=@samples/ocr-sample.png" \
+            http://localhost:8000/api/v1/extract_text \
+            | grep -i -q "quick brown"
+          for _ in $(seq 1 30); do
+            curl -fsS http://localhost:8501/_stcore/health && break
+            sleep 2
+          done
+          curl -fsS http://localhost:8501/_stcore/health
+          docker compose down

.streamlit/config.toml

@@ -0,0 +1,22 @@
+# Light page, dark text. Loaded when Streamlit is started from the repo root
+# and when the frontend image uses /app as its working directory.
+
+[theme]
+base = "light"
+primaryColor = "#0f4c81"
+backgroundColor = "#f6f3ee"
+secondaryBackgroundColor = "#ffffff"
+textColor = "#1c1917"
+font = "sans serif"
+
+[server]
+headless = true
+address = "0.0.0.0"
+# Matches the API limit in app/ocr.py. Streamlit's default is 200 MB.
+maxUploadSize = 10
+
+[browser]
+gatherUsageStats = false
+
+[client]
+toolbarMode = "minimal"

Dockerfile

@@ -0,0 +1,32 @@
+# API image: FastAPI plus the Tesseract binary OCR needs.
+# Build from the repository root: docker build -t text-ocr-api .
+
+FROM python:3.12-slim-bookworm
+
+ENV PYTHONDONTWRITEBYTECODE=1 \
+    PYTHONUNBUFFERED=1 \
+    PIP_DISABLE_PIP_VERSION_CHECK=1
+
+RUN apt-get update \
+    && apt-get install -y --no-install-recommends tesseract-ocr \
+    && rm -rf /var/lib/apt/lists/*
+
+WORKDIR /app
+
+COPY requirements.txt .
+RUN pip install --no-cache-dir -r requirements.txt
+
+COPY app ./app
+COPY main.py .
+COPY text-analytics-sdk ./text-analytics-sdk
+
+RUN useradd --create-home --uid 10001 appuser \
+    && chown -R appuser:appuser /app
+USER appuser
+
+EXPOSE 8000
+
+HEALTHCHECK --interval=30s --timeout=5s --start-period=15s --retries=3 \
+    CMD python -c "import urllib.request; urllib.request.urlopen('http://127.0.0.1:8000/health')"
+
+CMD ["uvicorn", "app.main:app", "--host", "0.0.0.0", "--port", "8000"]

Dockerfile.frontend

@@ -0,0 +1,29 @@
+# Streamlit UI. It only needs the frontend package and a URL for the API.
+# Build from the repository root: docker build -f Dockerfile.frontend -t text-ocr-ui .
+
+FROM python:3.12-slim-bookworm
+
+ENV PYTHONDONTWRITEBYTECODE=1 \
+    PYTHONUNBUFFERED=1 \
+    PIP_DISABLE_PIP_VERSION_CHECK=1 \
+    STREAMLIT_BROWSER_GATHER_USAGE_STATS=false \
+    API_BASE_URL=http://api:8000
+
+WORKDIR /app
+
+COPY requirements-ui.txt .
+RUN pip install --no-cache-dir -r requirements-ui.txt
+
+COPY frontend ./frontend
+COPY .streamlit ./.streamlit
+
+RUN useradd --create-home --uid 10001 appuser \
+    && chown -R appuser:appuser /app
+USER appuser
+
+EXPOSE 8501
+
+HEALTHCHECK --interval=30s --timeout=5s --start-period=20s --retries=3 \
+    CMD python -c "import urllib.request; urllib.request.urlopen('http://127.0.0.1:8501/_stcore/health')"
+
+CMD ["streamlit", "run", "frontend/streamlit_app.py", "--server.address", "0.0.0.0", "--server.port", "8501", "--server.headless", "true"]