mirror of
https://github.com/meta-llama/llama-stack.git
synced 2025-10-04 04:04:14 +00:00
feat: introduce API leveling, post_training, eval to v1alpha (#3449)
# 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>
This commit is contained in:
parent
65e01b5684
commit
c88c4ff2c6
35 changed files with 1507 additions and 260 deletions
|
@ -15,7 +15,6 @@ import httpx
|
|||
from pydantic import BaseModel, parse_obj_as
|
||||
from termcolor import cprint
|
||||
|
||||
from llama_stack.apis.version import LLAMA_STACK_API_VERSION
|
||||
from llama_stack.providers.datatypes import RemoteProviderConfig
|
||||
|
||||
_CLIENT_CLASSES = {}
|
||||
|
@ -114,7 +113,24 @@ def create_api_client_class(protocol) -> type:
|
|||
break
|
||||
kwargs[param.name] = args[i]
|
||||
|
||||
url = f"{self.base_url}/{LLAMA_STACK_API_VERSION}/{webmethod.route.lstrip('/')}"
|
||||
# Get all webmethods for this method (supports multiple decorators)
|
||||
webmethods = getattr(method, "__webmethods__", [])
|
||||
|
||||
if not webmethods:
|
||||
raise RuntimeError(f"Method {method} has no webmethod decorators")
|
||||
|
||||
# Choose the preferred webmethod (non-deprecated if available)
|
||||
preferred_webmethod = None
|
||||
for wm in webmethods:
|
||||
if not getattr(wm, "deprecated", False):
|
||||
preferred_webmethod = wm
|
||||
break
|
||||
|
||||
# If no non-deprecated found, use the first one
|
||||
if preferred_webmethod is None:
|
||||
preferred_webmethod = webmethods[0]
|
||||
|
||||
url = f"{self.base_url}/{preferred_webmethod.level}/{preferred_webmethod.route.lstrip('/')}"
|
||||
|
||||
def convert(value):
|
||||
if isinstance(value, list):
|
||||
|
|
Loading…
Add table
Add a link
Reference in a new issue