forked from phoenix-oss/llama-stack-mirror
314ee09ae3
llama-models should have extremely minimal cruft. Its sole purpose should be didactic -- show the simplest implementation of the llama models and document the prompt formats, etc. This PR is the complement to https://github.com/meta-llama/llama-models/pull/279 ## Test Plan Ensure all `llama` CLI `model` sub-commands work: ```bash llama model list llama model download --model-id ... llama model prompt-format -m ... ``` Ran tests: ```bash cd tests/client-sdk LLAMA_STACK_CONFIG=fireworks pytest -s -v inference/ LLAMA_STACK_CONFIG=fireworks pytest -s -v vector_io/ LLAMA_STACK_CONFIG=fireworks pytest -s -v agents/ ``` Create a fresh venv `uv venv && source .venv/bin/activate` and run `llama stack build --template fireworks --image-type venv` followed by `llama stack run together --image-type venv` <-- the server runs Also checked that the OpenAPI generator can run and there is no change in the generated files as a result. ```bash cd docs/openapi_generator sh run_openapi_generator.sh ```
142 lines
3.2 KiB
TOML
142 lines
3.2 KiB
TOML
[build-system]
|
|
requires = ["setuptools>=61.0"]
|
|
build-backend = "setuptools.build_meta"
|
|
|
|
[project]
|
|
name = "llama_stack"
|
|
version = "0.1.2"
|
|
authors = [{ name = "Meta Llama", email = "llama-oss@meta.com" }]
|
|
description = "Llama Stack"
|
|
readme = "README.md"
|
|
requires-python = ">=3.10"
|
|
license = { "text" = "MIT" }
|
|
classifiers = [
|
|
"License :: OSI Approved :: MIT License",
|
|
"Programming Language :: Python :: 3",
|
|
"Operating System :: OS Independent",
|
|
"Intended Audience :: Developers",
|
|
"Intended Audience :: Information Technology",
|
|
"Intended Audience :: Science/Research",
|
|
"Topic :: Scientific/Engineering :: Artificial Intelligence",
|
|
"Topic :: Scientific/Engineering :: Information Analysis",
|
|
]
|
|
dependencies = [
|
|
"blobfile",
|
|
"fire",
|
|
"httpx",
|
|
"huggingface-hub",
|
|
"jsonschema",
|
|
"llama-models>=0.1.2",
|
|
"llama-stack-client>=0.1.2",
|
|
"prompt-toolkit",
|
|
"python-dotenv",
|
|
"pydantic>=2",
|
|
"requests",
|
|
"rich",
|
|
"setuptools",
|
|
"termcolor",
|
|
]
|
|
|
|
[project.optional-dependencies]
|
|
dev = [
|
|
"pytest",
|
|
"pytest-asyncio",
|
|
"nbval", # For notebook testing
|
|
"black",
|
|
"ruff",
|
|
"types-requests",
|
|
"types-setuptools",
|
|
"pre-commit",
|
|
"uvicorn",
|
|
"fastapi",
|
|
]
|
|
docs = [
|
|
"sphinx-autobuild",
|
|
"myst-parser",
|
|
"sphinx-rtd-theme",
|
|
"sphinx-copybutton",
|
|
"sphinx-tabs",
|
|
"sphinx-design",
|
|
"sphinxcontrib.redoc",
|
|
"sphinxcontrib.video",
|
|
"sphinxcontrib.mermaid",
|
|
]
|
|
|
|
[project.urls]
|
|
Homepage = "https://github.com/meta-llama/llama-stack"
|
|
|
|
[project.scripts]
|
|
llama = "llama_stack.cli.llama:main"
|
|
install-wheel-from-presigned = "llama_stack.cli.scripts.run:install_wheel_from_presigned"
|
|
|
|
[tool.setuptools]
|
|
packages = { find = {} }
|
|
license-files = []
|
|
|
|
[[tool.uv.index]]
|
|
name = "pytorch-cpu"
|
|
url = "https://download.pytorch.org/whl/cpu"
|
|
explicit = true
|
|
|
|
[tool.ruff]
|
|
line-length = 120
|
|
exclude = [
|
|
"./.git",
|
|
"./docs/*",
|
|
"./build",
|
|
"./scripts",
|
|
"./venv",
|
|
"*.pyi",
|
|
".pre-commit-config.yaml",
|
|
"*.md",
|
|
".flake8",
|
|
]
|
|
|
|
[tool.ruff.lint]
|
|
select = [
|
|
"B", # flake8-bugbear
|
|
"B9", # flake8-bugbear subset
|
|
"C", # comprehensions
|
|
"E", # pycodestyle
|
|
"F", # Pyflakes
|
|
"N", # Naming
|
|
"W", # Warnings
|
|
"I", # isort
|
|
]
|
|
ignore = [
|
|
"E203",
|
|
"E305",
|
|
"E402",
|
|
"E501", # line too long
|
|
"E721",
|
|
"E741",
|
|
"F405",
|
|
"F821",
|
|
"F841",
|
|
"C408", # ignored because we like the dict keyword argument syntax
|
|
"E302",
|
|
"W291",
|
|
"E303",
|
|
"N812", # ignored because import torch.nn.functional as F is PyTorch convention
|
|
"N817", # ignored because importing using acronyms is convention (DistributedDataParallel as DDP)
|
|
"E731", # allow usage of assigning lambda expressions
|
|
# These are the additional ones we started ignoring after moving to ruff. We should look into each one of them later.
|
|
"C901",
|
|
"C405",
|
|
"C414",
|
|
"N803",
|
|
"N999",
|
|
"C403",
|
|
"C416",
|
|
"B028",
|
|
"C419",
|
|
"C401",
|
|
"B023",
|
|
# shebang has extra meaning in fbcode lints, so I think it's not worth trying
|
|
# to line this up with executable bit
|
|
"EXE001",
|
|
"N802", # random naming hints don't need
|
|
# these ignores are from flake8-bugbear; please fix!
|
|
"B007",
|
|
"B008",
|
|
]
|