mirror of
https://github.com/meta-llama/llama-stack.git
synced 2025-10-04 20:14:13 +00:00
c88c4ff2c6
# What does this PR do? Rather than have a single `LLAMA_STACK_VERSION`, we need to have a `_V1`, `_V1ALPHA`, and `_V1BETA` constant. This also necessitated addition of `level` to the `WebMethod` so that routing can be handeled properly. For backwards compat, the `v1` routes are being kept around and marked as `deprecated`. When used, the server will log a deprecation warning. Deprecation log: <img width="1224" height="134" alt="Screenshot 2025-09-25 at 2 43 36 PM" src="https://github.com/user-attachments/assets/0cc7c245-dafc-48f0-be99-269fb9a686f9" /> move: 1. post_training to `v1alpha` as it is under heavy development and not near its final state 2. eval: job scheduling is not implemented. Relies heavily on the datasetio API which is under development missing implementations of specific routes indicating the structure of those routes might change. Additionally eval depends on the `inference` API which is going to be deprecated, eval will likely need a major API surface change to conform to using completions properly implements leveling in #3317 note: integration tests will fail until the SDK is regenerated with v1alpha/inference as opposed to v1/inference ## Test Plan existing tests should pass with newly generated schema. Conformance will also pass as these routes are not the ones we currently test for stability Signed-off-by: Charlie Doern <cdoern@redhat.com>
91 lines
2.8 KiB
Python
91 lines
2.8 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.
|
|
|
|
# Copyright (c) Meta Platforms, Inc. and affiliates.
|
|
# All rights reserved.
|
|
#
|
|
# This source code is licensed under the terms described found in the
|
|
# LICENSE file in the root directory of this source tree.
|
|
|
|
from datetime import datetime
|
|
from pathlib import Path
|
|
import sys
|
|
import fire
|
|
import ruamel.yaml as yaml
|
|
|
|
from llama_stack.apis.version import LLAMA_STACK_API_V1 # noqa: E402
|
|
from llama_stack.core.stack import LlamaStack # noqa: E402
|
|
|
|
from .pyopenapi.options import Options # noqa: E402
|
|
from .pyopenapi.specification import Info, Server # noqa: E402
|
|
from .pyopenapi.utility import Specification, validate_api # noqa: E402
|
|
|
|
|
|
def str_presenter(dumper, data):
|
|
if data.startswith(f"/{LLAMA_STACK_API_V1}") or data.startswith(
|
|
"#/components/schemas/"
|
|
):
|
|
style = None
|
|
else:
|
|
style = ">" if "\n" in data or len(data) > 40 else None
|
|
return dumper.represent_scalar("tag:yaml.org,2002:str", data, style=style)
|
|
|
|
|
|
def main(output_dir: str):
|
|
output_dir = Path(output_dir)
|
|
if not output_dir.exists():
|
|
raise ValueError(f"Directory {output_dir} does not exist")
|
|
|
|
# Validate API protocols before generating spec
|
|
return_type_errors = validate_api()
|
|
if return_type_errors:
|
|
print("\nAPI Method Return Type Validation Errors:\n")
|
|
for error in return_type_errors:
|
|
print(error, file=sys.stderr)
|
|
sys.exit(1)
|
|
now = str(datetime.now())
|
|
print(
|
|
"Converting the spec to YAML (openapi.yaml) and HTML (openapi.html) at " + now
|
|
)
|
|
print("")
|
|
|
|
spec = Specification(
|
|
LlamaStack,
|
|
Options(
|
|
server=Server(url="http://any-hosted-llama-stack.com"),
|
|
info=Info(
|
|
title="Llama Stack Specification",
|
|
version=LLAMA_STACK_API_V1,
|
|
description="""This is the specification of the Llama Stack that provides
|
|
a set of endpoints and their corresponding interfaces that are tailored to
|
|
best leverage Llama Models.""",
|
|
),
|
|
include_standard_error_responses=True,
|
|
),
|
|
)
|
|
|
|
with open(output_dir / "llama-stack-spec.yaml", "w", encoding="utf-8") as fp:
|
|
y = yaml.YAML()
|
|
y.default_flow_style = False
|
|
y.block_seq_indent = 2
|
|
y.map_indent = 2
|
|
y.sequence_indent = 4
|
|
y.sequence_dash_offset = 2
|
|
y.width = 80
|
|
y.allow_unicode = True
|
|
y.representer.add_representer(str, str_presenter)
|
|
|
|
y.dump(
|
|
spec.get_json(),
|
|
fp,
|
|
)
|
|
|
|
with open(output_dir / "llama-stack-spec.html", "w") as fp:
|
|
spec.write_html(fp, pretty_print=True)
|
|
|
|
|
|
if __name__ == "__main__":
|
|
fire.Fire(main)
|