llama-stack-mirror/llama_stack/cli/stack/utils.py
Charlie Doern b11bcfde11
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
refactor(build): rework CLI commands and build process (1/2) (#2974)
# 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>
2025-10-17 19:52:14 -07:00

130 lines
4.7 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 json
import sys
from enum import Enum
from functools import lru_cache
from pathlib import Path
import yaml
from termcolor import cprint
from llama_stack.core.datatypes import (
BuildConfig,
Provider,
StackRunConfig,
)
from llama_stack.core.distribution import get_provider_registry
from llama_stack.core.resolver import InvalidProviderError
from llama_stack.core.utils.config_dirs import EXTERNAL_PROVIDERS_DIR
from llama_stack.core.utils.dynamic import instantiate_class_type
from llama_stack.core.utils.image_types import LlamaStackImageType
from llama_stack.providers.datatypes import Api
TEMPLATES_PATH = Path(__file__).parent.parent.parent / "distributions"
class ImageType(Enum):
CONTAINER = "container"
VENV = "venv"
def print_subcommand_description(parser, subparsers):
"""Print descriptions of subcommands."""
description_text = ""
for name, subcommand in subparsers.choices.items():
description = subcommand.description
description_text += f" {name:<21} {description}\n"
parser.epilog = description_text
def generate_run_config(
build_config: BuildConfig,
build_dir: Path,
image_name: str,
) -> Path:
"""
Generate a run.yaml template file for user to edit from a build.yaml file
"""
apis = list(build_config.distribution_spec.providers.keys())
run_config = StackRunConfig(
container_image=(image_name if build_config.image_type == LlamaStackImageType.CONTAINER.value else None),
image_name=image_name,
apis=apis,
providers={},
external_providers_dir=build_config.external_providers_dir
if build_config.external_providers_dir
else EXTERNAL_PROVIDERS_DIR,
)
# build providers dict
provider_registry = get_provider_registry(build_config)
for api in apis:
run_config.providers[api] = []
providers = build_config.distribution_spec.providers[api]
for provider in providers:
pid = provider.provider_type.split("::")[-1]
p = provider_registry[Api(api)][provider.provider_type]
if p.deprecation_error:
raise InvalidProviderError(p.deprecation_error)
try:
config_type = instantiate_class_type(provider_registry[Api(api)][provider.provider_type].config_class)
except (ModuleNotFoundError, ValueError) as exc:
# HACK ALERT:
# This code executes after building is done, the import cannot work since the
# package is either available in the venv or container - not available on the host.
# TODO: use a "is_external" flag in ProviderSpec to check if the provider is
# external
cprint(
f"Failed to import provider {provider.provider_type} for API {api} - assuming it's external, skipping: {exc}",
color="yellow",
file=sys.stderr,
)
# Set config_type to None to avoid UnboundLocalError
config_type = None
if config_type is not None and hasattr(config_type, "sample_run_config"):
config = config_type.sample_run_config(__distro_dir__=f"~/.llama/distributions/{image_name}")
else:
config = {}
p_spec = Provider(
provider_id=pid,
provider_type=provider.provider_type,
config=config,
module=provider.module,
)
run_config.providers[api].append(p_spec)
run_config_file = build_dir / f"{image_name}-run.yaml"
with open(run_config_file, "w") as f:
to_write = json.loads(run_config.model_dump_json())
f.write(yaml.dump(to_write, sort_keys=False))
# Only print this message for non-container builds since it will be displayed before the
# container is built
# For non-container builds, the run.yaml is generated at the very end of the build process so it
# makes sense to display this message
if build_config.image_type != LlamaStackImageType.CONTAINER.value:
cprint(f"You can now run your stack with `llama stack run {run_config_file}`", color="green", file=sys.stderr)
return run_config_file
@lru_cache
def available_templates_specs() -> dict[str, BuildConfig]:
import yaml
template_specs = {}
for p in TEMPLATES_PATH.rglob("*build.yaml"):
template_name = p.parent.name
with open(p) as f:
build_config = BuildConfig(**yaml.safe_load(f))
template_specs[template_name] = build_config
return template_specs