mirror of
https://github.com/meta-llama/llama-stack.git
synced 2025-10-20 23:58:52 +00:00
Some checks failed
SqlStore Integration Tests / test-postgres (3.12) (push) Failing after 0s
SqlStore Integration Tests / test-postgres (3.13) (push) Failing after 0s
Integration Tests (Replay) / Integration Tests (, , , client=, ) (push) Failing after 3s
Test Llama Stack Build / generate-matrix (push) Successful in 22s
Test llama stack list-deps / show-single-provider (push) Failing after 53s
Test Llama Stack Build / build-single-provider (push) Failing after 3s
Test External Providers Installed via Module / test-external-providers-from-module (venv) (push) Has been skipped
Python Package Build Test / build (3.12) (push) Failing after 18s
Python Package Build Test / build (3.13) (push) Failing after 24s
Test Llama Stack Build / build-ubi9-container-distribution (push) Failing after 26s
Test Llama Stack Build / build-custom-container-distribution (push) Failing after 27s
Unit Tests / unit-tests (3.12) (push) Failing after 26s
Vector IO Integration Tests / test-matrix (push) Failing after 44s
API Conformance Tests / check-schema-compatibility (push) Successful in 52s
Test llama stack list-deps / generate-matrix (push) Successful in 52s
Test Llama Stack Build / build (push) Failing after 29s
Test External API and Providers / test-external (venv) (push) Failing after 53s
Integration Auth Tests / test-matrix (oauth2_token) (push) Failing after 1m2s
Unit Tests / unit-tests (3.13) (push) Failing after 1m30s
Test llama stack list-deps / list-deps-from-config (push) Failing after 1m59s
Test llama stack list-deps / list-deps (push) Failing after 1m10s
UI Tests / ui-tests (22) (push) Successful in 2m26s
Pre-commit / pre-commit (push) Successful in 3m8s
# What does this PR do? This PR does a few things outlined in #2878 namely: 1. adds `llama stack list-deps` a command which simply takes the build logic and instead of executing one of the `build_...` scripts, it displays all of the providers' dependencies using the `module` and `uv`. 2. deprecated `llama stack build` in favor of `llama stack list-deps` 3. updates all tests to use `list-deps` alongside `build`. PR 2/2 will migrate `llama stack run`'s default behavior to be `llama stack build --run` and use the new `list-deps` command under the hood before running the server. examples of `llama stack list-deps starter` ``` llama stack list-deps starter --format json { "name": "starter", "description": "Quick start template for running Llama Stack with several popular providers. This distribution is intended for CPU-only environments.", "apis": [ { "api": "inference", "provider": "remote::cerebras" }, { "api": "inference", "provider": "remote::ollama" }, { "api": "inference", "provider": "remote::vllm" }, { "api": "inference", "provider": "remote::tgi" }, { "api": "inference", "provider": "remote::fireworks" }, { "api": "inference", "provider": "remote::together" }, { "api": "inference", "provider": "remote::bedrock" }, { "api": "inference", "provider": "remote::nvidia" }, { "api": "inference", "provider": "remote::openai" }, { "api": "inference", "provider": "remote::anthropic" }, { "api": "inference", "provider": "remote::gemini" }, { "api": "inference", "provider": "remote::vertexai" }, { "api": "inference", "provider": "remote::groq" }, { "api": "inference", "provider": "remote::sambanova" }, { "api": "inference", "provider": "remote::azure" }, { "api": "inference", "provider": "inline::sentence-transformers" }, { "api": "vector_io", "provider": "inline::faiss" }, { "api": "vector_io", "provider": "inline::sqlite-vec" }, { "api": "vector_io", "provider": "inline::milvus" }, { "api": "vector_io", "provider": "remote::chromadb" }, { "api": "vector_io", "provider": "remote::pgvector" }, { "api": "files", "provider": "inline::localfs" }, { "api": "safety", "provider": "inline::llama-guard" }, { "api": "safety", "provider": "inline::code-scanner" }, { "api": "agents", "provider": "inline::meta-reference" }, { "api": "telemetry", "provider": "inline::meta-reference" }, { "api": "post_training", "provider": "inline::torchtune-cpu" }, { "api": "eval", "provider": "inline::meta-reference" }, { "api": "datasetio", "provider": "remote::huggingface" }, { "api": "datasetio", "provider": "inline::localfs" }, { "api": "scoring", "provider": "inline::basic" }, { "api": "scoring", "provider": "inline::llm-as-judge" }, { "api": "scoring", "provider": "inline::braintrust" }, { "api": "tool_runtime", "provider": "remote::brave-search" }, { "api": "tool_runtime", "provider": "remote::tavily-search" }, { "api": "tool_runtime", "provider": "inline::rag-runtime" }, { "api": "tool_runtime", "provider": "remote::model-context-protocol" }, { "api": "batches", "provider": "inline::reference" } ], "pip_dependencies": [ "pandas", "opentelemetry-exporter-otlp-proto-http", "matplotlib", "opentelemetry-sdk", "sentence-transformers", "datasets", "pymilvus[milvus-lite]>=2.4.10", "codeshield", "scipy", "torchvision", "tree_sitter", "h11>=0.16.0", "aiohttp", "pymongo", "tqdm", "pythainlp", "pillow", "torch", "emoji", "grpcio>=1.67.1,<1.71.0", "fireworks-ai", "langdetect", "psycopg2-binary", "asyncpg", "redis", "together", "torchao>=0.12.0", "openai", "sentencepiece", "aiosqlite", "google-cloud-aiplatform", "faiss-cpu", "numpy", "sqlite-vec", "nltk", "scikit-learn", "mcp>=1.8.1", "transformers", "boto3", "huggingface_hub", "ollama", "autoevals", "sqlalchemy[asyncio]", "torchtune>=0.5.0", "chromadb-client", "pypdf", "requests", "anthropic", "chardet", "aiosqlite", "fastapi", "fire", "httpx", "uvicorn", "opentelemetry-sdk", "opentelemetry-exporter-otlp-proto-http" ] } ``` <img width="1500" height="420" alt="Screenshot 2025-10-16 at 5 53 03 PM" src="https://github.com/user-attachments/assets/765929fb-93e2-44d7-9c3d-8918b70fc721" /> --------- Signed-off-by: Charlie Doern <cdoern@redhat.com>
106 lines
4.2 KiB
Python
106 lines
4.2 KiB
Python
# Copyright (c) Meta Platforms, Inc. and affiliates.
|
|
# All rights reserved.
|
|
#
|
|
# This source code is licensed under the terms described in the LICENSE file in
|
|
# the root directory of this source tree.
|
|
import argparse
|
|
import textwrap
|
|
|
|
from llama_stack.cli.stack.utils import ImageType
|
|
from llama_stack.cli.subcommand import Subcommand
|
|
from llama_stack.log import get_logger
|
|
|
|
logger = get_logger(__name__, category="cli")
|
|
|
|
|
|
class StackBuild(Subcommand):
|
|
def __init__(self, subparsers: argparse._SubParsersAction):
|
|
super().__init__()
|
|
self.parser = subparsers.add_parser(
|
|
"build",
|
|
prog="llama stack build",
|
|
description="[DEPRECATED] Build a Llama stack container. This command is deprecated and will be removed in a future release. Use `llama stack list-deps <distro>' instead.",
|
|
formatter_class=argparse.ArgumentDefaultsHelpFormatter,
|
|
)
|
|
self._add_arguments()
|
|
self.parser.set_defaults(func=self._run_stack_build_command)
|
|
|
|
def _add_arguments(self):
|
|
self.parser.add_argument(
|
|
"--config",
|
|
type=str,
|
|
default=None,
|
|
help="Path to a config file to use for the build. You can find example configs in llama_stack.cores/**/build.yaml. If this argument is not provided, you will be prompted to enter information interactively",
|
|
)
|
|
|
|
self.parser.add_argument(
|
|
"--template",
|
|
type=str,
|
|
default=None,
|
|
help="""(deprecated) Name of the example template config to use for build. You may use `llama stack build --list-distros` to check out the available distributions""",
|
|
)
|
|
self.parser.add_argument(
|
|
"--distro",
|
|
"--distribution",
|
|
dest="distribution",
|
|
type=str,
|
|
default=None,
|
|
help="""Name of the distribution to use for build. You may use `llama stack build --list-distros` to check out the available distributions""",
|
|
)
|
|
|
|
self.parser.add_argument(
|
|
"--list-distros",
|
|
"--list-distributions",
|
|
action="store_true",
|
|
dest="list_distros",
|
|
default=False,
|
|
help="Show the available distributions for building a Llama Stack distribution",
|
|
)
|
|
|
|
self.parser.add_argument(
|
|
"--image-type",
|
|
type=str,
|
|
help="Image Type to use for the build. If not specified, will use the image type from the template config.",
|
|
choices=[e.value for e in ImageType],
|
|
default=None, # no default so we can detect if a user specified --image-type and override image_type in the config
|
|
)
|
|
|
|
self.parser.add_argument(
|
|
"--image-name",
|
|
type=str,
|
|
help=textwrap.dedent(
|
|
f"""[for image-type={"|".join(e.value for e in ImageType)}] Name of the virtual environment to use for
|
|
the build. If not specified, currently active environment will be used if found.
|
|
"""
|
|
),
|
|
default=None,
|
|
)
|
|
self.parser.add_argument(
|
|
"--print-deps-only",
|
|
default=False,
|
|
action="store_true",
|
|
help="Print the dependencies for the stack only, without building the stack",
|
|
)
|
|
|
|
self.parser.add_argument(
|
|
"--run",
|
|
action="store_true",
|
|
default=False,
|
|
help="Run the stack after building using the same image type, name, and other applicable arguments",
|
|
)
|
|
self.parser.add_argument(
|
|
"--providers",
|
|
type=str,
|
|
default=None,
|
|
help="Build a config for a list of providers and only those providers. This list is formatted like: api1=provider1,api2=provider2. Where there can be multiple providers per API.",
|
|
)
|
|
|
|
def _run_stack_build_command(self, args: argparse.Namespace) -> None:
|
|
logger.warning(
|
|
"The 'llama stack build' command is deprecated and will be removed in a future release. Please use 'llama stack list-deps'"
|
|
)
|
|
# always keep implementation completely silo-ed away from CLI so CLI
|
|
# can be fast to load and reduces dependencies
|
|
from ._build import run_stack_build_command
|
|
|
|
return run_stack_build_command(args)
|