mirror of
https://github.com/meta-llama/llama-stack.git
synced 2025-06-28 02:53:30 +00:00
Kill llama stack configure (#371)
* remove configure * build msg * wip * build->run * delete prints * docs * fix docs, kill configure * precommit * update fireworks build * docs * clean up build * comments * fix * test * remove baking build.yaml into docker * fix msg, urls * configure msg
This commit is contained in:
Xi Yan
GitHub
parent
d289afdbde
commit
748606195b
11 changed files with 248 additions and 401 deletions
|
|
@ -12,6 +12,10 @@ import os
|
|||
from functools import lru_cache
|
||||
from pathlib import Path
|
||||
|
||||
from llama_stack.distribution.distribution import get_provider_registry
|
||||
from llama_stack.distribution.utils.dynamic import instantiate_class_type
|
||||
|
||||
|
||||
TEMPLATES_PATH = Path(os.path.relpath(__file__)).parent.parent.parent / "templates"
|
||||
|
||||
|
||||
|
|
@ -176,6 +180,66 @@ class StackBuild(Subcommand):
|
|||
return
|
||||
self._run_stack_build_command_from_build_config(build_config)
|
||||
|
||||
def _generate_run_config(self, build_config: BuildConfig, build_dir: Path) -> None:
|
||||
"""
|
||||
Generate a run.yaml template file for user to edit from a build.yaml file
|
||||
"""
|
||||
import json
|
||||
|
||||
import yaml
|
||||
from termcolor import cprint
|
||||
|
||||
from llama_stack.distribution.build import ImageType
|
||||
|
||||
apis = list(build_config.distribution_spec.providers.keys())
|
||||
run_config = StackRunConfig(
|
||||
built_at=datetime.now(),
|
||||
docker_image=(
|
||||
build_config.name
|
||||
if build_config.image_type == ImageType.docker.value
|
||||
else None
|
||||
),
|
||||
image_name=build_config.name,
|
||||
conda_env=(
|
||||
build_config.name
|
||||
if build_config.image_type == ImageType.conda.value
|
||||
else None
|
||||
),
|
||||
apis=apis,
|
||||
providers={},
|
||||
)
|
||||
# build providers dict
|
||||
provider_registry = get_provider_registry()
|
||||
for api in apis:
|
||||
run_config.providers[api] = []
|
||||
provider_types = build_config.distribution_spec.providers[api]
|
||||
if isinstance(provider_types, str):
|
||||
provider_types = [provider_types]
|
||||
|
||||
for i, provider_type in enumerate(provider_types):
|
||||
p_spec = Provider(
|
||||
provider_id=f"{provider_type}-{i}",
|
||||
provider_type=provider_type,
|
||||
config={},
|
||||
)
|
||||
config_type = instantiate_class_type(
|
||||
provider_registry[Api(api)][provider_type].config_class
|
||||
)
|
||||
p_spec.config = config_type()
|
||||
run_config.providers[api].append(p_spec)
|
||||
|
||||
os.makedirs(build_dir, exist_ok=True)
|
||||
run_config_file = build_dir / f"{build_config.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))
|
||||
|
||||
cprint(
|
||||
f"You can now edit {run_config_file} and run `llama stack run {run_config_file}`",
|
||||
color="green",
|
||||
)
|
||||
|
||||
def _run_stack_build_command_from_build_config(
|
||||
self, build_config: BuildConfig
|
||||
) -> None:
|
||||
|
|
@ -183,48 +247,24 @@ class StackBuild(Subcommand):
|
|||
import os
|
||||
|
||||
import yaml
|
||||
from termcolor import cprint
|
||||
|
||||
from llama_stack.distribution.build import build_image, ImageType
|
||||
from llama_stack.distribution.build import build_image
|
||||
from llama_stack.distribution.utils.config_dirs import DISTRIBS_BASE_DIR
|
||||
from llama_stack.distribution.utils.serialize import EnumEncoder
|
||||
|
||||
# save build.yaml spec for building same distribution again
|
||||
if build_config.image_type == ImageType.docker.value:
|
||||
# docker needs build file to be in the llama-stack repo dir to be able to copy over to the image
|
||||
llama_stack_path = Path(
|
||||
os.path.abspath(__file__)
|
||||
).parent.parent.parent.parent
|
||||
build_dir = llama_stack_path / "tmp/configs/"
|
||||
else:
|
||||
build_dir = DISTRIBS_BASE_DIR / f"llamastack-{build_config.name}"
|
||||
|
||||
build_dir = DISTRIBS_BASE_DIR / f"llamastack-{build_config.name}"
|
||||
os.makedirs(build_dir, exist_ok=True)
|
||||
build_file_path = build_dir / f"{build_config.name}-build.yaml"
|
||||
|
||||
with open(build_file_path, "w") as f:
|
||||
to_write = json.loads(json.dumps(build_config.dict(), cls=EnumEncoder))
|
||||
to_write = json.loads(build_config.model_dump_json())
|
||||
f.write(yaml.dump(to_write, sort_keys=False))
|
||||
|
||||
return_code = build_image(build_config, build_file_path)
|
||||
if return_code != 0:
|
||||
return
|
||||
|
||||
configure_name = (
|
||||
build_config.name
|
||||
if build_config.image_type == "conda"
|
||||
else (f"llamastack-{build_config.name}")
|
||||
)
|
||||
if build_config.image_type == "conda":
|
||||
cprint(
|
||||
f"You can now run `llama stack configure {configure_name}`",
|
||||
color="green",
|
||||
)
|
||||
else:
|
||||
cprint(
|
||||
f"You can now edit your run.yaml file and run `docker run -it -p 5000:5000 {build_config.name}`. See full command in llama-stack/distributions/",
|
||||
color="green",
|
||||
)
|
||||
self._generate_run_config(build_config, build_dir)
|
||||
|
||||
def _run_template_list_cmd(self, args: argparse.Namespace) -> None:
|
||||
import json
|
||||
|
|
|
|||
|
|
@ -7,8 +7,6 @@
|
|||
import argparse
|
||||
|
||||
from llama_stack.cli.subcommand import Subcommand
|
||||
from llama_stack.distribution.utils.config_dirs import BUILDS_BASE_DIR
|
||||
from llama_stack.distribution.datatypes import * # noqa: F403
|
||||
|
||||
|
||||
class StackConfigure(Subcommand):
|
||||
|
|
@ -39,123 +37,10 @@ class StackConfigure(Subcommand):
|
|||
)
|
||||
|
||||
def _run_stack_configure_cmd(self, args: argparse.Namespace) -> None:
|
||||
import json
|
||||
import os
|
||||
import subprocess
|
||||
from pathlib import Path
|
||||
|
||||
import pkg_resources
|
||||
|
||||
import yaml
|
||||
from termcolor import cprint
|
||||
|
||||
from llama_stack.distribution.build import ImageType
|
||||
from llama_stack.distribution.utils.exec import run_with_pty
|
||||
|
||||
docker_image = None
|
||||
|
||||
build_config_file = Path(args.config)
|
||||
if build_config_file.exists():
|
||||
with open(build_config_file, "r") as f:
|
||||
build_config = BuildConfig(**yaml.safe_load(f))
|
||||
self._configure_llama_distribution(build_config, args.output_dir)
|
||||
return
|
||||
|
||||
conda_dir = (
|
||||
Path(os.path.expanduser("~/.conda/envs")) / f"llamastack-{args.config}"
|
||||
)
|
||||
output = subprocess.check_output(["bash", "-c", "conda info --json"])
|
||||
conda_envs = json.loads(output.decode("utf-8"))["envs"]
|
||||
|
||||
for x in conda_envs:
|
||||
if x.endswith(f"/llamastack-{args.config}"):
|
||||
conda_dir = Path(x)
|
||||
break
|
||||
|
||||
build_config_file = Path(conda_dir) / f"{args.config}-build.yaml"
|
||||
if build_config_file.exists():
|
||||
with open(build_config_file, "r") as f:
|
||||
build_config = BuildConfig(**yaml.safe_load(f))
|
||||
|
||||
cprint(f"Using {build_config_file}...", "green")
|
||||
self._configure_llama_distribution(build_config, args.output_dir)
|
||||
return
|
||||
|
||||
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)
|
||||
if return_code != 0:
|
||||
self.parser.error(
|
||||
f"Failed to configure container {docker_image} with return code {return_code}. Please run `llama stack build` first. "
|
||||
)
|
||||
|
||||
def _configure_llama_distribution(
|
||||
self,
|
||||
build_config: BuildConfig,
|
||||
output_dir: Optional[str] = None,
|
||||
):
|
||||
import json
|
||||
import os
|
||||
from pathlib import Path
|
||||
|
||||
import yaml
|
||||
from termcolor import cprint
|
||||
|
||||
from llama_stack.distribution.configure import (
|
||||
configure_api_providers,
|
||||
parse_and_maybe_upgrade_config,
|
||||
)
|
||||
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_dict = yaml.safe_load(run_config_file.read_text())
|
||||
config = parse_and_maybe_upgrade_config(config_dict)
|
||||
else:
|
||||
config = StackRunConfig(
|
||||
built_at=datetime.now(),
|
||||
image_name=image_name,
|
||||
apis=list(build_config.distribution_spec.providers.keys()),
|
||||
providers={},
|
||||
)
|
||||
|
||||
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",
|
||||
)
|
||||
|
||||
cprint(
|
||||
f"You can now run `llama stack run {image_name} --port PORT`",
|
||||
color="green",
|
||||
self.parser.error(
|
||||
"""
|
||||
DEPRECATED! llama stack configure has been deprecated.
|
||||
Please use llama stack run --config <path/to/run.yaml> instead.
|
||||
Please see example run.yaml in /distributions folder.
|
||||
"""
|
||||
)
|
||||
|
|
|
|||
|
|
@ -45,7 +45,6 @@ class StackRun(Subcommand):
|
|||
|
||||
import pkg_resources
|
||||
import yaml
|
||||
from termcolor import cprint
|
||||
|
||||
from llama_stack.distribution.build import ImageType
|
||||
from llama_stack.distribution.configure import parse_and_maybe_upgrade_config
|
||||
|
|
@ -71,14 +70,12 @@ class StackRun(Subcommand):
|
|||
|
||||
if not config_file.exists():
|
||||
self.parser.error(
|
||||
f"File {str(config_file)} does not exist. Please run `llama stack build` and `llama stack configure <name>` to generate a run.yaml file"
|
||||
f"File {str(config_file)} does not exist. Please run `llama stack build` to generate (and optionally edit) a run.yaml file"
|
||||
)
|
||||
return
|
||||
|
||||
cprint(f"Using config `{config_file}`", "green")
|
||||
with open(config_file, "r") as f:
|
||||
config_dict = yaml.safe_load(config_file.read_text())
|
||||
config = parse_and_maybe_upgrade_config(config_dict)
|
||||
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(
|
||||
|
|
|
|||
|
|
@ -36,7 +36,6 @@ SCRIPT_DIR=$(dirname "$(readlink -f "$0")")
|
|||
REPO_DIR=$(dirname $(dirname "$SCRIPT_DIR"))
|
||||
DOCKER_BINARY=${DOCKER_BINARY:-docker}
|
||||
DOCKER_OPTS=${DOCKER_OPTS:-}
|
||||
REPO_CONFIGS_DIR="$REPO_DIR/tmp/configs"
|
||||
|
||||
TEMP_DIR=$(mktemp -d)
|
||||
|
||||
|
|
@ -115,8 +114,6 @@ ENTRYPOINT ["python", "-m", "llama_stack.distribution.server.server"]
|
|||
|
||||
EOF
|
||||
|
||||
add_to_docker "ADD tmp/configs/$(basename "$build_file_path") ./llamastack-build.yaml"
|
||||
|
||||
printf "Dockerfile created successfully in $TEMP_DIR/Dockerfile"
|
||||
cat $TEMP_DIR/Dockerfile
|
||||
printf "\n"
|
||||
|
|
@ -138,7 +135,6 @@ set -x
|
|||
$DOCKER_BINARY build $DOCKER_OPTS -t $image_name -f "$TEMP_DIR/Dockerfile" "$REPO_DIR" $mounts
|
||||
|
||||
# clean up tmp/configs
|
||||
rm -rf $REPO_CONFIGS_DIR
|
||||
set +x
|
||||
|
||||
echo "Success!"
|
||||
|
|
|
|||
|
|
@ -12,9 +12,14 @@ from pydantic import BaseModel, Field
|
|||
|
||||
@json_schema_type
|
||||
class TGIImplConfig(BaseModel):
|
||||
url: str = Field(
|
||||
description="The URL for the TGI endpoint (e.g. 'http://localhost:8080')",
|
||||
)
|
||||
host: str = "localhost"
|
||||
port: int = 8080
|
||||
protocol: str = "http"
|
||||
|
||||
@property
|
||||
def url(self) -> str:
|
||||
return f"{self.protocol}://{self.host}:{self.port}"
|
||||
|
||||
api_token: Optional[str] = Field(
|
||||
default=None,
|
||||
description="A bearer token if your TGI endpoint is protected.",
|
||||
|
|
|
|||
|
|
@ -12,6 +12,6 @@ from pydantic import BaseModel, Field
|
|||
class PGVectorConfig(BaseModel):
|
||||
host: str = Field(default="localhost")
|
||||
port: int = Field(default=5432)
|
||||
db: str
|
||||
user: str
|
||||
password: str
|
||||
db: str = Field(default="postgres")
|
||||
user: str = Field(default="postgres")
|
||||
password: str = Field(default="mysecretpassword")
|
||||
|
|
|
|||
|
|
@ -145,11 +145,12 @@ Fully-qualified name of the module to import. The module is expected to have:
|
|||
|
||||
class RemoteProviderConfig(BaseModel):
|
||||
host: str = "localhost"
|
||||
port: int
|
||||
port: int = 0
|
||||
protocol: str = "http"
|
||||
|
||||
@property
|
||||
def url(self) -> str:
|
||||
return f"http://{self.host}:{self.port}"
|
||||
return f"{self.protocol}://{self.host}:{self.port}"
|
||||
|
||||
|
||||
@json_schema_type
|
||||
|
|
|
|||
|
|
@ -4,10 +4,11 @@
|
|||
# This source code is licensed under the terms described in the LICENSE file in
|
||||
# the root directory of this source tree.
|
||||
|
||||
from pydantic import BaseModel
|
||||
from pydantic import BaseModel, Field
|
||||
|
||||
from llama_stack.providers.utils.kvstore import KVStoreConfig
|
||||
from llama_stack.providers.utils.kvstore.config import SqliteKVStoreConfig
|
||||
|
||||
|
||||
class MetaReferenceAgentsImplConfig(BaseModel):
|
||||
persistence_store: KVStoreConfig
|
||||
persistence_store: KVStoreConfig = Field(default=SqliteKVStoreConfig())
|
||||
|
|
|
|||
|
|
@ -6,8 +6,6 @@ distribution_spec:
|
|||
memory:
|
||||
- meta-reference
|
||||
- remote::weaviate
|
||||
- remote::chromadb
|
||||
- remote::pgvector
|
||||
safety: meta-reference
|
||||
agents: meta-reference
|
||||
telemetry: meta-reference
|
||||
|
|
|
|||
Loading…
Add table
Add a link
Reference in a new issue