llama-stack-mirror/llama_stack/cli/stack/configure.py
Ashwin Bharambe 9487ad8294
API Updates (#73)
* 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>
2024-09-17 19:51:35 -07:00

137 lines
4.9 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 json
from pathlib import Path
import pkg_resources
import yaml
from termcolor import cprint
from llama_stack.cli.subcommand import Subcommand
from llama_stack.distribution.utils.config_dirs import BUILDS_BASE_DIR
from llama_stack.distribution.utils.exec import run_with_pty
from llama_stack.distribution.datatypes import * # noqa: F403
import os
class StackConfigure(Subcommand):
"""Llama cli for configuring llama toolchain configs"""
def __init__(self, subparsers: argparse._SubParsersAction):
super().__init__()
self.parser = subparsers.add_parser(
"configure",
prog="llama stack configure",
description="configure a llama stack distribution",
formatter_class=argparse.RawTextHelpFormatter,
)
self._add_arguments()
self.parser.set_defaults(func=self._run_stack_configure_cmd)
def _add_arguments(self):
self.parser.add_argument(
"config",
type=str,
help="Path to the build config file (e.g. ~/.llama/builds/<image_type>/<name>-build.yaml). For docker, this could also be the name of the docker image. ",
)
self.parser.add_argument(
"--output-dir",
type=str,
help="Path to the output directory to store generated run.yaml config file. If not specified, will use ~/.llama/build/<image_type>/<name>-run.yaml",
)
def _run_stack_configure_cmd(self, args: argparse.Namespace) -> None:
from llama_stack.distribution.build import ImageType
docker_image = None
build_config_file = Path(args.config)
if not build_config_file.exists():
cprint(
f"Could not find {build_config_file}. Trying docker image name instead...",
color="green",
)
docker_image = args.config
builds_dir = BUILDS_BASE_DIR / ImageType.docker.value
if args.output_dir:
builds_dir = Path(output_dir)
os.makedirs(builds_dir, exist_ok=True)
script = pkg_resources.resource_filename(
"llama_stack", "distribution/configure_container.sh"
)
script_args = [script, docker_image, str(builds_dir)]
return_code = run_with_pty(script_args)
# we have regenerated the build config file with script, now check if it exists
if return_code != 0:
self.parser.error(
f"Can not find {build_config_file}. Please run llama stack build first or check if docker image exists"
)
build_name = docker_image.removeprefix("llamastack-")
cprint(
f"YAML configuration has been written to {builds_dir / f'{build_name}-run.yaml'}",
color="green",
)
return
with open(build_config_file, "r") as f:
build_config = BuildConfig(**yaml.safe_load(f))
self._configure_llama_distribution(build_config, args.output_dir)
def _configure_llama_distribution(
self,
build_config: BuildConfig,
output_dir: Optional[str] = None,
):
from llama_stack.distribution.configure import configure_api_providers
from llama_stack.distribution.utils.serialize import EnumEncoder
builds_dir = BUILDS_BASE_DIR / build_config.image_type
if output_dir:
builds_dir = Path(output_dir)
os.makedirs(builds_dir, exist_ok=True)
image_name = build_config.name.replace("::", "-")
run_config_file = builds_dir / f"{image_name}-run.yaml"
if run_config_file.exists():
cprint(
f"Configuration already exists at `{str(run_config_file)}`. Will overwrite...",
"yellow",
attrs=["bold"],
)
config = StackRunConfig(**yaml.safe_load(run_config_file.read_text()))
else:
config = StackRunConfig(
built_at=datetime.now(),
image_name=image_name,
apis_to_serve=[],
provider_map={},
)
config = configure_api_providers(config, build_config.distribution_spec)
config.docker_image = (
image_name if build_config.image_type == "docker" else None
)
config.conda_env = image_name if build_config.image_type == "conda" else None
with open(run_config_file, "w") as f:
to_write = json.loads(json.dumps(config.dict(), cls=EnumEncoder))
f.write(yaml.dump(to_write, sort_keys=False))
cprint(
f"> YAML configuration has been written to {run_config_file}",
color="blue",
)