feat: add pyproject.toml and CI for ray-serve-apps package

- Restructure ray-serve as proper Python package (ray_serve/)
- Add pyproject.toml with hatch build system
- Add CI workflow to publish to Gitea PyPI
- Add py.typed for PEP 561 compliance
- Aligns with ADR-0019 handler deployment strategy

.gitea/workflows/publish-ray-serve.yaml

@@ -0,0 +1,87 @@
+name: Build and Publish ray-serve-apps
+
+on:
+  push:
+    branches:
+      - main
+    paths:
+      - 'ray-serve/**'
+      - '.gitea/workflows/publish-ray-serve.yaml'
+  pull_request:
+    branches:
+      - main
+    paths:
+      - 'ray-serve/**'
+  workflow_dispatch:
+
+env:
+  NTFY_URL: http://ntfy.observability.svc.cluster.local:80
+
+jobs:
+  lint:
+    runs-on: ubuntu-latest
+    steps:
+      - name: Checkout
+        uses: actions/checkout@v4
+
+      - name: Set up Python
+        uses: actions/setup-python@v5
+        with:
+          python-version: '3.11'
+
+      - name: Install ruff
+        run: pip install ruff
+
+      - name: Lint with ruff
+        run: |
+          cd ray-serve
+          ruff check .
+          ruff format --check .
+
+  publish:
+    needs: lint
+    runs-on: ubuntu-latest
+    if: github.event_name == 'push' && github.ref == 'refs/heads/main'
+    steps:
+      - name: Checkout
+        uses: actions/checkout@v4
+
+      - name: Set up Python
+        uses: actions/setup-python@v5
+        with:
+          python-version: '3.11'
+
+      - name: Install build tools
+        run: pip install build twine
+
+      - name: Build package
+        run: |
+          cd ray-serve
+          python -m build
+
+      - name: Publish to Gitea PyPI
+        env:
+          TWINE_USERNAME: ${{ secrets.REGISTRY_USER }}
+          TWINE_PASSWORD: ${{ secrets.REGISTRY_TOKEN }}
+        run: |
+          cd ray-serve
+          twine upload --repository-url https://git.daviestechlabs.io/api/packages/daviestechlabs/pypi \
+            dist/*
+
+      - name: Notify on success
+        if: success()
+        run: |
+          curl -s -X POST "${{ env.NTFY_URL }}/builds" \
+            -H "Title: ray-serve-apps published" \
+            -H "Priority: default" \
+            -H "Tags: package,white_check_mark" \
+            -d "Published ray-serve-apps to Gitea PyPI"
+
+      - name: Notify on failure
+        if: failure()
+        run: |
+          curl -s -X POST "${{ env.NTFY_URL }}/builds" \
+            -H "Title: ray-serve-apps publish failed" \
+            -H "Priority: high" \
+            -H "Tags: package,x" \
+            -d "Failed to publish ray-serve-apps to Gitea PyPI"

ray-serve/__init__.py

@@ -1 +0,0 @@
-# Ray Serve deployments for GPU-shared AI inference

ray-serve/pyproject.toml

@@ -0,0 +1,71 @@
+[project]
+name = "ray-serve-apps"
+version = "1.0.0"
+description = "Ray Serve deployments for GPU-shared AI inference"
+requires-python = ">=3.11"
+license = { text = "MIT" }
+authors = [{ name = "Davies Tech Labs" }]
+
+dependencies = [
+    # Ray Serve
+    "ray[serve]>=2.53.0",
+    
+    # HTTP client
+    "httpx>=0.27.0",
+    
+    # Numerical computing
+    "numpy>=1.26.0",
+]
+
+[project.optional-dependencies]
+# LLM inference (for vLLM deployments)
+llm = [
+    "vllm>=0.6.0",
+]
+
+# Embeddings and reranking
+embeddings = [
+    "sentence-transformers>=2.2.0",
+]
+
+# Speech-to-text
+stt = [
+    "faster-whisper>=1.0.0",
+]
+
+# Text-to-speech  
+tts = [
+    "TTS>=0.22.0",
+]
+
+# Development
+dev = [
+    "pytest>=8.0.0",
+    "pytest-asyncio>=0.23.0",
+    "ruff>=0.4.0",
+]
+
+[build-system]
+requires = ["hatchling"]
+build-backend = "hatchling.build"
+
+[tool.hatch.build.targets.wheel]
+# Map the ray-serve directory to ray_serve package name
+packages = ["ray_serve"]
+
+[tool.hatch.build.targets.sdist]
+include = [
+    "ray_serve/**/*.py",
+    "ray_serve/py.typed",
+]
+
+[tool.ruff]
+line-length = 100
+target-version = "py311"
+
+[tool.ruff.lint]
+select = ["E", "F", "I", "W", "UP", "B", "C4", "SIM"]
+ignore = ["E501"]
+
+[tool.ruff.lint.isort]
+known-first-party = ["ray_serve"]

ray-serve/ray_serve/__init__.py

@@ -0,0 +1,14 @@
+# Ray Serve deployments for GPU-shared AI inference
+from ray_serve.serve_embeddings import app as embeddings_app
+from ray_serve.serve_llm import app as llm_app
+from ray_serve.serve_reranker import app as reranker_app
+from ray_serve.serve_tts import app as tts_app
+from ray_serve.serve_whisper import app as whisper_app
+
+__all__ = [
+    "embeddings_app",
+    "llm_app",
+    "reranker_app",
+    "tts_app",
+    "whisper_app",
+]