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:
Charlie Doern
GitHub
parent
65e01b5684
commit
c88c4ff2c6
35 changed files with 1507 additions and 260 deletions
|
|
@ -16,7 +16,7 @@ import sys
|
|||
import fire
|
||||
import ruamel.yaml as yaml
|
||||
|
||||
from llama_stack.apis.version import LLAMA_STACK_API_VERSION # noqa: E402
|
||||
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
|
||||
|
|
@ -25,7 +25,7 @@ from .pyopenapi.utility import Specification, validate_api # noqa: E402
|
|||
|
||||
|
||||
def str_presenter(dumper, data):
|
||||
if data.startswith(f"/{LLAMA_STACK_API_VERSION}") or data.startswith(
|
||||
if data.startswith(f"/{LLAMA_STACK_API_V1}") or data.startswith(
|
||||
"#/components/schemas/"
|
||||
):
|
||||
style = None
|
||||
|
|
@ -58,7 +58,7 @@ def main(output_dir: str):
|
|||
server=Server(url="http://any-hosted-llama-stack.com"),
|
||||
info=Info(
|
||||
title="Llama Stack Specification",
|
||||
version=LLAMA_STACK_API_VERSION,
|
||||
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.""",
|
||||
|
|
|
|||
|
|
@ -829,7 +829,7 @@ class Generator:
|
|||
else:
|
||||
raise NotImplementedError(f"unknown HTTP method: {op.http_method}")
|
||||
|
||||
route = op.get_route()
|
||||
route = op.get_route(op.webmethod)
|
||||
route = route.replace(":path", "")
|
||||
print(f"route: {route}")
|
||||
if route in paths:
|
||||
|
|
|
|||
|
|
@ -11,7 +11,7 @@ import typing
|
|||
from dataclasses import dataclass
|
||||
from typing import Any, Callable, Dict, Iterable, Iterator, List, Optional, Tuple, Union
|
||||
|
||||
from llama_stack.apis.version import LLAMA_STACK_API_VERSION
|
||||
from llama_stack.apis.version import LLAMA_STACK_API_V1, LLAMA_STACK_API_V1BETA, LLAMA_STACK_API_V1ALPHA
|
||||
|
||||
from termcolor import colored
|
||||
|
||||
|
|
@ -113,11 +113,13 @@ class EndpointOperation:
|
|||
request_examples: Optional[List[Any]] = None
|
||||
response_examples: Optional[List[Any]] = None
|
||||
|
||||
def get_route(self) -> str:
|
||||
if self.route is not None:
|
||||
return "/".join(["", LLAMA_STACK_API_VERSION, self.route.lstrip("/")])
|
||||
def get_route(self, webmethod) -> str:
|
||||
api_level = webmethod.level
|
||||
|
||||
route_parts = ["", LLAMA_STACK_API_VERSION, self.name]
|
||||
if self.route is not None:
|
||||
return "/".join(["", api_level, self.route.lstrip("/")])
|
||||
|
||||
route_parts = ["", api_level, self.name]
|
||||
for param_name, _ in self.path_params:
|
||||
route_parts.append("{" + param_name + "}")
|
||||
return "/".join(route_parts)
|
||||
|
|
@ -152,33 +154,39 @@ def _get_endpoint_functions(
|
|||
|
||||
functions = inspect.getmembers(endpoint, inspect.isfunction)
|
||||
for func_name, func_ref in functions:
|
||||
webmethod = getattr(func_ref, "__webmethod__", None)
|
||||
if not webmethod:
|
||||
webmethods = []
|
||||
|
||||
# Check for multiple webmethods (stacked decorators)
|
||||
if hasattr(func_ref, "__webmethods__"):
|
||||
webmethods = func_ref.__webmethods__
|
||||
|
||||
if not webmethods:
|
||||
continue
|
||||
|
||||
print(f"Processing {colored(func_name, 'white')}...")
|
||||
operation_name = func_name
|
||||
|
||||
if webmethod.method == "GET":
|
||||
prefix = "get"
|
||||
elif webmethod.method == "DELETE":
|
||||
prefix = "delete"
|
||||
elif webmethod.method == "POST":
|
||||
prefix = "post"
|
||||
elif operation_name.startswith("get_") or operation_name.endswith("/get"):
|
||||
prefix = "get"
|
||||
elif (
|
||||
operation_name.startswith("delete_")
|
||||
or operation_name.startswith("remove_")
|
||||
or operation_name.endswith("/delete")
|
||||
or operation_name.endswith("/remove")
|
||||
):
|
||||
prefix = "delete"
|
||||
else:
|
||||
# by default everything else is a POST
|
||||
prefix = "post"
|
||||
for webmethod in webmethods:
|
||||
print(f"Processing {colored(func_name, 'white')}...")
|
||||
operation_name = func_name
|
||||
|
||||
if webmethod.method == "GET":
|
||||
prefix = "get"
|
||||
elif webmethod.method == "DELETE":
|
||||
prefix = "delete"
|
||||
elif webmethod.method == "POST":
|
||||
prefix = "post"
|
||||
elif operation_name.startswith("get_") or operation_name.endswith("/get"):
|
||||
prefix = "get"
|
||||
elif (
|
||||
operation_name.startswith("delete_")
|
||||
or operation_name.startswith("remove_")
|
||||
or operation_name.endswith("/delete")
|
||||
or operation_name.endswith("/remove")
|
||||
):
|
||||
prefix = "delete"
|
||||
else:
|
||||
# by default everything else is a POST
|
||||
prefix = "post"
|
||||
|
||||
yield prefix, operation_name, func_name, func_ref
|
||||
yield prefix, operation_name, func_name, func_ref
|
||||
|
||||
|
||||
def _get_defining_class(member_fn: str, derived_cls: type) -> type:
|
||||
|
|
@ -239,105 +247,101 @@ def get_endpoint_operations(
|
|||
"update",
|
||||
],
|
||||
):
|
||||
# extract routing information from function metadata
|
||||
webmethod = getattr(func_ref, "__webmethod__", None)
|
||||
if webmethod is not None:
|
||||
# Get all webmethods for this function
|
||||
webmethods = getattr(func_ref, "__webmethods__", [])
|
||||
|
||||
# Create one EndpointOperation for each webmethod
|
||||
for webmethod in webmethods:
|
||||
route = webmethod.route
|
||||
route_params = _get_route_parameters(route) if route is not None else None
|
||||
public = webmethod.public
|
||||
request_examples = webmethod.request_examples
|
||||
response_examples = webmethod.response_examples
|
||||
else:
|
||||
route = None
|
||||
route_params = None
|
||||
public = False
|
||||
request_examples = None
|
||||
response_examples = None
|
||||
|
||||
# inspect function signature for path and query parameters, and request/response payload type
|
||||
signature = get_signature(func_ref)
|
||||
# inspect function signature for path and query parameters, and request/response payload type
|
||||
signature = get_signature(func_ref)
|
||||
|
||||
path_params = []
|
||||
query_params = []
|
||||
request_params = []
|
||||
multipart_params = []
|
||||
path_params = []
|
||||
query_params = []
|
||||
request_params = []
|
||||
multipart_params = []
|
||||
|
||||
for param_name, parameter in signature.parameters.items():
|
||||
param_type = _get_annotation_type(parameter.annotation, func_ref)
|
||||
for param_name, parameter in signature.parameters.items():
|
||||
param_type = _get_annotation_type(parameter.annotation, func_ref)
|
||||
|
||||
# omit "self" for instance methods
|
||||
if param_name == "self" and param_type is inspect.Parameter.empty:
|
||||
continue
|
||||
# omit "self" for instance methods
|
||||
if param_name == "self" and param_type is inspect.Parameter.empty:
|
||||
continue
|
||||
|
||||
# check if all parameters have explicit type
|
||||
if parameter.annotation is inspect.Parameter.empty:
|
||||
# check if all parameters have explicit type
|
||||
if parameter.annotation is inspect.Parameter.empty:
|
||||
raise ValidationError(
|
||||
f"parameter '{param_name}' in function '{func_name}' has no type annotation"
|
||||
)
|
||||
|
||||
is_multipart = _is_multipart_param(param_type)
|
||||
|
||||
if prefix in ["get", "delete"]:
|
||||
if route_params is not None and param_name in route_params:
|
||||
path_params.append((param_name, param_type))
|
||||
else:
|
||||
query_params.append((param_name, param_type))
|
||||
else:
|
||||
if route_params is not None and param_name in route_params:
|
||||
path_params.append((param_name, param_type))
|
||||
elif is_multipart:
|
||||
multipart_params.append((param_name, param_type))
|
||||
else:
|
||||
request_params.append((param_name, param_type))
|
||||
|
||||
# check if function has explicit return type
|
||||
if signature.return_annotation is inspect.Signature.empty:
|
||||
raise ValidationError(
|
||||
f"parameter '{param_name}' in function '{func_name}' has no type annotation"
|
||||
f"function '{func_name}' has no return type annotation"
|
||||
)
|
||||
|
||||
is_multipart = _is_multipart_param(param_type)
|
||||
|
||||
if prefix in ["get", "delete"]:
|
||||
if route_params is not None and param_name in route_params:
|
||||
path_params.append((param_name, param_type))
|
||||
else:
|
||||
query_params.append((param_name, param_type))
|
||||
return_type = _get_annotation_type(signature.return_annotation, func_ref)
|
||||
|
||||
# operations that produce events are labeled as Generator[YieldType, SendType, ReturnType]
|
||||
# where YieldType is the event type, SendType is None, and ReturnType is the immediate response type to the request
|
||||
if typing.get_origin(return_type) is collections.abc.Generator:
|
||||
event_type, send_type, response_type = typing.get_args(return_type)
|
||||
if send_type is not type(None):
|
||||
raise ValidationError(
|
||||
f"function '{func_name}' has a return type Generator[Y,S,R] and therefore looks like an event but has an explicit send type"
|
||||
)
|
||||
else:
|
||||
if route_params is not None and param_name in route_params:
|
||||
path_params.append((param_name, param_type))
|
||||
elif is_multipart:
|
||||
multipart_params.append((param_name, param_type))
|
||||
event_type = None
|
||||
|
||||
def process_type(t):
|
||||
if typing.get_origin(t) is collections.abc.AsyncIterator:
|
||||
# NOTE(ashwin): this is SSE and there is no way to represent it. either we make it a List
|
||||
# or the item type. I am choosing it to be the latter
|
||||
args = typing.get_args(t)
|
||||
return args[0]
|
||||
elif typing.get_origin(t) is typing.Union:
|
||||
types = [process_type(a) for a in typing.get_args(t)]
|
||||
return typing._UnionGenericAlias(typing.Union, tuple(types))
|
||||
else:
|
||||
return t
|
||||
|
||||
response_type = process_type(return_type)
|
||||
|
||||
if prefix in ["delete", "remove"]:
|
||||
http_method = HTTPMethod.DELETE
|
||||
elif prefix == "post":
|
||||
http_method = HTTPMethod.POST
|
||||
elif prefix == "get":
|
||||
http_method = HTTPMethod.GET
|
||||
elif prefix == "set":
|
||||
http_method = HTTPMethod.PUT
|
||||
elif prefix == "update":
|
||||
http_method = HTTPMethod.PATCH
|
||||
else:
|
||||
request_params.append((param_name, param_type))
|
||||
raise ValidationError(f"unknown prefix {prefix}")
|
||||
|
||||
# check if function has explicit return type
|
||||
if signature.return_annotation is inspect.Signature.empty:
|
||||
raise ValidationError(
|
||||
f"function '{func_name}' has no return type annotation"
|
||||
)
|
||||
|
||||
return_type = _get_annotation_type(signature.return_annotation, func_ref)
|
||||
|
||||
# operations that produce events are labeled as Generator[YieldType, SendType, ReturnType]
|
||||
# where YieldType is the event type, SendType is None, and ReturnType is the immediate response type to the request
|
||||
if typing.get_origin(return_type) is collections.abc.Generator:
|
||||
event_type, send_type, response_type = typing.get_args(return_type)
|
||||
if send_type is not type(None):
|
||||
raise ValidationError(
|
||||
f"function '{func_name}' has a return type Generator[Y,S,R] and therefore looks like an event but has an explicit send type"
|
||||
)
|
||||
else:
|
||||
event_type = None
|
||||
|
||||
def process_type(t):
|
||||
if typing.get_origin(t) is collections.abc.AsyncIterator:
|
||||
# NOTE(ashwin): this is SSE and there is no way to represent it. either we make it a List
|
||||
# or the item type. I am choosing it to be the latter
|
||||
args = typing.get_args(t)
|
||||
return args[0]
|
||||
elif typing.get_origin(t) is typing.Union:
|
||||
types = [process_type(a) for a in typing.get_args(t)]
|
||||
return typing._UnionGenericAlias(typing.Union, tuple(types))
|
||||
else:
|
||||
return t
|
||||
|
||||
response_type = process_type(return_type)
|
||||
|
||||
if prefix in ["delete", "remove"]:
|
||||
http_method = HTTPMethod.DELETE
|
||||
elif prefix == "post":
|
||||
http_method = HTTPMethod.POST
|
||||
elif prefix == "get":
|
||||
http_method = HTTPMethod.GET
|
||||
elif prefix == "set":
|
||||
http_method = HTTPMethod.PUT
|
||||
elif prefix == "update":
|
||||
http_method = HTTPMethod.PATCH
|
||||
else:
|
||||
raise ValidationError(f"unknown prefix {prefix}")
|
||||
|
||||
result.append(
|
||||
EndpointOperation(
|
||||
# Create an EndpointOperation for this specific webmethod
|
||||
operation = EndpointOperation(
|
||||
defining_class=_get_defining_class(func_name, endpoint),
|
||||
name=operation_name,
|
||||
func_name=func_name,
|
||||
|
|
@ -354,7 +358,10 @@ def get_endpoint_operations(
|
|||
request_examples=request_examples if use_examples else None,
|
||||
response_examples=response_examples if use_examples else None,
|
||||
)
|
||||
)
|
||||
|
||||
# Store the specific webmethod with this operation
|
||||
operation.webmethod = webmethod
|
||||
result.append(operation)
|
||||
|
||||
if not result:
|
||||
raise ValidationError(f"no eligible endpoint operations in type {endpoint}")
|
||||
|
|
|
|||
653
docs/static/llama-stack-spec.html
vendored
653
docs/static/llama-stack-spec.html
vendored
|
|
@ -175,6 +175,43 @@
|
|||
}
|
||||
}
|
||||
},
|
||||
"/v1alpha/post-training/job/cancel": {
|
||||
"post": {
|
||||
"responses": {
|
||||
"200": {
|
||||
"description": "OK"
|
||||
},
|
||||
"400": {
|
||||
"$ref": "#/components/responses/BadRequest400"
|
||||
},
|
||||
"429": {
|
||||
"$ref": "#/components/responses/TooManyRequests429"
|
||||
},
|
||||
"500": {
|
||||
"$ref": "#/components/responses/InternalServerError500"
|
||||
},
|
||||
"default": {
|
||||
"$ref": "#/components/responses/DefaultError"
|
||||
}
|
||||
},
|
||||
"tags": [
|
||||
"PostTraining (Coming Soon)"
|
||||
],
|
||||
"summary": "Cancel a training job.",
|
||||
"description": "Cancel a training job.",
|
||||
"parameters": [],
|
||||
"requestBody": {
|
||||
"content": {
|
||||
"application/json": {
|
||||
"schema": {
|
||||
"$ref": "#/components/schemas/CancelTrainingJobRequest"
|
||||
}
|
||||
}
|
||||
},
|
||||
"required": true
|
||||
}
|
||||
}
|
||||
},
|
||||
"/v1/post-training/job/cancel": {
|
||||
"post": {
|
||||
"responses": {
|
||||
|
|
@ -1179,6 +1216,60 @@
|
|||
}
|
||||
}
|
||||
},
|
||||
"/v1alpha/eval/benchmarks/{benchmark_id}/evaluations": {
|
||||
"post": {
|
||||
"responses": {
|
||||
"200": {
|
||||
"description": "EvaluateResponse object containing generations and scores.",
|
||||
"content": {
|
||||
"application/json": {
|
||||
"schema": {
|
||||
"$ref": "#/components/schemas/EvaluateResponse"
|
||||
}
|
||||
}
|
||||
}
|
||||
},
|
||||
"400": {
|
||||
"$ref": "#/components/responses/BadRequest400"
|
||||
},
|
||||
"429": {
|
||||
"$ref": "#/components/responses/TooManyRequests429"
|
||||
},
|
||||
"500": {
|
||||
"$ref": "#/components/responses/InternalServerError500"
|
||||
},
|
||||
"default": {
|
||||
"$ref": "#/components/responses/DefaultError"
|
||||
}
|
||||
},
|
||||
"tags": [
|
||||
"Eval"
|
||||
],
|
||||
"summary": "Evaluate a list of rows on a benchmark.",
|
||||
"description": "Evaluate a list of rows on a benchmark.",
|
||||
"parameters": [
|
||||
{
|
||||
"name": "benchmark_id",
|
||||
"in": "path",
|
||||
"description": "The ID of the benchmark to run the evaluation on.",
|
||||
"required": true,
|
||||
"schema": {
|
||||
"type": "string"
|
||||
}
|
||||
}
|
||||
],
|
||||
"requestBody": {
|
||||
"content": {
|
||||
"application/json": {
|
||||
"schema": {
|
||||
"$ref": "#/components/schemas/EvaluateRowsRequest"
|
||||
}
|
||||
}
|
||||
},
|
||||
"required": true
|
||||
}
|
||||
}
|
||||
},
|
||||
"/v1/eval/benchmarks/{benchmark_id}/evaluations": {
|
||||
"post": {
|
||||
"responses": {
|
||||
|
|
@ -1366,6 +1457,85 @@
|
|||
]
|
||||
}
|
||||
},
|
||||
"/v1alpha/eval/benchmarks/{benchmark_id}": {
|
||||
"get": {
|
||||
"responses": {
|
||||
"200": {
|
||||
"description": "A Benchmark.",
|
||||
"content": {
|
||||
"application/json": {
|
||||
"schema": {
|
||||
"$ref": "#/components/schemas/Benchmark"
|
||||
}
|
||||
}
|
||||
}
|
||||
},
|
||||
"400": {
|
||||
"$ref": "#/components/responses/BadRequest400"
|
||||
},
|
||||
"429": {
|
||||
"$ref": "#/components/responses/TooManyRequests429"
|
||||
},
|
||||
"500": {
|
||||
"$ref": "#/components/responses/InternalServerError500"
|
||||
},
|
||||
"default": {
|
||||
"$ref": "#/components/responses/DefaultError"
|
||||
}
|
||||
},
|
||||
"tags": [
|
||||
"Benchmarks"
|
||||
],
|
||||
"summary": "Get a benchmark by its ID.",
|
||||
"description": "Get a benchmark by its ID.",
|
||||
"parameters": [
|
||||
{
|
||||
"name": "benchmark_id",
|
||||
"in": "path",
|
||||
"description": "The ID of the benchmark to get.",
|
||||
"required": true,
|
||||
"schema": {
|
||||
"type": "string"
|
||||
}
|
||||
}
|
||||
]
|
||||
},
|
||||
"delete": {
|
||||
"responses": {
|
||||
"200": {
|
||||
"description": "OK"
|
||||
},
|
||||
"400": {
|
||||
"$ref": "#/components/responses/BadRequest400"
|
||||
},
|
||||
"429": {
|
||||
"$ref": "#/components/responses/TooManyRequests429"
|
||||
},
|
||||
"500": {
|
||||
"$ref": "#/components/responses/InternalServerError500"
|
||||
},
|
||||
"default": {
|
||||
"$ref": "#/components/responses/DefaultError"
|
||||
}
|
||||
},
|
||||
"tags": [
|
||||
"Benchmarks"
|
||||
],
|
||||
"summary": "Unregister a benchmark.",
|
||||
"description": "Unregister a benchmark.",
|
||||
"parameters": [
|
||||
{
|
||||
"name": "benchmark_id",
|
||||
"in": "path",
|
||||
"description": "The ID of the benchmark to unregister.",
|
||||
"required": true,
|
||||
"schema": {
|
||||
"type": "string"
|
||||
}
|
||||
}
|
||||
]
|
||||
}
|
||||
},
|
||||
"/v1/eval/benchmarks/{benchmark_id}": {
|
||||
"get": {
|
||||
"responses": {
|
||||
|
|
@ -2079,6 +2249,50 @@
|
|||
]
|
||||
}
|
||||
},
|
||||
"/v1alpha/post-training/job/artifacts": {
|
||||
"get": {
|
||||
"responses": {
|
||||
"200": {
|
||||
"description": "A PostTrainingJobArtifactsResponse.",
|
||||
"content": {
|
||||
"application/json": {
|
||||
"schema": {
|
||||
"$ref": "#/components/schemas/PostTrainingJobArtifactsResponse"
|
||||
}
|
||||
}
|
||||
}
|
||||
},
|
||||
"400": {
|
||||
"$ref": "#/components/responses/BadRequest400"
|
||||
},
|
||||
"429": {
|
||||
"$ref": "#/components/responses/TooManyRequests429"
|
||||
},
|
||||
"500": {
|
||||
"$ref": "#/components/responses/InternalServerError500"
|
||||
},
|
||||
"default": {
|
||||
"$ref": "#/components/responses/DefaultError"
|
||||
}
|
||||
},
|
||||
"tags": [
|
||||
"PostTraining (Coming Soon)"
|
||||
],
|
||||
"summary": "Get the artifacts of a training job.",
|
||||
"description": "Get the artifacts of a training job.",
|
||||
"parameters": [
|
||||
{
|
||||
"name": "job_uuid",
|
||||
"in": "query",
|
||||
"description": "The UUID of the job to get the artifacts of.",
|
||||
"required": true,
|
||||
"schema": {
|
||||
"type": "string"
|
||||
}
|
||||
}
|
||||
]
|
||||
}
|
||||
},
|
||||
"/v1/post-training/job/artifacts": {
|
||||
"get": {
|
||||
"responses": {
|
||||
|
|
@ -2123,6 +2337,50 @@
|
|||
]
|
||||
}
|
||||
},
|
||||
"/v1alpha/post-training/job/status": {
|
||||
"get": {
|
||||
"responses": {
|
||||
"200": {
|
||||
"description": "A PostTrainingJobStatusResponse.",
|
||||
"content": {
|
||||
"application/json": {
|
||||
"schema": {
|
||||
"$ref": "#/components/schemas/PostTrainingJobStatusResponse"
|
||||
}
|
||||
}
|
||||
}
|
||||
},
|
||||
"400": {
|
||||
"$ref": "#/components/responses/BadRequest400"
|
||||
},
|
||||
"429": {
|
||||
"$ref": "#/components/responses/TooManyRequests429"
|
||||
},
|
||||
"500": {
|
||||
"$ref": "#/components/responses/InternalServerError500"
|
||||
},
|
||||
"default": {
|
||||
"$ref": "#/components/responses/DefaultError"
|
||||
}
|
||||
},
|
||||
"tags": [
|
||||
"PostTraining (Coming Soon)"
|
||||
],
|
||||
"summary": "Get the status of a training job.",
|
||||
"description": "Get the status of a training job.",
|
||||
"parameters": [
|
||||
{
|
||||
"name": "job_uuid",
|
||||
"in": "query",
|
||||
"description": "The UUID of the job to get the status of.",
|
||||
"required": true,
|
||||
"schema": {
|
||||
"type": "string"
|
||||
}
|
||||
}
|
||||
]
|
||||
}
|
||||
},
|
||||
"/v1/post-training/job/status": {
|
||||
"get": {
|
||||
"responses": {
|
||||
|
|
@ -2167,6 +2425,40 @@
|
|||
]
|
||||
}
|
||||
},
|
||||
"/v1alpha/post-training/jobs": {
|
||||
"get": {
|
||||
"responses": {
|
||||
"200": {
|
||||
"description": "A ListPostTrainingJobsResponse.",
|
||||
"content": {
|
||||
"application/json": {
|
||||
"schema": {
|
||||
"$ref": "#/components/schemas/ListPostTrainingJobsResponse"
|
||||
}
|
||||
}
|
||||
}
|
||||
},
|
||||
"400": {
|
||||
"$ref": "#/components/responses/BadRequest400"
|
||||
},
|
||||
"429": {
|
||||
"$ref": "#/components/responses/TooManyRequests429"
|
||||
},
|
||||
"500": {
|
||||
"$ref": "#/components/responses/InternalServerError500"
|
||||
},
|
||||
"default": {
|
||||
"$ref": "#/components/responses/DefaultError"
|
||||
}
|
||||
},
|
||||
"tags": [
|
||||
"PostTraining (Coming Soon)"
|
||||
],
|
||||
"summary": "Get all training jobs.",
|
||||
"description": "Get all training jobs.",
|
||||
"parameters": []
|
||||
}
|
||||
},
|
||||
"/v1/post-training/jobs": {
|
||||
"get": {
|
||||
"responses": {
|
||||
|
|
@ -2538,6 +2830,103 @@
|
|||
]
|
||||
}
|
||||
},
|
||||
"/v1alpha/eval/benchmarks/{benchmark_id}/jobs/{job_id}": {
|
||||
"get": {
|
||||
"responses": {
|
||||
"200": {
|
||||
"description": "The status of the evaluation job.",
|
||||
"content": {
|
||||
"application/json": {
|
||||
"schema": {
|
||||
"$ref": "#/components/schemas/Job"
|
||||
}
|
||||
}
|
||||
}
|
||||
},
|
||||
"400": {
|
||||
"$ref": "#/components/responses/BadRequest400"
|
||||
},
|
||||
"429": {
|
||||
"$ref": "#/components/responses/TooManyRequests429"
|
||||
},
|
||||
"500": {
|
||||
"$ref": "#/components/responses/InternalServerError500"
|
||||
},
|
||||
"default": {
|
||||
"$ref": "#/components/responses/DefaultError"
|
||||
}
|
||||
},
|
||||
"tags": [
|
||||
"Eval"
|
||||
],
|
||||
"summary": "Get the status of a job.",
|
||||
"description": "Get the status of a job.",
|
||||
"parameters": [
|
||||
{
|
||||
"name": "benchmark_id",
|
||||
"in": "path",
|
||||
"description": "The ID of the benchmark to run the evaluation on.",
|
||||
"required": true,
|
||||
"schema": {
|
||||
"type": "string"
|
||||
}
|
||||
},
|
||||
{
|
||||
"name": "job_id",
|
||||
"in": "path",
|
||||
"description": "The ID of the job to get the status of.",
|
||||
"required": true,
|
||||
"schema": {
|
||||
"type": "string"
|
||||
}
|
||||
}
|
||||
]
|
||||
},
|
||||
"delete": {
|
||||
"responses": {
|
||||
"200": {
|
||||
"description": "OK"
|
||||
},
|
||||
"400": {
|
||||
"$ref": "#/components/responses/BadRequest400"
|
||||
},
|
||||
"429": {
|
||||
"$ref": "#/components/responses/TooManyRequests429"
|
||||
},
|
||||
"500": {
|
||||
"$ref": "#/components/responses/InternalServerError500"
|
||||
},
|
||||
"default": {
|
||||
"$ref": "#/components/responses/DefaultError"
|
||||
}
|
||||
},
|
||||
"tags": [
|
||||
"Eval"
|
||||
],
|
||||
"summary": "Cancel a job.",
|
||||
"description": "Cancel a job.",
|
||||
"parameters": [
|
||||
{
|
||||
"name": "benchmark_id",
|
||||
"in": "path",
|
||||
"description": "The ID of the benchmark to run the evaluation on.",
|
||||
"required": true,
|
||||
"schema": {
|
||||
"type": "string"
|
||||
}
|
||||
},
|
||||
{
|
||||
"name": "job_id",
|
||||
"in": "path",
|
||||
"description": "The ID of the job to cancel.",
|
||||
"required": true,
|
||||
"schema": {
|
||||
"type": "string"
|
||||
}
|
||||
}
|
||||
]
|
||||
}
|
||||
},
|
||||
"/v1/eval/benchmarks/{benchmark_id}/jobs/{job_id}": {
|
||||
"get": {
|
||||
"responses": {
|
||||
|
|
@ -2635,6 +3024,59 @@
|
|||
]
|
||||
}
|
||||
},
|
||||
"/v1alpha/eval/benchmarks/{benchmark_id}/jobs/{job_id}/result": {
|
||||
"get": {
|
||||
"responses": {
|
||||
"200": {
|
||||
"description": "The result of the job.",
|
||||
"content": {
|
||||
"application/json": {
|
||||
"schema": {
|
||||
"$ref": "#/components/schemas/EvaluateResponse"
|
||||
}
|
||||
}
|
||||
}
|
||||
},
|
||||
"400": {
|
||||
"$ref": "#/components/responses/BadRequest400"
|
||||
},
|
||||
"429": {
|
||||
"$ref": "#/components/responses/TooManyRequests429"
|
||||
},
|
||||
"500": {
|
||||
"$ref": "#/components/responses/InternalServerError500"
|
||||
},
|
||||
"default": {
|
||||
"$ref": "#/components/responses/DefaultError"
|
||||
}
|
||||
},
|
||||
"tags": [
|
||||
"Eval"
|
||||
],
|
||||
"summary": "Get the result of a job.",
|
||||
"description": "Get the result of a job.",
|
||||
"parameters": [
|
||||
{
|
||||
"name": "benchmark_id",
|
||||
"in": "path",
|
||||
"description": "The ID of the benchmark to run the evaluation on.",
|
||||
"required": true,
|
||||
"schema": {
|
||||
"type": "string"
|
||||
}
|
||||
},
|
||||
{
|
||||
"name": "job_id",
|
||||
"in": "path",
|
||||
"description": "The ID of the job to get the result of.",
|
||||
"required": true,
|
||||
"schema": {
|
||||
"type": "string"
|
||||
}
|
||||
}
|
||||
]
|
||||
}
|
||||
},
|
||||
"/v1/eval/benchmarks/{benchmark_id}/jobs/{job_id}/result": {
|
||||
"get": {
|
||||
"responses": {
|
||||
|
|
@ -2750,6 +3192,75 @@
|
|||
]
|
||||
}
|
||||
},
|
||||
"/v1alpha/eval/benchmarks": {
|
||||
"get": {
|
||||
"responses": {
|
||||
"200": {
|
||||
"description": "A ListBenchmarksResponse.",
|
||||
"content": {
|
||||
"application/json": {
|
||||
"schema": {
|
||||
"$ref": "#/components/schemas/ListBenchmarksResponse"
|
||||
}
|
||||
}
|
||||
}
|
||||
},
|
||||
"400": {
|
||||
"$ref": "#/components/responses/BadRequest400"
|
||||
},
|
||||
"429": {
|
||||
"$ref": "#/components/responses/TooManyRequests429"
|
||||
},
|
||||
"500": {
|
||||
"$ref": "#/components/responses/InternalServerError500"
|
||||
},
|
||||
"default": {
|
||||
"$ref": "#/components/responses/DefaultError"
|
||||
}
|
||||
},
|
||||
"tags": [
|
||||
"Benchmarks"
|
||||
],
|
||||
"summary": "List all benchmarks.",
|
||||
"description": "List all benchmarks.",
|
||||
"parameters": []
|
||||
},
|
||||
"post": {
|
||||
"responses": {
|
||||
"200": {
|
||||
"description": "OK"
|
||||
},
|
||||
"400": {
|
||||
"$ref": "#/components/responses/BadRequest400"
|
||||
},
|
||||
"429": {
|
||||
"$ref": "#/components/responses/TooManyRequests429"
|
||||
},
|
||||
"500": {
|
||||
"$ref": "#/components/responses/InternalServerError500"
|
||||
},
|
||||
"default": {
|
||||
"$ref": "#/components/responses/DefaultError"
|
||||
}
|
||||
},
|
||||
"tags": [
|
||||
"Benchmarks"
|
||||
],
|
||||
"summary": "Register a benchmark.",
|
||||
"description": "Register a benchmark.",
|
||||
"parameters": [],
|
||||
"requestBody": {
|
||||
"content": {
|
||||
"application/json": {
|
||||
"schema": {
|
||||
"$ref": "#/components/schemas/RegisterBenchmarkRequest"
|
||||
}
|
||||
}
|
||||
},
|
||||
"required": true
|
||||
}
|
||||
}
|
||||
},
|
||||
"/v1/eval/benchmarks": {
|
||||
"get": {
|
||||
"responses": {
|
||||
|
|
@ -4783,6 +5294,50 @@
|
|||
}
|
||||
}
|
||||
},
|
||||
"/v1alpha/post-training/preference-optimize": {
|
||||
"post": {
|
||||
"responses": {
|
||||
"200": {
|
||||
"description": "A PostTrainingJob.",
|
||||
"content": {
|
||||
"application/json": {
|
||||
"schema": {
|
||||
"$ref": "#/components/schemas/PostTrainingJob"
|
||||
}
|
||||
}
|
||||
}
|
||||
},
|
||||
"400": {
|
||||
"$ref": "#/components/responses/BadRequest400"
|
||||
},
|
||||
"429": {
|
||||
"$ref": "#/components/responses/TooManyRequests429"
|
||||
},
|
||||
"500": {
|
||||
"$ref": "#/components/responses/InternalServerError500"
|
||||
},
|
||||
"default": {
|
||||
"$ref": "#/components/responses/DefaultError"
|
||||
}
|
||||
},
|
||||
"tags": [
|
||||
"PostTraining (Coming Soon)"
|
||||
],
|
||||
"summary": "Run preference optimization of a model.",
|
||||
"description": "Run preference optimization of a model.",
|
||||
"parameters": [],
|
||||
"requestBody": {
|
||||
"content": {
|
||||
"application/json": {
|
||||
"schema": {
|
||||
"$ref": "#/components/schemas/PreferenceOptimizeRequest"
|
||||
}
|
||||
}
|
||||
},
|
||||
"required": true
|
||||
}
|
||||
}
|
||||
},
|
||||
"/v1/post-training/preference-optimize": {
|
||||
"post": {
|
||||
"responses": {
|
||||
|
|
@ -5178,6 +5733,60 @@
|
|||
}
|
||||
}
|
||||
},
|
||||
"/v1alpha/eval/benchmarks/{benchmark_id}/jobs": {
|
||||
"post": {
|
||||
"responses": {
|
||||
"200": {
|
||||
"description": "The job that was created to run the evaluation.",
|
||||
"content": {
|
||||
"application/json": {
|
||||
"schema": {
|
||||
"$ref": "#/components/schemas/Job"
|
||||
}
|
||||
}
|
||||
}
|
||||
},
|
||||
"400": {
|
||||
"$ref": "#/components/responses/BadRequest400"
|
||||
},
|
||||
"429": {
|
||||
"$ref": "#/components/responses/TooManyRequests429"
|
||||
},
|
||||
"500": {
|
||||
"$ref": "#/components/responses/InternalServerError500"
|
||||
},
|
||||
"default": {
|
||||
"$ref": "#/components/responses/DefaultError"
|
||||
}
|
||||
},
|
||||
"tags": [
|
||||
"Eval"
|
||||
],
|
||||
"summary": "Run an evaluation on a benchmark.",
|
||||
"description": "Run an evaluation on a benchmark.",
|
||||
"parameters": [
|
||||
{
|
||||
"name": "benchmark_id",
|
||||
"in": "path",
|
||||
"description": "The ID of the benchmark to run the evaluation on.",
|
||||
"required": true,
|
||||
"schema": {
|
||||
"type": "string"
|
||||
}
|
||||
}
|
||||
],
|
||||
"requestBody": {
|
||||
"content": {
|
||||
"application/json": {
|
||||
"schema": {
|
||||
"$ref": "#/components/schemas/RunEvalRequest"
|
||||
}
|
||||
}
|
||||
},
|
||||
"required": true
|
||||
}
|
||||
}
|
||||
},
|
||||
"/v1/eval/benchmarks/{benchmark_id}/jobs": {
|
||||
"post": {
|
||||
"responses": {
|
||||
|
|
@ -5499,6 +6108,50 @@
|
|||
}
|
||||
}
|
||||
},
|
||||
"/v1alpha/post-training/supervised-fine-tune": {
|
||||
"post": {
|
||||
"responses": {
|
||||
"200": {
|
||||
"description": "A PostTrainingJob.",
|
||||
"content": {
|
||||
"application/json": {
|
||||
"schema": {
|
||||
"$ref": "#/components/schemas/PostTrainingJob"
|
||||
}
|
||||
}
|
||||
}
|
||||
},
|
||||
"400": {
|
||||
"$ref": "#/components/responses/BadRequest400"
|
||||
},
|
||||
"429": {
|
||||
"$ref": "#/components/responses/TooManyRequests429"
|
||||
},
|
||||
"500": {
|
||||
"$ref": "#/components/responses/InternalServerError500"
|
||||
},
|
||||
"default": {
|
||||
"$ref": "#/components/responses/DefaultError"
|
||||
}
|
||||
},
|
||||
"tags": [
|
||||
"PostTraining (Coming Soon)"
|
||||
],
|
||||
"summary": "Run supervised fine-tuning of a model.",
|
||||
"description": "Run supervised fine-tuning of a model.",
|
||||
"parameters": [],
|
||||
"requestBody": {
|
||||
"content": {
|
||||
"application/json": {
|
||||
"schema": {
|
||||
"$ref": "#/components/schemas/SupervisedFineTuneRequest"
|
||||
}
|
||||
}
|
||||
},
|
||||
"required": true
|
||||
}
|
||||
}
|
||||
},
|
||||
"/v1/post-training/supervised-fine-tune": {
|
||||
"post": {
|
||||
"responses": {
|
||||
|
|
|
|||
458
docs/static/llama-stack-spec.yaml
vendored
458
docs/static/llama-stack-spec.yaml
vendored
|
|
@ -109,6 +109,32 @@ paths:
|
|||
schema:
|
||||
$ref: '#/components/schemas/BatchCompletionRequest'
|
||||
required: true
|
||||
/v1alpha/post-training/job/cancel:
|
||||
post:
|
||||
responses:
|
||||
'200':
|
||||
description: OK
|
||||
'400':
|
||||
$ref: '#/components/responses/BadRequest400'
|
||||
'429':
|
||||
$ref: >-
|
||||
#/components/responses/TooManyRequests429
|
||||
'500':
|
||||
$ref: >-
|
||||
#/components/responses/InternalServerError500
|
||||
default:
|
||||
$ref: '#/components/responses/DefaultError'
|
||||
tags:
|
||||
- PostTraining (Coming Soon)
|
||||
summary: Cancel a training job.
|
||||
description: Cancel a training job.
|
||||
parameters: []
|
||||
requestBody:
|
||||
content:
|
||||
application/json:
|
||||
schema:
|
||||
$ref: '#/components/schemas/CancelTrainingJobRequest'
|
||||
required: true
|
||||
/v1/post-training/job/cancel:
|
||||
post:
|
||||
responses:
|
||||
|
|
@ -832,6 +858,44 @@ paths:
|
|||
schema:
|
||||
$ref: '#/components/schemas/EmbeddingsRequest'
|
||||
required: true
|
||||
/v1alpha/eval/benchmarks/{benchmark_id}/evaluations:
|
||||
post:
|
||||
responses:
|
||||
'200':
|
||||
description: >-
|
||||
EvaluateResponse object containing generations and scores.
|
||||
content:
|
||||
application/json:
|
||||
schema:
|
||||
$ref: '#/components/schemas/EvaluateResponse'
|
||||
'400':
|
||||
$ref: '#/components/responses/BadRequest400'
|
||||
'429':
|
||||
$ref: >-
|
||||
#/components/responses/TooManyRequests429
|
||||
'500':
|
||||
$ref: >-
|
||||
#/components/responses/InternalServerError500
|
||||
default:
|
||||
$ref: '#/components/responses/DefaultError'
|
||||
tags:
|
||||
- Eval
|
||||
summary: Evaluate a list of rows on a benchmark.
|
||||
description: Evaluate a list of rows on a benchmark.
|
||||
parameters:
|
||||
- name: benchmark_id
|
||||
in: path
|
||||
description: >-
|
||||
The ID of the benchmark to run the evaluation on.
|
||||
required: true
|
||||
schema:
|
||||
type: string
|
||||
requestBody:
|
||||
content:
|
||||
application/json:
|
||||
schema:
|
||||
$ref: '#/components/schemas/EvaluateRowsRequest'
|
||||
required: true
|
||||
/v1/eval/benchmarks/{benchmark_id}/evaluations:
|
||||
post:
|
||||
responses:
|
||||
|
|
@ -962,6 +1026,61 @@ paths:
|
|||
required: true
|
||||
schema:
|
||||
type: string
|
||||
/v1alpha/eval/benchmarks/{benchmark_id}:
|
||||
get:
|
||||
responses:
|
||||
'200':
|
||||
description: A Benchmark.
|
||||
content:
|
||||
application/json:
|
||||
schema:
|
||||
$ref: '#/components/schemas/Benchmark'
|
||||
'400':
|
||||
$ref: '#/components/responses/BadRequest400'
|
||||
'429':
|
||||
$ref: >-
|
||||
#/components/responses/TooManyRequests429
|
||||
'500':
|
||||
$ref: >-
|
||||
#/components/responses/InternalServerError500
|
||||
default:
|
||||
$ref: '#/components/responses/DefaultError'
|
||||
tags:
|
||||
- Benchmarks
|
||||
summary: Get a benchmark by its ID.
|
||||
description: Get a benchmark by its ID.
|
||||
parameters:
|
||||
- name: benchmark_id
|
||||
in: path
|
||||
description: The ID of the benchmark to get.
|
||||
required: true
|
||||
schema:
|
||||
type: string
|
||||
delete:
|
||||
responses:
|
||||
'200':
|
||||
description: OK
|
||||
'400':
|
||||
$ref: '#/components/responses/BadRequest400'
|
||||
'429':
|
||||
$ref: >-
|
||||
#/components/responses/TooManyRequests429
|
||||
'500':
|
||||
$ref: >-
|
||||
#/components/responses/InternalServerError500
|
||||
default:
|
||||
$ref: '#/components/responses/DefaultError'
|
||||
tags:
|
||||
- Benchmarks
|
||||
summary: Unregister a benchmark.
|
||||
description: Unregister a benchmark.
|
||||
parameters:
|
||||
- name: benchmark_id
|
||||
in: path
|
||||
description: The ID of the benchmark to unregister.
|
||||
required: true
|
||||
schema:
|
||||
type: string
|
||||
/v1/eval/benchmarks/{benchmark_id}:
|
||||
get:
|
||||
responses:
|
||||
|
|
@ -1458,6 +1577,37 @@ paths:
|
|||
required: true
|
||||
schema:
|
||||
type: string
|
||||
/v1alpha/post-training/job/artifacts:
|
||||
get:
|
||||
responses:
|
||||
'200':
|
||||
description: A PostTrainingJobArtifactsResponse.
|
||||
content:
|
||||
application/json:
|
||||
schema:
|
||||
$ref: '#/components/schemas/PostTrainingJobArtifactsResponse'
|
||||
'400':
|
||||
$ref: '#/components/responses/BadRequest400'
|
||||
'429':
|
||||
$ref: >-
|
||||
#/components/responses/TooManyRequests429
|
||||
'500':
|
||||
$ref: >-
|
||||
#/components/responses/InternalServerError500
|
||||
default:
|
||||
$ref: '#/components/responses/DefaultError'
|
||||
tags:
|
||||
- PostTraining (Coming Soon)
|
||||
summary: Get the artifacts of a training job.
|
||||
description: Get the artifacts of a training job.
|
||||
parameters:
|
||||
- name: job_uuid
|
||||
in: query
|
||||
description: >-
|
||||
The UUID of the job to get the artifacts of.
|
||||
required: true
|
||||
schema:
|
||||
type: string
|
||||
/v1/post-training/job/artifacts:
|
||||
get:
|
||||
responses:
|
||||
|
|
@ -1489,6 +1639,37 @@ paths:
|
|||
required: true
|
||||
schema:
|
||||
type: string
|
||||
/v1alpha/post-training/job/status:
|
||||
get:
|
||||
responses:
|
||||
'200':
|
||||
description: A PostTrainingJobStatusResponse.
|
||||
content:
|
||||
application/json:
|
||||
schema:
|
||||
$ref: '#/components/schemas/PostTrainingJobStatusResponse'
|
||||
'400':
|
||||
$ref: '#/components/responses/BadRequest400'
|
||||
'429':
|
||||
$ref: >-
|
||||
#/components/responses/TooManyRequests429
|
||||
'500':
|
||||
$ref: >-
|
||||
#/components/responses/InternalServerError500
|
||||
default:
|
||||
$ref: '#/components/responses/DefaultError'
|
||||
tags:
|
||||
- PostTraining (Coming Soon)
|
||||
summary: Get the status of a training job.
|
||||
description: Get the status of a training job.
|
||||
parameters:
|
||||
- name: job_uuid
|
||||
in: query
|
||||
description: >-
|
||||
The UUID of the job to get the status of.
|
||||
required: true
|
||||
schema:
|
||||
type: string
|
||||
/v1/post-training/job/status:
|
||||
get:
|
||||
responses:
|
||||
|
|
@ -1520,6 +1701,30 @@ paths:
|
|||
required: true
|
||||
schema:
|
||||
type: string
|
||||
/v1alpha/post-training/jobs:
|
||||
get:
|
||||
responses:
|
||||
'200':
|
||||
description: A ListPostTrainingJobsResponse.
|
||||
content:
|
||||
application/json:
|
||||
schema:
|
||||
$ref: '#/components/schemas/ListPostTrainingJobsResponse'
|
||||
'400':
|
||||
$ref: '#/components/responses/BadRequest400'
|
||||
'429':
|
||||
$ref: >-
|
||||
#/components/responses/TooManyRequests429
|
||||
'500':
|
||||
$ref: >-
|
||||
#/components/responses/InternalServerError500
|
||||
default:
|
||||
$ref: '#/components/responses/DefaultError'
|
||||
tags:
|
||||
- PostTraining (Coming Soon)
|
||||
summary: Get all training jobs.
|
||||
description: Get all training jobs.
|
||||
parameters: []
|
||||
/v1/post-training/jobs:
|
||||
get:
|
||||
responses:
|
||||
|
|
@ -1804,6 +2009,75 @@ paths:
|
|||
required: false
|
||||
schema:
|
||||
type: integer
|
||||
/v1alpha/eval/benchmarks/{benchmark_id}/jobs/{job_id}:
|
||||
get:
|
||||
responses:
|
||||
'200':
|
||||
description: The status of the evaluation job.
|
||||
content:
|
||||
application/json:
|
||||
schema:
|
||||
$ref: '#/components/schemas/Job'
|
||||
'400':
|
||||
$ref: '#/components/responses/BadRequest400'
|
||||
'429':
|
||||
$ref: >-
|
||||
#/components/responses/TooManyRequests429
|
||||
'500':
|
||||
$ref: >-
|
||||
#/components/responses/InternalServerError500
|
||||
default:
|
||||
$ref: '#/components/responses/DefaultError'
|
||||
tags:
|
||||
- Eval
|
||||
summary: Get the status of a job.
|
||||
description: Get the status of a job.
|
||||
parameters:
|
||||
- name: benchmark_id
|
||||
in: path
|
||||
description: >-
|
||||
The ID of the benchmark to run the evaluation on.
|
||||
required: true
|
||||
schema:
|
||||
type: string
|
||||
- name: job_id
|
||||
in: path
|
||||
description: The ID of the job to get the status of.
|
||||
required: true
|
||||
schema:
|
||||
type: string
|
||||
delete:
|
||||
responses:
|
||||
'200':
|
||||
description: OK
|
||||
'400':
|
||||
$ref: '#/components/responses/BadRequest400'
|
||||
'429':
|
||||
$ref: >-
|
||||
#/components/responses/TooManyRequests429
|
||||
'500':
|
||||
$ref: >-
|
||||
#/components/responses/InternalServerError500
|
||||
default:
|
||||
$ref: '#/components/responses/DefaultError'
|
||||
tags:
|
||||
- Eval
|
||||
summary: Cancel a job.
|
||||
description: Cancel a job.
|
||||
parameters:
|
||||
- name: benchmark_id
|
||||
in: path
|
||||
description: >-
|
||||
The ID of the benchmark to run the evaluation on.
|
||||
required: true
|
||||
schema:
|
||||
type: string
|
||||
- name: job_id
|
||||
in: path
|
||||
description: The ID of the job to cancel.
|
||||
required: true
|
||||
schema:
|
||||
type: string
|
||||
/v1/eval/benchmarks/{benchmark_id}/jobs/{job_id}:
|
||||
get:
|
||||
responses:
|
||||
|
|
@ -1873,6 +2147,43 @@ paths:
|
|||
required: true
|
||||
schema:
|
||||
type: string
|
||||
/v1alpha/eval/benchmarks/{benchmark_id}/jobs/{job_id}/result:
|
||||
get:
|
||||
responses:
|
||||
'200':
|
||||
description: The result of the job.
|
||||
content:
|
||||
application/json:
|
||||
schema:
|
||||
$ref: '#/components/schemas/EvaluateResponse'
|
||||
'400':
|
||||
$ref: '#/components/responses/BadRequest400'
|
||||
'429':
|
||||
$ref: >-
|
||||
#/components/responses/TooManyRequests429
|
||||
'500':
|
||||
$ref: >-
|
||||
#/components/responses/InternalServerError500
|
||||
default:
|
||||
$ref: '#/components/responses/DefaultError'
|
||||
tags:
|
||||
- Eval
|
||||
summary: Get the result of a job.
|
||||
description: Get the result of a job.
|
||||
parameters:
|
||||
- name: benchmark_id
|
||||
in: path
|
||||
description: >-
|
||||
The ID of the benchmark to run the evaluation on.
|
||||
required: true
|
||||
schema:
|
||||
type: string
|
||||
- name: job_id
|
||||
in: path
|
||||
description: The ID of the job to get the result of.
|
||||
required: true
|
||||
schema:
|
||||
type: string
|
||||
/v1/eval/benchmarks/{benchmark_id}/jobs/{job_id}/result:
|
||||
get:
|
||||
responses:
|
||||
|
|
@ -1953,6 +2264,55 @@ paths:
|
|||
required: false
|
||||
schema:
|
||||
type: integer
|
||||
/v1alpha/eval/benchmarks:
|
||||
get:
|
||||
responses:
|
||||
'200':
|
||||
description: A ListBenchmarksResponse.
|
||||
content:
|
||||
application/json:
|
||||
schema:
|
||||
$ref: '#/components/schemas/ListBenchmarksResponse'
|
||||
'400':
|
||||
$ref: '#/components/responses/BadRequest400'
|
||||
'429':
|
||||
$ref: >-
|
||||
#/components/responses/TooManyRequests429
|
||||
'500':
|
||||
$ref: >-
|
||||
#/components/responses/InternalServerError500
|
||||
default:
|
||||
$ref: '#/components/responses/DefaultError'
|
||||
tags:
|
||||
- Benchmarks
|
||||
summary: List all benchmarks.
|
||||
description: List all benchmarks.
|
||||
parameters: []
|
||||
post:
|
||||
responses:
|
||||
'200':
|
||||
description: OK
|
||||
'400':
|
||||
$ref: '#/components/responses/BadRequest400'
|
||||
'429':
|
||||
$ref: >-
|
||||
#/components/responses/TooManyRequests429
|
||||
'500':
|
||||
$ref: >-
|
||||
#/components/responses/InternalServerError500
|
||||
default:
|
||||
$ref: '#/components/responses/DefaultError'
|
||||
tags:
|
||||
- Benchmarks
|
||||
summary: Register a benchmark.
|
||||
description: Register a benchmark.
|
||||
parameters: []
|
||||
requestBody:
|
||||
content:
|
||||
application/json:
|
||||
schema:
|
||||
$ref: '#/components/schemas/RegisterBenchmarkRequest'
|
||||
required: true
|
||||
/v1/eval/benchmarks:
|
||||
get:
|
||||
responses:
|
||||
|
|
@ -3454,6 +3814,36 @@ paths:
|
|||
schema:
|
||||
$ref: '#/components/schemas/OpenaiSearchVectorStoreRequest'
|
||||
required: true
|
||||
/v1alpha/post-training/preference-optimize:
|
||||
post:
|
||||
responses:
|
||||
'200':
|
||||
description: A PostTrainingJob.
|
||||
content:
|
||||
application/json:
|
||||
schema:
|
||||
$ref: '#/components/schemas/PostTrainingJob'
|
||||
'400':
|
||||
$ref: '#/components/responses/BadRequest400'
|
||||
'429':
|
||||
$ref: >-
|
||||
#/components/responses/TooManyRequests429
|
||||
'500':
|
||||
$ref: >-
|
||||
#/components/responses/InternalServerError500
|
||||
default:
|
||||
$ref: '#/components/responses/DefaultError'
|
||||
tags:
|
||||
- PostTraining (Coming Soon)
|
||||
summary: Run preference optimization of a model.
|
||||
description: Run preference optimization of a model.
|
||||
parameters: []
|
||||
requestBody:
|
||||
content:
|
||||
application/json:
|
||||
schema:
|
||||
$ref: '#/components/schemas/PreferenceOptimizeRequest'
|
||||
required: true
|
||||
/v1/post-training/preference-optimize:
|
||||
post:
|
||||
responses:
|
||||
|
|
@ -3735,6 +4125,44 @@ paths:
|
|||
schema:
|
||||
$ref: '#/components/schemas/ResumeAgentTurnRequest'
|
||||
required: true
|
||||
/v1alpha/eval/benchmarks/{benchmark_id}/jobs:
|
||||
post:
|
||||
responses:
|
||||
'200':
|
||||
description: >-
|
||||
The job that was created to run the evaluation.
|
||||
content:
|
||||
application/json:
|
||||
schema:
|
||||
$ref: '#/components/schemas/Job'
|
||||
'400':
|
||||
$ref: '#/components/responses/BadRequest400'
|
||||
'429':
|
||||
$ref: >-
|
||||
#/components/responses/TooManyRequests429
|
||||
'500':
|
||||
$ref: >-
|
||||
#/components/responses/InternalServerError500
|
||||
default:
|
||||
$ref: '#/components/responses/DefaultError'
|
||||
tags:
|
||||
- Eval
|
||||
summary: Run an evaluation on a benchmark.
|
||||
description: Run an evaluation on a benchmark.
|
||||
parameters:
|
||||
- name: benchmark_id
|
||||
in: path
|
||||
description: >-
|
||||
The ID of the benchmark to run the evaluation on.
|
||||
required: true
|
||||
schema:
|
||||
type: string
|
||||
requestBody:
|
||||
content:
|
||||
application/json:
|
||||
schema:
|
||||
$ref: '#/components/schemas/RunEvalRequest'
|
||||
required: true
|
||||
/v1/eval/benchmarks/{benchmark_id}/jobs:
|
||||
post:
|
||||
responses:
|
||||
|
|
@ -3961,6 +4389,36 @@ paths:
|
|||
schema:
|
||||
$ref: '#/components/schemas/SetDefaultVersionRequest'
|
||||
required: true
|
||||
/v1alpha/post-training/supervised-fine-tune:
|
||||
post:
|
||||
responses:
|
||||
'200':
|
||||
description: A PostTrainingJob.
|
||||
content:
|
||||
application/json:
|
||||
schema:
|
||||
$ref: '#/components/schemas/PostTrainingJob'
|
||||
'400':
|
||||
$ref: '#/components/responses/BadRequest400'
|
||||
'429':
|
||||
$ref: >-
|
||||
#/components/responses/TooManyRequests429
|
||||
'500':
|
||||
$ref: >-
|
||||
#/components/responses/InternalServerError500
|
||||
default:
|
||||
$ref: '#/components/responses/DefaultError'
|
||||
tags:
|
||||
- PostTraining (Coming Soon)
|
||||
summary: Run supervised fine-tuning of a model.
|
||||
description: Run supervised fine-tuning of a model.
|
||||
parameters: []
|
||||
requestBody:
|
||||
content:
|
||||
application/json:
|
||||
schema:
|
||||
$ref: '#/components/schemas/SupervisedFineTuneRequest'
|
||||
required: true
|
||||
/v1/post-training/supervised-fine-tune:
|
||||
post:
|
||||
responses:
|
||||
|
|
|
|||
Loading…
Add table
Add a link
Reference in a new issue