mirror of
https://github.com/meta-llama/llama-stack.git
synced 2025-06-28 02:53:30 +00:00
f1b9578f8d
**Summary:** Extend the shorthand run command so it can run successfully when config exists under DISTRIBS_BASE_DIR (i.e. ~/.llama/distributions). For example, imagine you created a new stack using the `llama stack build` command where you named it "my-awesome-llama-stack". ``` $ llama stack build > Enter a name for your Llama Stack (e.g. my-local-stack): my-awesome-llama-stack ``` To run the stack you created you will have to use long config path: ``` llama stack run ~/.llama/distributions/llamastack-my-awesome-llama-stack/my-awesome-llama-stack-run.yaml ``` With this change, you can start it using the stack name instead of full path: ``` llama stack run my-awesome-llama-stack ``` **Test Plan:** Verify command fails when stack doesn't exist ``` python3 -m llama_stack.cli.llama stack run my-test-stack ``` Output [FAILURE] ``` usage: llama stack run [-h] [--port PORT] [--disable-ipv6] config llama stack run: error: File /Users/vladimirivic/.llama/distributions/llamastack-my-test-stack/my-test-stack-run.yaml does not exist. Please run `llama stack build` to generate (and optionally edit) a run.yaml file ``` Create a new stack using `llama stack build`. Name it `my-test-stack`. Verify command runs successfully ``` python3 -m llama_stack.cli.llama stack run my-test-stack ``` Output [SUCCESS] ``` Listening on ['::', '0.0.0.0']:5000 INFO: Started server process [80146] INFO: Waiting for application startup. INFO: Application startup complete. INFO: Uvicorn running on http://['::', '0.0.0.0']:5000 (Press CTRL+C to quit) ```
111 lines
3.8 KiB
Python
111 lines
3.8 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
|
|
|
|
from llama_stack.cli.subcommand import Subcommand
|
|
|
|
|
|
class StackRun(Subcommand):
|
|
def __init__(self, subparsers: argparse._SubParsersAction):
|
|
super().__init__()
|
|
self.parser = subparsers.add_parser(
|
|
"run",
|
|
prog="llama stack run",
|
|
description="""start the server for a Llama Stack Distribution. You should have already built (or downloaded) and configured the distribution.""",
|
|
formatter_class=argparse.RawTextHelpFormatter,
|
|
)
|
|
self._add_arguments()
|
|
self.parser.set_defaults(func=self._run_stack_run_cmd)
|
|
|
|
def _add_arguments(self):
|
|
self.parser.add_argument(
|
|
"config",
|
|
type=str,
|
|
help="Path to config file to use for the run",
|
|
)
|
|
self.parser.add_argument(
|
|
"--port",
|
|
type=int,
|
|
help="Port to run the server on. Defaults to 5000",
|
|
default=5000,
|
|
)
|
|
self.parser.add_argument(
|
|
"--disable-ipv6",
|
|
action="store_true",
|
|
help="Disable IPv6 support",
|
|
default=False,
|
|
)
|
|
|
|
def _run_stack_run_cmd(self, args: argparse.Namespace) -> None:
|
|
from pathlib import Path
|
|
|
|
import pkg_resources
|
|
import yaml
|
|
|
|
from llama_stack.distribution.build import ImageType
|
|
from llama_stack.distribution.configure import parse_and_maybe_upgrade_config
|
|
from llama_stack.distribution.utils.config_dirs import (
|
|
BUILDS_BASE_DIR,
|
|
DISTRIBS_BASE_DIR,
|
|
)
|
|
from llama_stack.distribution.utils.exec import run_with_pty
|
|
|
|
if not args.config:
|
|
self.parser.error("Must specify a config file to run")
|
|
return
|
|
|
|
config_file = Path(args.config)
|
|
if not config_file.exists() and not args.config.endswith(".yaml"):
|
|
# check if it's a build config saved to conda dir
|
|
config_file = Path(
|
|
BUILDS_BASE_DIR / ImageType.conda.value / f"{args.config}-run.yaml"
|
|
)
|
|
|
|
if not config_file.exists() and not args.config.endswith(".yaml"):
|
|
# check if it's a build config saved to docker dir
|
|
config_file = Path(
|
|
BUILDS_BASE_DIR / ImageType.docker.value / f"{args.config}-run.yaml"
|
|
)
|
|
|
|
if not config_file.exists() and not args.config.endswith(".yaml"):
|
|
# check if it's a build config saved to ~/.llama dir
|
|
config_file = Path(
|
|
DISTRIBS_BASE_DIR
|
|
/ f"llamastack-{args.config}"
|
|
/ f"{args.config}-run.yaml"
|
|
)
|
|
|
|
if not config_file.exists():
|
|
self.parser.error(
|
|
f"File {str(config_file)} does not exist. Please run `llama stack build` to generate (and optionally edit) a run.yaml file"
|
|
)
|
|
return
|
|
|
|
config_dict = yaml.safe_load(config_file.read_text())
|
|
config = parse_and_maybe_upgrade_config(config_dict)
|
|
|
|
if config.docker_image:
|
|
script = pkg_resources.resource_filename(
|
|
"llama_stack",
|
|
"distribution/start_container.sh",
|
|
)
|
|
run_args = [script, config.docker_image]
|
|
else:
|
|
script = pkg_resources.resource_filename(
|
|
"llama_stack",
|
|
"distribution/start_conda_env.sh",
|
|
)
|
|
run_args = [
|
|
script,
|
|
config.conda_env,
|
|
]
|
|
|
|
run_args.extend([str(config_file), str(args.port)])
|
|
if args.disable_ipv6:
|
|
run_args.append("--disable-ipv6")
|
|
|
|
run_with_pty(run_args)
|