feat: add pyproject.toml and CI for ray-serve-apps package
Some checks failed
Build and Push Images / build-nvidia (push) Failing after 7m25s
Build and Push Images / build-rdna2 (push) Failing after 7m29s
Build and Push Images / build-strixhalo (push) Failing after 6m45s
Build and Push Images / build-intel (push) Failing after 6m22s
Build and Push Images / Release (push) Has been skipped
Build and Push Images / Notify (push) Successful in 1s
Build and Publish ray-serve-apps / lint (push) Failing after 3m9s
Build and Publish ray-serve-apps / publish (push) Has been skipped

- 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
This commit is contained in:
2026-02-02 09:22:03 -05:00
parent 876188a150
commit 7efdcb059e
10 changed files with 172 additions and 1 deletions

View File

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

71
ray-serve/pyproject.toml Normal file
View File

@@ -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"]

View File

@@ -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",
]

View File