mirror of
https://github.com/meta-llama/llama-stack.git
synced 2025-12-03 18:00:36 +00:00
Merge branch 'main' into feat/gunicorn-production-server
This commit is contained in:
Roy Belio
GitHub
commit
9ff881a28a
17 changed files with 439 additions and 11392 deletions
|
|
@ -491,13 +491,6 @@ class Agents(Protocol):
|
|||
|
||||
APIs for creating and interacting with agentic systems."""
|
||||
|
||||
@webmethod(
|
||||
route="/agents",
|
||||
method="POST",
|
||||
descriptive_name="create_agent",
|
||||
deprecated=True,
|
||||
level=LLAMA_STACK_API_V1,
|
||||
)
|
||||
@webmethod(
|
||||
route="/agents",
|
||||
method="POST",
|
||||
|
|
@ -515,13 +508,6 @@ class Agents(Protocol):
|
|||
"""
|
||||
...
|
||||
|
||||
@webmethod(
|
||||
route="/agents/{agent_id}/session/{session_id}/turn",
|
||||
method="POST",
|
||||
descriptive_name="create_agent_turn",
|
||||
deprecated=True,
|
||||
level=LLAMA_STACK_API_V1,
|
||||
)
|
||||
@webmethod(
|
||||
route="/agents/{agent_id}/session/{session_id}/turn",
|
||||
method="POST",
|
||||
|
|
@ -552,13 +538,6 @@ class Agents(Protocol):
|
|||
"""
|
||||
...
|
||||
|
||||
@webmethod(
|
||||
route="/agents/{agent_id}/session/{session_id}/turn/{turn_id}/resume",
|
||||
method="POST",
|
||||
descriptive_name="resume_agent_turn",
|
||||
deprecated=True,
|
||||
level=LLAMA_STACK_API_V1,
|
||||
)
|
||||
@webmethod(
|
||||
route="/agents/{agent_id}/session/{session_id}/turn/{turn_id}/resume",
|
||||
method="POST",
|
||||
|
|
@ -586,12 +565,6 @@ class Agents(Protocol):
|
|||
"""
|
||||
...
|
||||
|
||||
@webmethod(
|
||||
route="/agents/{agent_id}/session/{session_id}/turn/{turn_id}",
|
||||
method="GET",
|
||||
deprecated=True,
|
||||
level=LLAMA_STACK_API_V1,
|
||||
)
|
||||
@webmethod(
|
||||
route="/agents/{agent_id}/session/{session_id}/turn/{turn_id}",
|
||||
method="GET",
|
||||
|
|
@ -612,12 +585,6 @@ class Agents(Protocol):
|
|||
"""
|
||||
...
|
||||
|
||||
@webmethod(
|
||||
route="/agents/{agent_id}/session/{session_id}/turn/{turn_id}/step/{step_id}",
|
||||
method="GET",
|
||||
deprecated=True,
|
||||
level=LLAMA_STACK_API_V1,
|
||||
)
|
||||
@webmethod(
|
||||
route="/agents/{agent_id}/session/{session_id}/turn/{turn_id}/step/{step_id}",
|
||||
method="GET",
|
||||
|
|
@ -640,13 +607,6 @@ class Agents(Protocol):
|
|||
"""
|
||||
...
|
||||
|
||||
@webmethod(
|
||||
route="/agents/{agent_id}/session",
|
||||
method="POST",
|
||||
descriptive_name="create_agent_session",
|
||||
deprecated=True,
|
||||
level=LLAMA_STACK_API_V1,
|
||||
)
|
||||
@webmethod(
|
||||
route="/agents/{agent_id}/session",
|
||||
method="POST",
|
||||
|
|
@ -666,12 +626,6 @@ class Agents(Protocol):
|
|||
"""
|
||||
...
|
||||
|
||||
@webmethod(
|
||||
route="/agents/{agent_id}/session/{session_id}",
|
||||
method="GET",
|
||||
deprecated=True,
|
||||
level=LLAMA_STACK_API_V1,
|
||||
)
|
||||
@webmethod(
|
||||
route="/agents/{agent_id}/session/{session_id}",
|
||||
method="GET",
|
||||
|
|
@ -692,12 +646,6 @@ class Agents(Protocol):
|
|||
"""
|
||||
...
|
||||
|
||||
@webmethod(
|
||||
route="/agents/{agent_id}/session/{session_id}",
|
||||
method="DELETE",
|
||||
deprecated=True,
|
||||
level=LLAMA_STACK_API_V1,
|
||||
)
|
||||
@webmethod(
|
||||
route="/agents/{agent_id}/session/{session_id}",
|
||||
method="DELETE",
|
||||
|
|
@ -715,12 +663,6 @@ class Agents(Protocol):
|
|||
"""
|
||||
...
|
||||
|
||||
@webmethod(
|
||||
route="/agents/{agent_id}",
|
||||
method="DELETE",
|
||||
deprecated=True,
|
||||
level=LLAMA_STACK_API_V1,
|
||||
)
|
||||
@webmethod(route="/agents/{agent_id}", method="DELETE", level=LLAMA_STACK_API_V1ALPHA)
|
||||
async def delete_agent(
|
||||
self,
|
||||
|
|
@ -732,7 +674,6 @@ class Agents(Protocol):
|
|||
"""
|
||||
...
|
||||
|
||||
@webmethod(route="/agents", method="GET", deprecated=True, level=LLAMA_STACK_API_V1)
|
||||
@webmethod(route="/agents", method="GET", level=LLAMA_STACK_API_V1ALPHA)
|
||||
async def list_agents(self, start_index: int | None = None, limit: int | None = None) -> PaginatedResponse:
|
||||
"""List all agents.
|
||||
|
|
@ -743,12 +684,6 @@ class Agents(Protocol):
|
|||
"""
|
||||
...
|
||||
|
||||
@webmethod(
|
||||
route="/agents/{agent_id}",
|
||||
method="GET",
|
||||
deprecated=True,
|
||||
level=LLAMA_STACK_API_V1,
|
||||
)
|
||||
@webmethod(route="/agents/{agent_id}", method="GET", level=LLAMA_STACK_API_V1ALPHA)
|
||||
async def get_agent(self, agent_id: str) -> Agent:
|
||||
"""Describe an agent by its ID.
|
||||
|
|
@ -758,12 +693,6 @@ class Agents(Protocol):
|
|||
"""
|
||||
...
|
||||
|
||||
@webmethod(
|
||||
route="/agents/{agent_id}/sessions",
|
||||
method="GET",
|
||||
deprecated=True,
|
||||
level=LLAMA_STACK_API_V1,
|
||||
)
|
||||
@webmethod(route="/agents/{agent_id}/sessions", method="GET", level=LLAMA_STACK_API_V1ALPHA)
|
||||
async def list_agent_sessions(
|
||||
self,
|
||||
|
|
@ -787,12 +716,6 @@ class Agents(Protocol):
|
|||
#
|
||||
# Both of these APIs are inherently stateful.
|
||||
|
||||
@webmethod(
|
||||
route="/openai/v1/responses/{response_id}",
|
||||
method="GET",
|
||||
level=LLAMA_STACK_API_V1,
|
||||
deprecated=True,
|
||||
)
|
||||
@webmethod(route="/responses/{response_id}", method="GET", level=LLAMA_STACK_API_V1)
|
||||
async def get_openai_response(
|
||||
self,
|
||||
|
|
@ -805,7 +728,6 @@ class Agents(Protocol):
|
|||
"""
|
||||
...
|
||||
|
||||
@webmethod(route="/openai/v1/responses", method="POST", level=LLAMA_STACK_API_V1, deprecated=True)
|
||||
@webmethod(route="/responses", method="POST", level=LLAMA_STACK_API_V1)
|
||||
async def create_openai_response(
|
||||
self,
|
||||
|
|
@ -842,7 +764,6 @@ class Agents(Protocol):
|
|||
"""
|
||||
...
|
||||
|
||||
@webmethod(route="/openai/v1/responses", method="GET", level=LLAMA_STACK_API_V1, deprecated=True)
|
||||
@webmethod(route="/responses", method="GET", level=LLAMA_STACK_API_V1)
|
||||
async def list_openai_responses(
|
||||
self,
|
||||
|
|
@ -861,9 +782,6 @@ class Agents(Protocol):
|
|||
"""
|
||||
...
|
||||
|
||||
@webmethod(
|
||||
route="/openai/v1/responses/{response_id}/input_items", method="GET", level=LLAMA_STACK_API_V1, deprecated=True
|
||||
)
|
||||
@webmethod(route="/responses/{response_id}/input_items", method="GET", level=LLAMA_STACK_API_V1)
|
||||
async def list_openai_response_input_items(
|
||||
self,
|
||||
|
|
@ -886,7 +804,6 @@ class Agents(Protocol):
|
|||
"""
|
||||
...
|
||||
|
||||
@webmethod(route="/openai/v1/responses/{response_id}", method="DELETE", level=LLAMA_STACK_API_V1, deprecated=True)
|
||||
@webmethod(route="/responses/{response_id}", method="DELETE", level=LLAMA_STACK_API_V1)
|
||||
async def delete_openai_response(self, response_id: str) -> OpenAIDeleteResponseObject:
|
||||
"""Delete a response.
|
||||
|
|
|
|||
|
|
@ -43,7 +43,6 @@ class Batches(Protocol):
|
|||
Note: This API is currently under active development and may undergo changes.
|
||||
"""
|
||||
|
||||
@webmethod(route="/openai/v1/batches", method="POST", level=LLAMA_STACK_API_V1, deprecated=True)
|
||||
@webmethod(route="/batches", method="POST", level=LLAMA_STACK_API_V1)
|
||||
async def create_batch(
|
||||
self,
|
||||
|
|
@ -64,7 +63,6 @@ class Batches(Protocol):
|
|||
"""
|
||||
...
|
||||
|
||||
@webmethod(route="/openai/v1/batches/{batch_id}", method="GET", level=LLAMA_STACK_API_V1, deprecated=True)
|
||||
@webmethod(route="/batches/{batch_id}", method="GET", level=LLAMA_STACK_API_V1)
|
||||
async def retrieve_batch(self, batch_id: str) -> BatchObject:
|
||||
"""Retrieve information about a specific batch.
|
||||
|
|
@ -74,7 +72,6 @@ class Batches(Protocol):
|
|||
"""
|
||||
...
|
||||
|
||||
@webmethod(route="/openai/v1/batches/{batch_id}/cancel", method="POST", level=LLAMA_STACK_API_V1, deprecated=True)
|
||||
@webmethod(route="/batches/{batch_id}/cancel", method="POST", level=LLAMA_STACK_API_V1)
|
||||
async def cancel_batch(self, batch_id: str) -> BatchObject:
|
||||
"""Cancel a batch that is in progress.
|
||||
|
|
@ -84,7 +81,6 @@ class Batches(Protocol):
|
|||
"""
|
||||
...
|
||||
|
||||
@webmethod(route="/openai/v1/batches", method="GET", level=LLAMA_STACK_API_V1, deprecated=True)
|
||||
@webmethod(route="/batches", method="GET", level=LLAMA_STACK_API_V1)
|
||||
async def list_batches(
|
||||
self,
|
||||
|
|
|
|||
|
|
@ -8,7 +8,7 @@ from typing import Any, Literal, Protocol, runtime_checkable
|
|||
from pydantic import BaseModel, Field
|
||||
|
||||
from llama_stack.apis.resource import Resource, ResourceType
|
||||
from llama_stack.apis.version import LLAMA_STACK_API_V1, LLAMA_STACK_API_V1ALPHA
|
||||
from llama_stack.apis.version import LLAMA_STACK_API_V1ALPHA
|
||||
from llama_stack.schema_utils import json_schema_type, webmethod
|
||||
|
||||
|
||||
|
|
@ -54,7 +54,6 @@ class ListBenchmarksResponse(BaseModel):
|
|||
|
||||
@runtime_checkable
|
||||
class Benchmarks(Protocol):
|
||||
@webmethod(route="/eval/benchmarks", method="GET", level=LLAMA_STACK_API_V1, deprecated=True)
|
||||
@webmethod(route="/eval/benchmarks", method="GET", level=LLAMA_STACK_API_V1ALPHA)
|
||||
async def list_benchmarks(self) -> ListBenchmarksResponse:
|
||||
"""List all benchmarks.
|
||||
|
|
@ -63,7 +62,6 @@ class Benchmarks(Protocol):
|
|||
"""
|
||||
...
|
||||
|
||||
@webmethod(route="/eval/benchmarks/{benchmark_id}", method="GET", level=LLAMA_STACK_API_V1, deprecated=True)
|
||||
@webmethod(route="/eval/benchmarks/{benchmark_id}", method="GET", level=LLAMA_STACK_API_V1ALPHA)
|
||||
async def get_benchmark(
|
||||
self,
|
||||
|
|
@ -76,7 +74,6 @@ class Benchmarks(Protocol):
|
|||
"""
|
||||
...
|
||||
|
||||
@webmethod(route="/eval/benchmarks", method="POST", level=LLAMA_STACK_API_V1, deprecated=True)
|
||||
@webmethod(route="/eval/benchmarks", method="POST", level=LLAMA_STACK_API_V1ALPHA)
|
||||
async def register_benchmark(
|
||||
self,
|
||||
|
|
@ -98,7 +95,6 @@ class Benchmarks(Protocol):
|
|||
"""
|
||||
...
|
||||
|
||||
@webmethod(route="/eval/benchmarks/{benchmark_id}", method="DELETE", level=LLAMA_STACK_API_V1, deprecated=True)
|
||||
@webmethod(route="/eval/benchmarks/{benchmark_id}", method="DELETE", level=LLAMA_STACK_API_V1ALPHA)
|
||||
async def unregister_benchmark(self, benchmark_id: str) -> None:
|
||||
"""Unregister a benchmark.
|
||||
|
|
|
|||
|
|
@ -8,7 +8,7 @@ from typing import Any, Protocol, runtime_checkable
|
|||
|
||||
from llama_stack.apis.common.responses import PaginatedResponse
|
||||
from llama_stack.apis.datasets import Dataset
|
||||
from llama_stack.apis.version import LLAMA_STACK_API_V1, LLAMA_STACK_API_V1BETA
|
||||
from llama_stack.apis.version import LLAMA_STACK_API_V1BETA
|
||||
from llama_stack.schema_utils import webmethod
|
||||
|
||||
|
||||
|
|
@ -21,7 +21,6 @@ class DatasetIO(Protocol):
|
|||
# keeping for aligning with inference/safety, but this is not used
|
||||
dataset_store: DatasetStore
|
||||
|
||||
@webmethod(route="/datasetio/iterrows/{dataset_id:path}", method="GET", deprecated=True, level=LLAMA_STACK_API_V1)
|
||||
@webmethod(route="/datasetio/iterrows/{dataset_id:path}", method="GET", level=LLAMA_STACK_API_V1BETA)
|
||||
async def iterrows(
|
||||
self,
|
||||
|
|
@ -46,9 +45,6 @@ class DatasetIO(Protocol):
|
|||
"""
|
||||
...
|
||||
|
||||
@webmethod(
|
||||
route="/datasetio/append-rows/{dataset_id:path}", method="POST", deprecated=True, level=LLAMA_STACK_API_V1
|
||||
)
|
||||
@webmethod(route="/datasetio/append-rows/{dataset_id:path}", method="POST", level=LLAMA_STACK_API_V1BETA)
|
||||
async def append_rows(self, dataset_id: str, rows: list[dict[str, Any]]) -> None:
|
||||
"""Append rows to a dataset.
|
||||
|
|
|
|||
|
|
@ -10,7 +10,7 @@ from typing import Annotated, Any, Literal, Protocol
|
|||
from pydantic import BaseModel, Field
|
||||
|
||||
from llama_stack.apis.resource import Resource, ResourceType
|
||||
from llama_stack.apis.version import LLAMA_STACK_API_V1, LLAMA_STACK_API_V1BETA
|
||||
from llama_stack.apis.version import LLAMA_STACK_API_V1BETA
|
||||
from llama_stack.schema_utils import json_schema_type, register_schema, webmethod
|
||||
|
||||
|
||||
|
|
@ -146,7 +146,6 @@ class ListDatasetsResponse(BaseModel):
|
|||
|
||||
|
||||
class Datasets(Protocol):
|
||||
@webmethod(route="/datasets", method="POST", deprecated=True, level=LLAMA_STACK_API_V1)
|
||||
@webmethod(route="/datasets", method="POST", level=LLAMA_STACK_API_V1BETA)
|
||||
async def register_dataset(
|
||||
self,
|
||||
|
|
@ -216,7 +215,6 @@ class Datasets(Protocol):
|
|||
"""
|
||||
...
|
||||
|
||||
@webmethod(route="/datasets/{dataset_id:path}", method="GET", deprecated=True, level=LLAMA_STACK_API_V1)
|
||||
@webmethod(route="/datasets/{dataset_id:path}", method="GET", level=LLAMA_STACK_API_V1BETA)
|
||||
async def get_dataset(
|
||||
self,
|
||||
|
|
@ -229,7 +227,6 @@ class Datasets(Protocol):
|
|||
"""
|
||||
...
|
||||
|
||||
@webmethod(route="/datasets", method="GET", deprecated=True, level=LLAMA_STACK_API_V1)
|
||||
@webmethod(route="/datasets", method="GET", level=LLAMA_STACK_API_V1BETA)
|
||||
async def list_datasets(self) -> ListDatasetsResponse:
|
||||
"""List all datasets.
|
||||
|
|
@ -238,7 +235,6 @@ class Datasets(Protocol):
|
|||
"""
|
||||
...
|
||||
|
||||
@webmethod(route="/datasets/{dataset_id:path}", method="DELETE", deprecated=True, level=LLAMA_STACK_API_V1)
|
||||
@webmethod(route="/datasets/{dataset_id:path}", method="DELETE", level=LLAMA_STACK_API_V1BETA)
|
||||
async def unregister_dataset(
|
||||
self,
|
||||
|
|
|
|||
|
|
@ -13,7 +13,7 @@ from llama_stack.apis.common.job_types import Job
|
|||
from llama_stack.apis.inference import SamplingParams, SystemMessage
|
||||
from llama_stack.apis.scoring import ScoringResult
|
||||
from llama_stack.apis.scoring_functions import ScoringFnParams
|
||||
from llama_stack.apis.version import LLAMA_STACK_API_V1, LLAMA_STACK_API_V1ALPHA
|
||||
from llama_stack.apis.version import LLAMA_STACK_API_V1ALPHA
|
||||
from llama_stack.schema_utils import json_schema_type, register_schema, webmethod
|
||||
|
||||
|
||||
|
|
@ -86,7 +86,6 @@ class Eval(Protocol):
|
|||
|
||||
Llama Stack Evaluation API for running evaluations on model and agent candidates."""
|
||||
|
||||
@webmethod(route="/eval/benchmarks/{benchmark_id}/jobs", method="POST", level=LLAMA_STACK_API_V1, deprecated=True)
|
||||
@webmethod(route="/eval/benchmarks/{benchmark_id}/jobs", method="POST", level=LLAMA_STACK_API_V1ALPHA)
|
||||
async def run_eval(
|
||||
self,
|
||||
|
|
@ -101,9 +100,6 @@ class Eval(Protocol):
|
|||
"""
|
||||
...
|
||||
|
||||
@webmethod(
|
||||
route="/eval/benchmarks/{benchmark_id}/evaluations", method="POST", level=LLAMA_STACK_API_V1, deprecated=True
|
||||
)
|
||||
@webmethod(route="/eval/benchmarks/{benchmark_id}/evaluations", method="POST", level=LLAMA_STACK_API_V1ALPHA)
|
||||
async def evaluate_rows(
|
||||
self,
|
||||
|
|
@ -122,9 +118,6 @@ class Eval(Protocol):
|
|||
"""
|
||||
...
|
||||
|
||||
@webmethod(
|
||||
route="/eval/benchmarks/{benchmark_id}/jobs/{job_id}", method="GET", level=LLAMA_STACK_API_V1, deprecated=True
|
||||
)
|
||||
@webmethod(route="/eval/benchmarks/{benchmark_id}/jobs/{job_id}", method="GET", level=LLAMA_STACK_API_V1ALPHA)
|
||||
async def job_status(self, benchmark_id: str, job_id: str) -> Job:
|
||||
"""Get the status of a job.
|
||||
|
|
@ -135,12 +128,6 @@ class Eval(Protocol):
|
|||
"""
|
||||
...
|
||||
|
||||
@webmethod(
|
||||
route="/eval/benchmarks/{benchmark_id}/jobs/{job_id}",
|
||||
method="DELETE",
|
||||
level=LLAMA_STACK_API_V1,
|
||||
deprecated=True,
|
||||
)
|
||||
@webmethod(route="/eval/benchmarks/{benchmark_id}/jobs/{job_id}", method="DELETE", level=LLAMA_STACK_API_V1ALPHA)
|
||||
async def job_cancel(self, benchmark_id: str, job_id: str) -> None:
|
||||
"""Cancel a job.
|
||||
|
|
@ -150,12 +137,6 @@ class Eval(Protocol):
|
|||
"""
|
||||
...
|
||||
|
||||
@webmethod(
|
||||
route="/eval/benchmarks/{benchmark_id}/jobs/{job_id}/result",
|
||||
method="GET",
|
||||
level=LLAMA_STACK_API_V1,
|
||||
deprecated=True,
|
||||
)
|
||||
@webmethod(
|
||||
route="/eval/benchmarks/{benchmark_id}/jobs/{job_id}/result", method="GET", level=LLAMA_STACK_API_V1ALPHA
|
||||
)
|
||||
|
|
|
|||
|
|
@ -110,7 +110,6 @@ class Files(Protocol):
|
|||
"""
|
||||
|
||||
# OpenAI Files API Endpoints
|
||||
@webmethod(route="/openai/v1/files", method="POST", level=LLAMA_STACK_API_V1, deprecated=True)
|
||||
@webmethod(route="/files", method="POST", level=LLAMA_STACK_API_V1)
|
||||
async def openai_upload_file(
|
||||
self,
|
||||
|
|
@ -134,7 +133,6 @@ class Files(Protocol):
|
|||
"""
|
||||
...
|
||||
|
||||
@webmethod(route="/openai/v1/files", method="GET", level=LLAMA_STACK_API_V1, deprecated=True)
|
||||
@webmethod(route="/files", method="GET", level=LLAMA_STACK_API_V1)
|
||||
async def openai_list_files(
|
||||
self,
|
||||
|
|
@ -155,7 +153,6 @@ class Files(Protocol):
|
|||
"""
|
||||
...
|
||||
|
||||
@webmethod(route="/openai/v1/files/{file_id}", method="GET", level=LLAMA_STACK_API_V1, deprecated=True)
|
||||
@webmethod(route="/files/{file_id}", method="GET", level=LLAMA_STACK_API_V1)
|
||||
async def openai_retrieve_file(
|
||||
self,
|
||||
|
|
@ -170,7 +167,6 @@ class Files(Protocol):
|
|||
"""
|
||||
...
|
||||
|
||||
@webmethod(route="/openai/v1/files/{file_id}", method="DELETE", level=LLAMA_STACK_API_V1, deprecated=True)
|
||||
@webmethod(route="/files/{file_id}", method="DELETE", level=LLAMA_STACK_API_V1)
|
||||
async def openai_delete_file(
|
||||
self,
|
||||
|
|
@ -183,7 +179,6 @@ class Files(Protocol):
|
|||
"""
|
||||
...
|
||||
|
||||
@webmethod(route="/openai/v1/files/{file_id}/content", method="GET", level=LLAMA_STACK_API_V1, deprecated=True)
|
||||
@webmethod(route="/files/{file_id}/content", method="GET", level=LLAMA_STACK_API_V1)
|
||||
async def openai_retrieve_file_content(
|
||||
self,
|
||||
|
|
|
|||
|
|
@ -1189,7 +1189,6 @@ class InferenceProvider(Protocol):
|
|||
raise NotImplementedError("Reranking is not implemented")
|
||||
return # this is so mypy's safe-super rule will consider the method concrete
|
||||
|
||||
@webmethod(route="/openai/v1/completions", method="POST", level=LLAMA_STACK_API_V1, deprecated=True)
|
||||
@webmethod(route="/completions", method="POST", level=LLAMA_STACK_API_V1)
|
||||
async def openai_completion(
|
||||
self,
|
||||
|
|
@ -1202,7 +1201,6 @@ class InferenceProvider(Protocol):
|
|||
"""
|
||||
...
|
||||
|
||||
@webmethod(route="/openai/v1/chat/completions", method="POST", level=LLAMA_STACK_API_V1, deprecated=True)
|
||||
@webmethod(route="/chat/completions", method="POST", level=LLAMA_STACK_API_V1)
|
||||
async def openai_chat_completion(
|
||||
self,
|
||||
|
|
@ -1215,7 +1213,6 @@ class InferenceProvider(Protocol):
|
|||
"""
|
||||
...
|
||||
|
||||
@webmethod(route="/openai/v1/embeddings", method="POST", level=LLAMA_STACK_API_V1, deprecated=True)
|
||||
@webmethod(route="/embeddings", method="POST", level=LLAMA_STACK_API_V1)
|
||||
async def openai_embeddings(
|
||||
self,
|
||||
|
|
@ -1240,7 +1237,6 @@ class Inference(InferenceProvider):
|
|||
- Rerank models: these models reorder the documents based on their relevance to a query.
|
||||
"""
|
||||
|
||||
@webmethod(route="/openai/v1/chat/completions", method="GET", level=LLAMA_STACK_API_V1, deprecated=True)
|
||||
@webmethod(route="/chat/completions", method="GET", level=LLAMA_STACK_API_V1)
|
||||
async def list_chat_completions(
|
||||
self,
|
||||
|
|
@ -1259,9 +1255,6 @@ class Inference(InferenceProvider):
|
|||
"""
|
||||
raise NotImplementedError("List chat completions is not implemented")
|
||||
|
||||
@webmethod(
|
||||
route="/openai/v1/chat/completions/{completion_id}", method="GET", level=LLAMA_STACK_API_V1, deprecated=True
|
||||
)
|
||||
@webmethod(route="/chat/completions/{completion_id}", method="GET", level=LLAMA_STACK_API_V1)
|
||||
async def get_chat_completion(self, completion_id: str) -> OpenAICompletionWithInputMessages:
|
||||
"""Get chat completion.
|
||||
|
|
|
|||
|
|
@ -107,7 +107,6 @@ class OpenAIListModelsResponse(BaseModel):
|
|||
@runtime_checkable
|
||||
@trace_protocol
|
||||
class Models(Protocol):
|
||||
@webmethod(route="/models", method="GET", level=LLAMA_STACK_API_V1)
|
||||
async def list_models(self) -> ListModelsResponse:
|
||||
"""List all models.
|
||||
|
||||
|
|
@ -115,7 +114,7 @@ class Models(Protocol):
|
|||
"""
|
||||
...
|
||||
|
||||
@webmethod(route="/openai/v1/models", method="GET", level=LLAMA_STACK_API_V1)
|
||||
@webmethod(route="/models", method="GET", level=LLAMA_STACK_API_V1)
|
||||
async def openai_list_models(self) -> OpenAIListModelsResponse:
|
||||
"""List models using the OpenAI API.
|
||||
|
||||
|
|
|
|||
|
|
@ -13,7 +13,7 @@ from pydantic import BaseModel, Field
|
|||
from llama_stack.apis.common.content_types import URL
|
||||
from llama_stack.apis.common.job_types import JobStatus
|
||||
from llama_stack.apis.common.training_types import Checkpoint
|
||||
from llama_stack.apis.version import LLAMA_STACK_API_V1, LLAMA_STACK_API_V1ALPHA
|
||||
from llama_stack.apis.version import LLAMA_STACK_API_V1ALPHA
|
||||
from llama_stack.schema_utils import json_schema_type, register_schema, webmethod
|
||||
|
||||
|
||||
|
|
@ -284,7 +284,6 @@ class PostTrainingJobArtifactsResponse(BaseModel):
|
|||
|
||||
|
||||
class PostTraining(Protocol):
|
||||
@webmethod(route="/post-training/supervised-fine-tune", method="POST", level=LLAMA_STACK_API_V1, deprecated=True)
|
||||
@webmethod(route="/post-training/supervised-fine-tune", method="POST", level=LLAMA_STACK_API_V1ALPHA)
|
||||
async def supervised_fine_tune(
|
||||
self,
|
||||
|
|
@ -312,7 +311,6 @@ class PostTraining(Protocol):
|
|||
"""
|
||||
...
|
||||
|
||||
@webmethod(route="/post-training/preference-optimize", method="POST", level=LLAMA_STACK_API_V1, deprecated=True)
|
||||
@webmethod(route="/post-training/preference-optimize", method="POST", level=LLAMA_STACK_API_V1ALPHA)
|
||||
async def preference_optimize(
|
||||
self,
|
||||
|
|
@ -335,7 +333,6 @@ class PostTraining(Protocol):
|
|||
"""
|
||||
...
|
||||
|
||||
@webmethod(route="/post-training/jobs", method="GET", level=LLAMA_STACK_API_V1, deprecated=True)
|
||||
@webmethod(route="/post-training/jobs", method="GET", level=LLAMA_STACK_API_V1ALPHA)
|
||||
async def get_training_jobs(self) -> ListPostTrainingJobsResponse:
|
||||
"""Get all training jobs.
|
||||
|
|
@ -344,7 +341,6 @@ class PostTraining(Protocol):
|
|||
"""
|
||||
...
|
||||
|
||||
@webmethod(route="/post-training/job/status", method="GET", level=LLAMA_STACK_API_V1, deprecated=True)
|
||||
@webmethod(route="/post-training/job/status", method="GET", level=LLAMA_STACK_API_V1ALPHA)
|
||||
async def get_training_job_status(self, job_uuid: str) -> PostTrainingJobStatusResponse:
|
||||
"""Get the status of a training job.
|
||||
|
|
@ -354,7 +350,6 @@ class PostTraining(Protocol):
|
|||
"""
|
||||
...
|
||||
|
||||
@webmethod(route="/post-training/job/cancel", method="POST", level=LLAMA_STACK_API_V1, deprecated=True)
|
||||
@webmethod(route="/post-training/job/cancel", method="POST", level=LLAMA_STACK_API_V1ALPHA)
|
||||
async def cancel_training_job(self, job_uuid: str) -> None:
|
||||
"""Cancel a training job.
|
||||
|
|
@ -363,7 +358,6 @@ class PostTraining(Protocol):
|
|||
"""
|
||||
...
|
||||
|
||||
@webmethod(route="/post-training/job/artifacts", method="GET", level=LLAMA_STACK_API_V1, deprecated=True)
|
||||
@webmethod(route="/post-training/job/artifacts", method="GET", level=LLAMA_STACK_API_V1ALPHA)
|
||||
async def get_training_job_artifacts(self, job_uuid: str) -> PostTrainingJobArtifactsResponse:
|
||||
"""Get the artifacts of a training job.
|
||||
|
|
|
|||
|
|
@ -121,7 +121,6 @@ class Safety(Protocol):
|
|||
"""
|
||||
...
|
||||
|
||||
@webmethod(route="/openai/v1/moderations", method="POST", level=LLAMA_STACK_API_V1, deprecated=True)
|
||||
@webmethod(route="/moderations", method="POST", level=LLAMA_STACK_API_V1)
|
||||
async def run_moderation(self, input: str | list[str], model: str | None = None) -> ModerationObject:
|
||||
"""Create moderation.
|
||||
|
|
|
|||
|
|
@ -545,7 +545,6 @@ class VectorIO(Protocol):
|
|||
...
|
||||
|
||||
# OpenAI Vector Stores API endpoints
|
||||
@webmethod(route="/openai/v1/vector_stores", method="POST", level=LLAMA_STACK_API_V1, deprecated=True)
|
||||
@webmethod(route="/vector_stores", method="POST", level=LLAMA_STACK_API_V1)
|
||||
async def openai_create_vector_store(
|
||||
self,
|
||||
|
|
@ -558,7 +557,6 @@ class VectorIO(Protocol):
|
|||
"""
|
||||
...
|
||||
|
||||
@webmethod(route="/openai/v1/vector_stores", method="GET", level=LLAMA_STACK_API_V1, deprecated=True)
|
||||
@webmethod(route="/vector_stores", method="GET", level=LLAMA_STACK_API_V1)
|
||||
async def openai_list_vector_stores(
|
||||
self,
|
||||
|
|
@ -577,9 +575,6 @@ class VectorIO(Protocol):
|
|||
"""
|
||||
...
|
||||
|
||||
@webmethod(
|
||||
route="/openai/v1/vector_stores/{vector_store_id}", method="GET", level=LLAMA_STACK_API_V1, deprecated=True
|
||||
)
|
||||
@webmethod(route="/vector_stores/{vector_store_id}", method="GET", level=LLAMA_STACK_API_V1)
|
||||
async def openai_retrieve_vector_store(
|
||||
self,
|
||||
|
|
@ -592,9 +587,6 @@ class VectorIO(Protocol):
|
|||
"""
|
||||
...
|
||||
|
||||
@webmethod(
|
||||
route="/openai/v1/vector_stores/{vector_store_id}", method="POST", level=LLAMA_STACK_API_V1, deprecated=True
|
||||
)
|
||||
@webmethod(
|
||||
route="/vector_stores/{vector_store_id}",
|
||||
method="POST",
|
||||
|
|
@ -617,9 +609,6 @@ class VectorIO(Protocol):
|
|||
"""
|
||||
...
|
||||
|
||||
@webmethod(
|
||||
route="/openai/v1/vector_stores/{vector_store_id}", method="DELETE", level=LLAMA_STACK_API_V1, deprecated=True
|
||||
)
|
||||
@webmethod(
|
||||
route="/vector_stores/{vector_store_id}",
|
||||
method="DELETE",
|
||||
|
|
@ -636,12 +625,6 @@ class VectorIO(Protocol):
|
|||
"""
|
||||
...
|
||||
|
||||
@webmethod(
|
||||
route="/openai/v1/vector_stores/{vector_store_id}/search",
|
||||
method="POST",
|
||||
level=LLAMA_STACK_API_V1,
|
||||
deprecated=True,
|
||||
)
|
||||
@webmethod(
|
||||
route="/vector_stores/{vector_store_id}/search",
|
||||
method="POST",
|
||||
|
|
@ -674,12 +657,6 @@ class VectorIO(Protocol):
|
|||
"""
|
||||
...
|
||||
|
||||
@webmethod(
|
||||
route="/openai/v1/vector_stores/{vector_store_id}/files",
|
||||
method="POST",
|
||||
level=LLAMA_STACK_API_V1,
|
||||
deprecated=True,
|
||||
)
|
||||
@webmethod(
|
||||
route="/vector_stores/{vector_store_id}/files",
|
||||
method="POST",
|
||||
|
|
@ -702,12 +679,6 @@ class VectorIO(Protocol):
|
|||
"""
|
||||
...
|
||||
|
||||
@webmethod(
|
||||
route="/openai/v1/vector_stores/{vector_store_id}/files",
|
||||
method="GET",
|
||||
level=LLAMA_STACK_API_V1,
|
||||
deprecated=True,
|
||||
)
|
||||
@webmethod(
|
||||
route="/vector_stores/{vector_store_id}/files",
|
||||
method="GET",
|
||||
|
|
@ -734,12 +705,6 @@ class VectorIO(Protocol):
|
|||
"""
|
||||
...
|
||||
|
||||
@webmethod(
|
||||
route="/openai/v1/vector_stores/{vector_store_id}/files/{file_id}",
|
||||
method="GET",
|
||||
level=LLAMA_STACK_API_V1,
|
||||
deprecated=True,
|
||||
)
|
||||
@webmethod(
|
||||
route="/vector_stores/{vector_store_id}/files/{file_id}",
|
||||
method="GET",
|
||||
|
|
@ -758,12 +723,6 @@ class VectorIO(Protocol):
|
|||
"""
|
||||
...
|
||||
|
||||
@webmethod(
|
||||
route="/openai/v1/vector_stores/{vector_store_id}/files/{file_id}/content",
|
||||
method="GET",
|
||||
level=LLAMA_STACK_API_V1,
|
||||
deprecated=True,
|
||||
)
|
||||
@webmethod(
|
||||
route="/vector_stores/{vector_store_id}/files/{file_id}/content",
|
||||
method="GET",
|
||||
|
|
@ -782,12 +741,6 @@ class VectorIO(Protocol):
|
|||
"""
|
||||
...
|
||||
|
||||
@webmethod(
|
||||
route="/openai/v1/vector_stores/{vector_store_id}/files/{file_id}",
|
||||
method="POST",
|
||||
level=LLAMA_STACK_API_V1,
|
||||
deprecated=True,
|
||||
)
|
||||
@webmethod(
|
||||
route="/vector_stores/{vector_store_id}/files/{file_id}",
|
||||
method="POST",
|
||||
|
|
@ -808,12 +761,6 @@ class VectorIO(Protocol):
|
|||
"""
|
||||
...
|
||||
|
||||
@webmethod(
|
||||
route="/openai/v1/vector_stores/{vector_store_id}/files/{file_id}",
|
||||
method="DELETE",
|
||||
level=LLAMA_STACK_API_V1,
|
||||
deprecated=True,
|
||||
)
|
||||
@webmethod(
|
||||
route="/vector_stores/{vector_store_id}/files/{file_id}",
|
||||
method="DELETE",
|
||||
|
|
@ -837,12 +784,6 @@ class VectorIO(Protocol):
|
|||
method="POST",
|
||||
level=LLAMA_STACK_API_V1,
|
||||
)
|
||||
@webmethod(
|
||||
route="/openai/v1/vector_stores/{vector_store_id}/file_batches",
|
||||
method="POST",
|
||||
level=LLAMA_STACK_API_V1,
|
||||
deprecated=True,
|
||||
)
|
||||
async def openai_create_vector_store_file_batch(
|
||||
self,
|
||||
vector_store_id: str,
|
||||
|
|
@ -861,12 +802,6 @@ class VectorIO(Protocol):
|
|||
method="GET",
|
||||
level=LLAMA_STACK_API_V1,
|
||||
)
|
||||
@webmethod(
|
||||
route="/openai/v1/vector_stores/{vector_store_id}/file_batches/{batch_id}",
|
||||
method="GET",
|
||||
level=LLAMA_STACK_API_V1,
|
||||
deprecated=True,
|
||||
)
|
||||
async def openai_retrieve_vector_store_file_batch(
|
||||
self,
|
||||
batch_id: str,
|
||||
|
|
@ -880,12 +815,6 @@ class VectorIO(Protocol):
|
|||
"""
|
||||
...
|
||||
|
||||
@webmethod(
|
||||
route="/openai/v1/vector_stores/{vector_store_id}/file_batches/{batch_id}/files",
|
||||
method="GET",
|
||||
level=LLAMA_STACK_API_V1,
|
||||
deprecated=True,
|
||||
)
|
||||
@webmethod(
|
||||
route="/vector_stores/{vector_store_id}/file_batches/{batch_id}/files",
|
||||
method="GET",
|
||||
|
|
@ -914,12 +843,6 @@ class VectorIO(Protocol):
|
|||
"""
|
||||
...
|
||||
|
||||
@webmethod(
|
||||
route="/openai/v1/vector_stores/{vector_store_id}/file_batches/{batch_id}/cancel",
|
||||
method="POST",
|
||||
level=LLAMA_STACK_API_V1,
|
||||
deprecated=True,
|
||||
)
|
||||
@webmethod(
|
||||
route="/vector_stores/{vector_store_id}/file_batches/{batch_id}/cancel",
|
||||
method="POST",
|
||||
|
|
|
|||
Loading…
Add table
Add a link
Reference in a new issue