feat: initial ray-serve-apps PyPI package

Implements ADR-0024: Ray Repository Structure

- Ray Serve deployments for GPU-shared AI inference
- Published as PyPI package for dynamic code loading
- Deployments: LLM, embeddings, reranker, whisper, TTS
- CI/CD workflow publishes to Gitea PyPI on push to main

Extracted from kuberay-images repo per ADR-0024

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"]