mirror of
https://github.com/meta-llama/llama-stack.git
synced 2025-06-27 18:50:41 +00:00
9487ad8294
* API Keys passed from Client instead of distro configuration * delete distribution registry * Rename the "package" word away * Introduce a "Router" layer for providers Some providers need to be factorized and considered as thin routing layers on top of other providers. Consider two examples: - The inference API should be a routing layer over inference providers, routed using the "model" key - The memory banks API is another instance where various memory bank types will be provided by independent providers (e.g., a vector store is served by Chroma while a keyvalue memory can be served by Redis or PGVector) This commit introduces a generalized routing layer for this purpose. * update `apis_to_serve` * llama_toolchain -> llama_stack * Codemod from llama_toolchain -> llama_stack - added providers/registry - cleaned up api/ subdirectories and moved impls away - restructured api/api.py - from llama_stack.apis.<api> import foo should work now - update imports to do llama_stack.apis.<api> - update many other imports - added __init__, fixed some registry imports - updated registry imports - create_agentic_system -> create_agent - AgenticSystem -> Agent * Moved some stuff out of common/; re-generated OpenAPI spec * llama-toolchain -> llama-stack (hyphens) * add control plane API * add redis adapter + sqlite provider * move core -> distribution * Some more toolchain -> stack changes * small naming shenanigans * Removing custom tool and agent utilities and moving them client side * Move control plane to distribution server for now * Remove control plane from API list * no codeshield dependency randomly plzzzzz * Add "fire" as a dependency * add back event loggers * stack configure fixes * use brave instead of bing in the example client * add init file so it gets packaged * add init files so it gets packaged * Update MANIFEST * bug fix --------- Co-authored-by: Hardik Shah <hjshah@fb.com> Co-authored-by: Xi Yan <xiyan@meta.com> Co-authored-by: Ashwin Bharambe <ashwin@meta.com>
88 lines
2.7 KiB
Python
88 lines
2.7 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 argparse
|
|
|
|
from pathlib import Path
|
|
|
|
import pkg_resources
|
|
import yaml
|
|
|
|
from llama_stack.cli.subcommand import Subcommand
|
|
from llama_stack.distribution.datatypes import * # noqa: F403
|
|
|
|
|
|
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 llama_stack.distribution.utils.exec import run_with_pty
|
|
|
|
if not args.config:
|
|
self.parser.error("Must specify a config file to run")
|
|
return
|
|
|
|
path = args.config
|
|
config_file = Path(path)
|
|
|
|
if not config_file.exists():
|
|
self.parser.error(
|
|
f"File {str(config_file)} does not exist. Did you run `llama stack build`?"
|
|
)
|
|
return
|
|
|
|
with open(config_file, "r") as f:
|
|
config = StackRunConfig(**yaml.safe_load(f))
|
|
|
|
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)
|