mirror of
https://github.com/meta-llama/llama-stack.git
synced 2025-07-23 21:04:29 +00:00
7cf1e24c4e
# What does this PR do?
This commit introduces a new logging system that allows loggers to be
assigned
a category while retaining the logger name based on the file name. The
log
format includes both the logger name and the category, producing output
like:
```
INFO 2025-03-03 21:44:11,323 llama_stack.distribution.stack:103 [core]: Tool_groups: builtin::websearch served by
tavily-search
```
Key features include:
- Category-based logging: Loggers can be assigned a category (e.g.,
"core", "server") when programming. The logger can be loaded like
this: `logger = get_logger(name=__name__, category="server")`
- Environment variable control: Log levels can be configured
per-category using the
`LLAMA_STACK_LOGGING` environment variable. For example:
`LLAMA_STACK_LOGGING="server=DEBUG;core=debug"` enables DEBUG level for
the "server"
and "core" categories.
- `LLAMA_STACK_LOGGING="all=debug"` sets DEBUG level globally for all
categories and
third-party libraries.
This provides fine-grained control over logging levels while maintaining
a clean and
informative log format.
The formatter uses the rich library which provides nice colors better
stack traces like so:
```
ERROR 2025-03-03 21:49:37,124 asyncio:1758 [uncategorized]: unhandled exception during asyncio.run() shutdown
task: <Task finished name='Task-16' coro=<handle_signal.<locals>.shutdown() done, defined at
/Users/leseb/Documents/AI/llama-stack/llama_stack/distribution/server/server.py:146>
exception=UnboundLocalError("local variable 'loop' referenced before assignment")>
╭────────────────────────────────────── Traceback (most recent call last) ───────────────────────────────────────╮
│ /Users/leseb/Documents/AI/llama-stack/llama_stack/distribution/server/server.py:178 in shutdown │
│ │
│ 175 │ │ except asyncio.CancelledError: │
│ 176 │ │ │ pass │
│ 177 │ │ finally: │
│ ❱ 178 │ │ │ loop.stop() │
│ 179 │ │
│ 180 │ loop = asyncio.get_running_loop() │
│ 181 │ loop.create_task(shutdown()) │
╰────────────────────────────────────────────────────────────────────────────────────────────────────────────────╯
UnboundLocalError: local variable 'loop' referenced before assignment
```
Co-authored-by: Ashwin Bharambe <@ashwinb>
Signed-off-by: Sébastien Han <seb@redhat.com>
[//]: # (If resolving an issue, uncomment and update the line below)
[//]: # (Closes #[issue-number])
## Test Plan
```
python -m llama_stack.distribution.server.server --yaml-config ./llama_stack/templates/ollama/run.yaml
INFO 2025-03-03 21:55:35,918 __main__:365 [server]: Using config file: llama_stack/templates/ollama/run.yaml
INFO 2025-03-03 21:55:35,925 __main__:378 [server]: Run configuration:
INFO 2025-03-03 21:55:35,928 __main__:380 [server]: apis:
- agents
```
[//]: # (## Documentation)
---------
Signed-off-by: Sébastien Han <seb@redhat.com>
Co-authored-by: Ashwin Bharambe <ashwin.bharambe@gmail.com>
166 lines
4.1 KiB
TOML
166 lines
4.1 KiB
TOML
[build-system]
|
|
requires = ["setuptools>=61.0"]
|
|
build-backend = "setuptools.build_meta"
|
|
|
|
[project]
|
|
name = "llama_stack"
|
|
version = "0.1.5"
|
|
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-stack-client>=0.1.4",
|
|
"prompt-toolkit",
|
|
"python-dotenv",
|
|
"pydantic>=2",
|
|
"requests",
|
|
"rich",
|
|
"setuptools",
|
|
"termcolor",
|
|
]
|
|
|
|
[project.optional-dependencies]
|
|
dev = [
|
|
"pytest",
|
|
"pytest-asyncio",
|
|
"pytest-html",
|
|
"nbval", # For notebook testing
|
|
"black",
|
|
"ruff",
|
|
"types-requests",
|
|
"types-setuptools",
|
|
"pre-commit",
|
|
"uvicorn",
|
|
"fastapi",
|
|
"ruamel.yaml", # needed for openapi generator
|
|
]
|
|
test = [
|
|
"openai",
|
|
"aiosqlite",
|
|
"sqlite-vec",
|
|
"ollama",
|
|
"torch>=2.6.0",
|
|
"fairscale>=0.4.13",
|
|
"torchvision>=0.21.0",
|
|
"lm-format-enforcer>=0.10.9",
|
|
"groq",
|
|
"opentelemetry-sdk",
|
|
"opentelemetry-exporter-otlp-proto-http",
|
|
"tiktoken",
|
|
"chardet",
|
|
"pypdf",
|
|
]
|
|
docs = [
|
|
"sphinx-autobuild",
|
|
"myst-parser",
|
|
"sphinx-rtd-theme",
|
|
"sphinx-copybutton",
|
|
"sphinx-tabs",
|
|
"sphinx-design",
|
|
"sphinxcontrib.redoc",
|
|
"sphinxcontrib.video",
|
|
"sphinxcontrib.mermaid",
|
|
"tomli",
|
|
]
|
|
codegen = ["rich", "pydantic", "jinja2>=3.1.6"]
|
|
|
|
[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.uv.sources]
|
|
torch = [{ index = "pytorch-cpu" }]
|
|
torchvision = [{ index = "pytorch-cpu" }]
|
|
|
|
[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 = [
|
|
# The following ignores are desired by the project maintainers.
|
|
"E402", # Module level import not at top of file
|
|
"E501", # Line too long
|
|
"F405", # Maybe undefined or defined from star import
|
|
"C408", # Ignored because we like the dict keyword argument syntax
|
|
"N812", # Ignored because import torch.nn.functional as F is PyTorch convention
|
|
|
|
# These are the additional ones we started ignoring after moving to ruff. We should look into each one of them later.
|
|
"C901", # Complexity of the function is too high
|
|
]
|
|
|
|
[tool.mypy]
|
|
mypy_path = ["llama_stack"]
|
|
packages = ["llama_stack"]
|
|
disable_error_code = []
|
|
warn_return_any = true
|
|
# # honor excludes by not following there through imports
|
|
follow_imports = "silent"
|
|
exclude = [
|
|
# As we fix more and more of these, we should remove them from the list
|
|
"llama_stack/providers",
|
|
"llama_stack/distribution",
|
|
"llama_stack/apis",
|
|
"llama_stack/cli",
|
|
"llama_stack/models",
|
|
"llama_stack/strong_typing",
|
|
"llama_stack/templates",
|
|
]
|
|
|
|
[[tool.mypy.overrides]]
|
|
# packages that lack typing annotations, do not have stubs, or are unavailable.
|
|
module = ["yaml", "fire"]
|
|
ignore_missing_imports = true
|
|
|
|
[[tool.mypy.overrides]]
|
|
module = ["llama_stack.distribution.resolver", "llama_stack.log"]
|
|
follow_imports = "normal" # This will force type checking on this module
|