From 8335986443a75b92f40bea7e319894dfccbf6126 Mon Sep 17 00:00:00 2001 From: Xi Yan Date: Wed, 15 Jan 2025 10:54:13 -0800 Subject: [PATCH 1/2] sync v1 prefix sdk --- src/llama_stack_client/_client.py | 18 ++-- src/llama_stack_client/_version.py | 2 +- .../resources/agents/agents.py | 8 +- .../resources/agents/session.py | 12 +-- .../resources/agents/steps.py | 4 +- .../resources/agents/turn.py | 8 +- .../resources/batch_inference.py | 8 +- src/llama_stack_client/resources/datasetio.py | 8 +- src/llama_stack_client/resources/datasets.py | 16 ++-- src/llama_stack_client/resources/eval/eval.py | 8 +- src/llama_stack_client/resources/eval/jobs.py | 12 +-- .../resources/eval_tasks.py | 12 +-- src/llama_stack_client/resources/inference.py | 12 +-- src/llama_stack_client/resources/inspect.py | 8 +- src/llama_stack_client/resources/memory.py | 8 +- .../resources/memory_banks.py | 85 ++++++++++--------- src/llama_stack_client/resources/models.py | 16 ++-- .../resources/post_training/job.py | 16 ++-- .../resources/post_training/post_training.py | 8 +- src/llama_stack_client/resources/providers.py | 4 +- src/llama_stack_client/resources/routes.py | 4 +- src/llama_stack_client/resources/safety.py | 4 +- src/llama_stack_client/resources/scoring.py | 8 +- .../resources/scoring_functions.py | 12 +-- src/llama_stack_client/resources/shields.py | 12 +-- .../resources/synthetic_data_generation.py | 4 +- src/llama_stack_client/resources/telemetry.py | 20 ++--- .../resources/tool_runtime.py | 8 +- .../resources/toolgroups.py | 16 ++-- src/llama_stack_client/resources/tools.py | 8 +- src/llama_stack_client/types/__init__.py | 1 + .../types/memory_bank_register_response.py | 73 ++++++++++++++++ ...ost_training_preference_optimize_params.py | 2 + ...st_training_supervised_fine_tune_params.py | 2 + .../types/shared/content_delta.py | 8 +- tests/api_resources/test_memory_banks.py | 17 ++-- tests/api_resources/test_post_training.py | 16 ++++ tests/test_client.py | 34 ++++---- 38 files changed, 311 insertions(+), 211 deletions(-) create mode 100644 src/llama_stack_client/types/memory_bank_register_response.py diff --git a/src/llama_stack_client/_client.py b/src/llama_stack_client/_client.py index 763dbe24..25d14254 100644 --- a/src/llama_stack_client/_client.py +++ b/src/llama_stack_client/_client.py @@ -1,7 +1,7 @@ # File generated from our OpenAPI spec by Stainless. See CONTRIBUTING.md for details. -from __future__ import annotations import json +from __future__ import annotations import os from typing import Any, Union, Mapping @@ -128,10 +128,10 @@ def __init__( if base_url is None: base_url = f"http://any-hosted-llama-stack.com" - custom_headers = default_headers or {} - custom_headers["X-LlamaStack-Client-Version"] = __version__ if provider_data is not None: - custom_headers["X-LlamaStack-Provider-Data"] = json.dumps(provider_data) + if default_headers is None: + default_headers = {} + default_headers["X-LlamaStack-ProviderData"] = json.dumps(provider_data) super().__init__( version=__version__, @@ -139,7 +139,7 @@ def __init__( max_retries=max_retries, timeout=timeout, http_client=http_client, - custom_headers=custom_headers, + custom_headers=default_headers, custom_query=default_query, _strict_response_validation=_strict_response_validation, ) @@ -325,10 +325,10 @@ def __init__( if base_url is None: base_url = f"http://any-hosted-llama-stack.com" - custom_headers = default_headers or {} - custom_headers["X-LlamaStack-Client-Version"] = __version__ if provider_data is not None: - custom_headers["X-LlamaStack-Provider-Data"] = json.dumps(provider_data) + if default_headers is None: + default_headers = {} + default_headers["X-LlamaStack-ProviderData"] = json.dumps(provider_data) super().__init__( version=__version__, @@ -336,7 +336,7 @@ def __init__( max_retries=max_retries, timeout=timeout, http_client=http_client, - custom_headers=custom_headers, + custom_headers=default_headers, custom_query=default_query, _strict_response_validation=_strict_response_validation, ) diff --git a/src/llama_stack_client/_version.py b/src/llama_stack_client/_version.py index e6be9c7e..d4078242 100644 --- a/src/llama_stack_client/_version.py +++ b/src/llama_stack_client/_version.py @@ -1,4 +1,4 @@ # File generated from our OpenAPI spec by Stainless. See CONTRIBUTING.md for details. __title__ = "llama_stack_client" -__version__ = "0.0.63" +__version__ = "0.0.1-alpha.0" diff --git a/src/llama_stack_client/resources/agents/agents.py b/src/llama_stack_client/resources/agents/agents.py index fefa0b6e..32dea896 100644 --- a/src/llama_stack_client/resources/agents/agents.py +++ b/src/llama_stack_client/resources/agents/agents.py @@ -115,7 +115,7 @@ def create( **(extra_headers or {}), } return self._post( - "/alpha/agents/create", + "/v1/agents/create", body=maybe_transform({"agent_config": agent_config}, agent_create_params.AgentCreateParams), options=make_request_options( extra_headers=extra_headers, extra_query=extra_query, extra_body=extra_body, timeout=timeout @@ -157,7 +157,7 @@ def delete( **(extra_headers or {}), } return self._post( - "/alpha/agents/delete", + "/v1/agents/delete", body=maybe_transform({"agent_id": agent_id}, agent_delete_params.AgentDeleteParams), options=make_request_options( extra_headers=extra_headers, extra_query=extra_query, extra_body=extra_body, timeout=timeout @@ -231,7 +231,7 @@ async def create( **(extra_headers or {}), } return await self._post( - "/alpha/agents/create", + "/v1/agents/create", body=await async_maybe_transform({"agent_config": agent_config}, agent_create_params.AgentCreateParams), options=make_request_options( extra_headers=extra_headers, extra_query=extra_query, extra_body=extra_body, timeout=timeout @@ -273,7 +273,7 @@ async def delete( **(extra_headers or {}), } return await self._post( - "/alpha/agents/delete", + "/v1/agents/delete", body=await async_maybe_transform({"agent_id": agent_id}, agent_delete_params.AgentDeleteParams), options=make_request_options( extra_headers=extra_headers, extra_query=extra_query, extra_body=extra_body, timeout=timeout diff --git a/src/llama_stack_client/resources/agents/session.py b/src/llama_stack_client/resources/agents/session.py index 7ed0f320..1ed12c90 100644 --- a/src/llama_stack_client/resources/agents/session.py +++ b/src/llama_stack_client/resources/agents/session.py @@ -82,7 +82,7 @@ def create( **(extra_headers or {}), } return self._post( - "/alpha/agents/session/create", + "/v1/agents/session/create", body=maybe_transform( { "agent_id": agent_id, @@ -131,7 +131,7 @@ def retrieve( **(extra_headers or {}), } return self._post( - "/alpha/agents/session/get", + "/v1/agents/session/get", body=maybe_transform({"turn_ids": turn_ids}, session_retrieve_params.SessionRetrieveParams), options=make_request_options( extra_headers=extra_headers, @@ -184,7 +184,7 @@ def delete( **(extra_headers or {}), } return self._post( - "/alpha/agents/session/delete", + "/v1/agents/session/delete", body=maybe_transform( { "agent_id": agent_id, @@ -253,7 +253,7 @@ async def create( **(extra_headers or {}), } return await self._post( - "/alpha/agents/session/create", + "/v1/agents/session/create", body=await async_maybe_transform( { "agent_id": agent_id, @@ -302,7 +302,7 @@ async def retrieve( **(extra_headers or {}), } return await self._post( - "/alpha/agents/session/get", + "/v1/agents/session/get", body=await async_maybe_transform({"turn_ids": turn_ids}, session_retrieve_params.SessionRetrieveParams), options=make_request_options( extra_headers=extra_headers, @@ -355,7 +355,7 @@ async def delete( **(extra_headers or {}), } return await self._post( - "/alpha/agents/session/delete", + "/v1/agents/session/delete", body=await async_maybe_transform( { "agent_id": agent_id, diff --git a/src/llama_stack_client/resources/agents/steps.py b/src/llama_stack_client/resources/agents/steps.py index 67359084..06488eed 100644 --- a/src/llama_stack_client/resources/agents/steps.py +++ b/src/llama_stack_client/resources/agents/steps.py @@ -81,7 +81,7 @@ def retrieve( **(extra_headers or {}), } return self._get( - "/alpha/agents/step/get", + "/v1/agents/step/get", options=make_request_options( extra_headers=extra_headers, extra_query=extra_query, @@ -157,7 +157,7 @@ async def retrieve( **(extra_headers or {}), } return await self._get( - "/alpha/agents/step/get", + "/v1/agents/step/get", options=make_request_options( extra_headers=extra_headers, extra_query=extra_query, diff --git a/src/llama_stack_client/resources/agents/turn.py b/src/llama_stack_client/resources/agents/turn.py index b74e6aa6..8e671e26 100644 --- a/src/llama_stack_client/resources/agents/turn.py +++ b/src/llama_stack_client/resources/agents/turn.py @@ -176,7 +176,7 @@ def create( return cast( TurnCreateResponse, self._post( - "/alpha/agents/turn/create", + "/v1/agents/turn/create", body=maybe_transform( { "agent_id": agent_id, @@ -234,7 +234,7 @@ def retrieve( **(extra_headers or {}), } return self._get( - "/alpha/agents/turn/get", + "/v1/agents/turn/get", options=make_request_options( extra_headers=extra_headers, extra_query=extra_query, @@ -398,7 +398,7 @@ async def create( return cast( TurnCreateResponse, await self._post( - "/alpha/agents/turn/create", + "/v1/agents/turn/create", body=await async_maybe_transform( { "agent_id": agent_id, @@ -456,7 +456,7 @@ async def retrieve( **(extra_headers or {}), } return await self._get( - "/alpha/agents/turn/get", + "/v1/agents/turn/get", options=make_request_options( extra_headers=extra_headers, extra_query=extra_query, diff --git a/src/llama_stack_client/resources/batch_inference.py b/src/llama_stack_client/resources/batch_inference.py index 4b8169b0..ada3cc6e 100644 --- a/src/llama_stack_client/resources/batch_inference.py +++ b/src/llama_stack_client/resources/batch_inference.py @@ -100,7 +100,7 @@ def chat_completion( **(extra_headers or {}), } return self._post( - "/alpha/batch-inference/chat-completion", + "/v1/batch-inference/chat-completion", body=maybe_transform( { "messages_batch": messages_batch, @@ -155,7 +155,7 @@ def completion( **(extra_headers or {}), } return self._post( - "/alpha/batch-inference/completion", + "/v1/batch-inference/completion", body=maybe_transform( { "content_batch": content_batch, @@ -241,7 +241,7 @@ async def chat_completion( **(extra_headers or {}), } return await self._post( - "/alpha/batch-inference/chat-completion", + "/v1/batch-inference/chat-completion", body=await async_maybe_transform( { "messages_batch": messages_batch, @@ -296,7 +296,7 @@ async def completion( **(extra_headers or {}), } return await self._post( - "/alpha/batch-inference/completion", + "/v1/batch-inference/completion", body=await async_maybe_transform( { "content_batch": content_batch, diff --git a/src/llama_stack_client/resources/datasetio.py b/src/llama_stack_client/resources/datasetio.py index c6dfa2d6..947c2bcb 100644 --- a/src/llama_stack_client/resources/datasetio.py +++ b/src/llama_stack_client/resources/datasetio.py @@ -82,7 +82,7 @@ def append_rows( **(extra_headers or {}), } return self._post( - "/alpha/datasetio/append-rows", + "/v1/datasetio/append-rows", body=maybe_transform( { "dataset_id": dataset_id, @@ -132,7 +132,7 @@ def get_rows_paginated( **(extra_headers or {}), } return self._get( - "/alpha/datasetio/get-rows-paginated", + "/v1/datasetio/get-rows-paginated", options=make_request_options( extra_headers=extra_headers, extra_query=extra_query, @@ -207,7 +207,7 @@ async def append_rows( **(extra_headers or {}), } return await self._post( - "/alpha/datasetio/append-rows", + "/v1/datasetio/append-rows", body=await async_maybe_transform( { "dataset_id": dataset_id, @@ -257,7 +257,7 @@ async def get_rows_paginated( **(extra_headers or {}), } return await self._get( - "/alpha/datasetio/get-rows-paginated", + "/v1/datasetio/get-rows-paginated", options=make_request_options( extra_headers=extra_headers, extra_query=extra_query, diff --git a/src/llama_stack_client/resources/datasets.py b/src/llama_stack_client/resources/datasets.py index 18128677..6cb7a4b3 100644 --- a/src/llama_stack_client/resources/datasets.py +++ b/src/llama_stack_client/resources/datasets.py @@ -83,7 +83,7 @@ def retrieve( **(extra_headers or {}), } return self._get( - "/alpha/datasets/get", + "/v1/datasets/get", options=make_request_options( extra_headers=extra_headers, extra_query=extra_query, @@ -127,7 +127,7 @@ def list( **(extra_headers or {}), } return self._get( - "/alpha/datasets/list", + "/v1/datasets/list", options=make_request_options( extra_headers=extra_headers, extra_query=extra_query, extra_body=extra_body, timeout=timeout ), @@ -173,7 +173,7 @@ def register( **(extra_headers or {}), } return self._post( - "/alpha/datasets/register", + "/v1/datasets/register", body=maybe_transform( { "dataset_id": dataset_id, @@ -225,7 +225,7 @@ def unregister( **(extra_headers or {}), } return self._post( - "/alpha/datasets/unregister", + "/v1/datasets/unregister", body=maybe_transform({"dataset_id": dataset_id}, dataset_unregister_params.DatasetUnregisterParams), options=make_request_options( extra_headers=extra_headers, extra_query=extra_query, extra_body=extra_body, timeout=timeout @@ -287,7 +287,7 @@ async def retrieve( **(extra_headers or {}), } return await self._get( - "/alpha/datasets/get", + "/v1/datasets/get", options=make_request_options( extra_headers=extra_headers, extra_query=extra_query, @@ -333,7 +333,7 @@ async def list( **(extra_headers or {}), } return await self._get( - "/alpha/datasets/list", + "/v1/datasets/list", options=make_request_options( extra_headers=extra_headers, extra_query=extra_query, extra_body=extra_body, timeout=timeout ), @@ -379,7 +379,7 @@ async def register( **(extra_headers or {}), } return await self._post( - "/alpha/datasets/register", + "/v1/datasets/register", body=await async_maybe_transform( { "dataset_id": dataset_id, @@ -431,7 +431,7 @@ async def unregister( **(extra_headers or {}), } return await self._post( - "/alpha/datasets/unregister", + "/v1/datasets/unregister", body=await async_maybe_transform( {"dataset_id": dataset_id}, dataset_unregister_params.DatasetUnregisterParams ), diff --git a/src/llama_stack_client/resources/eval/eval.py b/src/llama_stack_client/resources/eval/eval.py index 77a5e5b0..47673d8b 100644 --- a/src/llama_stack_client/resources/eval/eval.py +++ b/src/llama_stack_client/resources/eval/eval.py @@ -96,7 +96,7 @@ def evaluate_rows( **(extra_headers or {}), } return self._post( - "/alpha/eval/evaluate-rows", + "/v1/eval/evaluate-rows", body=maybe_transform( { "input_rows": input_rows, @@ -146,7 +146,7 @@ def run_eval( **(extra_headers or {}), } return self._post( - "/alpha/eval/run-eval", + "/v1/eval/run-eval", body=maybe_transform( { "task_config": task_config, @@ -221,7 +221,7 @@ async def evaluate_rows( **(extra_headers or {}), } return await self._post( - "/alpha/eval/evaluate-rows", + "/v1/eval/evaluate-rows", body=await async_maybe_transform( { "input_rows": input_rows, @@ -271,7 +271,7 @@ async def run_eval( **(extra_headers or {}), } return await self._post( - "/alpha/eval/run-eval", + "/v1/eval/run-eval", body=await async_maybe_transform( { "task_config": task_config, diff --git a/src/llama_stack_client/resources/eval/jobs.py b/src/llama_stack_client/resources/eval/jobs.py index be83b4db..aada8a42 100644 --- a/src/llama_stack_client/resources/eval/jobs.py +++ b/src/llama_stack_client/resources/eval/jobs.py @@ -82,7 +82,7 @@ def retrieve( **(extra_headers or {}), } return self._get( - "/alpha/eval/job/result", + "/v1/eval/job/result", options=make_request_options( extra_headers=extra_headers, extra_query=extra_query, @@ -134,7 +134,7 @@ def cancel( **(extra_headers or {}), } return self._post( - "/alpha/eval/job/cancel", + "/v1/eval/job/cancel", body=maybe_transform( { "job_id": job_id, @@ -182,7 +182,7 @@ def status( **(extra_headers or {}), } return self._get( - "/alpha/eval/job/status", + "/v1/eval/job/status", options=make_request_options( extra_headers=extra_headers, extra_query=extra_query, @@ -254,7 +254,7 @@ async def retrieve( **(extra_headers or {}), } return await self._get( - "/alpha/eval/job/result", + "/v1/eval/job/result", options=make_request_options( extra_headers=extra_headers, extra_query=extra_query, @@ -306,7 +306,7 @@ async def cancel( **(extra_headers or {}), } return await self._post( - "/alpha/eval/job/cancel", + "/v1/eval/job/cancel", body=await async_maybe_transform( { "job_id": job_id, @@ -354,7 +354,7 @@ async def status( **(extra_headers or {}), } return await self._get( - "/alpha/eval/job/status", + "/v1/eval/job/status", options=make_request_options( extra_headers=extra_headers, extra_query=extra_query, diff --git a/src/llama_stack_client/resources/eval_tasks.py b/src/llama_stack_client/resources/eval_tasks.py index 3466d617..9ee4f2cf 100644 --- a/src/llama_stack_client/resources/eval_tasks.py +++ b/src/llama_stack_client/resources/eval_tasks.py @@ -80,7 +80,7 @@ def retrieve( **(extra_headers or {}), } return self._get( - "/alpha/eval-tasks/get", + "/v1/eval-tasks/get", options=make_request_options( extra_headers=extra_headers, extra_query=extra_query, @@ -124,7 +124,7 @@ def list( **(extra_headers or {}), } return self._get( - "/alpha/eval-tasks/list", + "/v1/eval-tasks/list", options=make_request_options( extra_headers=extra_headers, extra_query=extra_query, extra_body=extra_body, timeout=timeout ), @@ -170,7 +170,7 @@ def register( **(extra_headers or {}), } return self._post( - "/alpha/eval-tasks/register", + "/v1/eval-tasks/register", body=maybe_transform( { "dataset_id": dataset_id, @@ -242,7 +242,7 @@ async def retrieve( **(extra_headers or {}), } return await self._get( - "/alpha/eval-tasks/get", + "/v1/eval-tasks/get", options=make_request_options( extra_headers=extra_headers, extra_query=extra_query, @@ -286,7 +286,7 @@ async def list( **(extra_headers or {}), } return await self._get( - "/alpha/eval-tasks/list", + "/v1/eval-tasks/list", options=make_request_options( extra_headers=extra_headers, extra_query=extra_query, extra_body=extra_body, timeout=timeout ), @@ -332,7 +332,7 @@ async def register( **(extra_headers or {}), } return await self._post( - "/alpha/eval-tasks/register", + "/v1/eval-tasks/register", body=await async_maybe_transform( { "dataset_id": dataset_id, diff --git a/src/llama_stack_client/resources/inference.py b/src/llama_stack_client/resources/inference.py index e5d80d99..96ca5f41 100644 --- a/src/llama_stack_client/resources/inference.py +++ b/src/llama_stack_client/resources/inference.py @@ -225,7 +225,7 @@ def chat_completion( return cast( InferenceChatCompletionResponse, self._post( - "/alpha/inference/chat-completion", + "/v1/inference/chat-completion", body=maybe_transform( { "messages": messages, @@ -376,7 +376,7 @@ def completion( return cast( InferenceCompletionResponse, self._post( - "/alpha/inference/completion", + "/v1/inference/completion", body=maybe_transform( { "content": content, @@ -433,7 +433,7 @@ def embeddings( **(extra_headers or {}), } return self._post( - "/alpha/inference/embeddings", + "/v1/inference/embeddings", body=maybe_transform( { "contents": contents, @@ -635,7 +635,7 @@ async def chat_completion( return cast( InferenceChatCompletionResponse, await self._post( - "/alpha/inference/chat-completion", + "/v1/inference/chat-completion", body=await async_maybe_transform( { "messages": messages, @@ -786,7 +786,7 @@ async def completion( return cast( InferenceCompletionResponse, await self._post( - "/alpha/inference/completion", + "/v1/inference/completion", body=await async_maybe_transform( { "content": content, @@ -843,7 +843,7 @@ async def embeddings( **(extra_headers or {}), } return await self._post( - "/alpha/inference/embeddings", + "/v1/inference/embeddings", body=await async_maybe_transform( { "contents": contents, diff --git a/src/llama_stack_client/resources/inspect.py b/src/llama_stack_client/resources/inspect.py index b4127c33..a307d2df 100644 --- a/src/llama_stack_client/resources/inspect.py +++ b/src/llama_stack_client/resources/inspect.py @@ -73,7 +73,7 @@ def health( **(extra_headers or {}), } return self._get( - "/alpha/health", + "/v1/health", options=make_request_options( extra_headers=extra_headers, extra_query=extra_query, extra_body=extra_body, timeout=timeout ), @@ -112,7 +112,7 @@ def version( **(extra_headers or {}), } return self._get( - "/alpha/version", + "/v1/version", options=make_request_options( extra_headers=extra_headers, extra_query=extra_query, extra_body=extra_body, timeout=timeout ), @@ -172,7 +172,7 @@ async def health( **(extra_headers or {}), } return await self._get( - "/alpha/health", + "/v1/health", options=make_request_options( extra_headers=extra_headers, extra_query=extra_query, extra_body=extra_body, timeout=timeout ), @@ -211,7 +211,7 @@ async def version( **(extra_headers or {}), } return await self._get( - "/alpha/version", + "/v1/version", options=make_request_options( extra_headers=extra_headers, extra_query=extra_query, extra_body=extra_body, timeout=timeout ), diff --git a/src/llama_stack_client/resources/memory.py b/src/llama_stack_client/resources/memory.py index 19a4ac0f..b5292704 100644 --- a/src/llama_stack_client/resources/memory.py +++ b/src/llama_stack_client/resources/memory.py @@ -84,7 +84,7 @@ def insert( **(extra_headers or {}), } return self._post( - "/alpha/memory/insert", + "/v1/memory/insert", body=maybe_transform( { "bank_id": bank_id, @@ -134,7 +134,7 @@ def query( **(extra_headers or {}), } return self._post( - "/alpha/memory/query", + "/v1/memory/query", body=maybe_transform( { "bank_id": bank_id, @@ -206,7 +206,7 @@ async def insert( **(extra_headers or {}), } return await self._post( - "/alpha/memory/insert", + "/v1/memory/insert", body=await async_maybe_transform( { "bank_id": bank_id, @@ -256,7 +256,7 @@ async def query( **(extra_headers or {}), } return await self._post( - "/alpha/memory/query", + "/v1/memory/query", body=await async_maybe_transform( { "bank_id": bank_id, diff --git a/src/llama_stack_client/resources/memory_banks.py b/src/llama_stack_client/resources/memory_banks.py index cede9a15..4aa7c2ca 100644 --- a/src/llama_stack_client/resources/memory_banks.py +++ b/src/llama_stack_client/resources/memory_banks.py @@ -27,6 +27,7 @@ ) from .._base_client import make_request_options from ..types.memory_bank_list_response import MemoryBankListResponse +from ..types.memory_bank_register_response import MemoryBankRegisterResponse from ..types.memory_bank_retrieve_response import MemoryBankRetrieveResponse __all__ = ["MemoryBanksResource", "AsyncMemoryBanksResource"] @@ -87,7 +88,7 @@ def retrieve( return cast( Optional[MemoryBankRetrieveResponse], self._get( - "/alpha/memory-banks/get", + "/v1/memory-banks/get", options=make_request_options( extra_headers=extra_headers, extra_query=extra_query, @@ -138,7 +139,7 @@ def list( return cast( MemoryBankListResponse, self._get( - "/alpha/memory-banks/list", + "/v1/memory-banks/list", options=make_request_options( extra_headers=extra_headers, extra_query=extra_query, extra_body=extra_body, timeout=timeout ), @@ -163,7 +164,7 @@ def register( extra_query: Query | None = None, extra_body: Body | None = None, timeout: float | httpx.Timeout | None | NotGiven = NOT_GIVEN, - ) -> None: + ) -> MemoryBankRegisterResponse: """ Args: extra_headers: Send extra headers @@ -174,7 +175,6 @@ def register( timeout: Override the client-level default timeout for this request, in seconds """ - extra_headers = {"Accept": "*/*", **(extra_headers or {})} extra_headers = { **strip_not_given( { @@ -184,21 +184,26 @@ def register( ), **(extra_headers or {}), } - return self._post( - "/alpha/memory-banks/register", - body=maybe_transform( - { - "memory_bank_id": memory_bank_id, - "params": params, - "provider_id": provider_id, - "provider_memory_bank_id": provider_memory_bank_id, - }, - memory_bank_register_params.MemoryBankRegisterParams, - ), - options=make_request_options( - extra_headers=extra_headers, extra_query=extra_query, extra_body=extra_body, timeout=timeout + return cast( + MemoryBankRegisterResponse, + self._post( + "/v1/memory-banks/register", + body=maybe_transform( + { + "memory_bank_id": memory_bank_id, + "params": params, + "provider_id": provider_id, + "provider_memory_bank_id": provider_memory_bank_id, + }, + memory_bank_register_params.MemoryBankRegisterParams, + ), + options=make_request_options( + extra_headers=extra_headers, extra_query=extra_query, extra_body=extra_body, timeout=timeout + ), + cast_to=cast( + Any, MemoryBankRegisterResponse + ), # Union types cannot be passed in as arguments in the type system ), - cast_to=NoneType, ) def unregister( @@ -235,7 +240,7 @@ def unregister( **(extra_headers or {}), } return self._post( - "/alpha/memory-banks/unregister", + "/v1/memory-banks/unregister", body=maybe_transform( {"memory_bank_id": memory_bank_id}, memory_bank_unregister_params.MemoryBankUnregisterParams ), @@ -301,7 +306,7 @@ async def retrieve( return cast( Optional[MemoryBankRetrieveResponse], await self._get( - "/alpha/memory-banks/get", + "/v1/memory-banks/get", options=make_request_options( extra_headers=extra_headers, extra_query=extra_query, @@ -352,7 +357,7 @@ async def list( return cast( MemoryBankListResponse, await self._get( - "/alpha/memory-banks/list", + "/v1/memory-banks/list", options=make_request_options( extra_headers=extra_headers, extra_query=extra_query, extra_body=extra_body, timeout=timeout ), @@ -377,7 +382,7 @@ async def register( extra_query: Query | None = None, extra_body: Body | None = None, timeout: float | httpx.Timeout | None | NotGiven = NOT_GIVEN, - ) -> None: + ) -> MemoryBankRegisterResponse: """ Args: extra_headers: Send extra headers @@ -388,7 +393,6 @@ async def register( timeout: Override the client-level default timeout for this request, in seconds """ - extra_headers = {"Accept": "*/*", **(extra_headers or {})} extra_headers = { **strip_not_given( { @@ -398,21 +402,26 @@ async def register( ), **(extra_headers or {}), } - return await self._post( - "/alpha/memory-banks/register", - body=await async_maybe_transform( - { - "memory_bank_id": memory_bank_id, - "params": params, - "provider_id": provider_id, - "provider_memory_bank_id": provider_memory_bank_id, - }, - memory_bank_register_params.MemoryBankRegisterParams, - ), - options=make_request_options( - extra_headers=extra_headers, extra_query=extra_query, extra_body=extra_body, timeout=timeout + return cast( + MemoryBankRegisterResponse, + await self._post( + "/v1/memory-banks/register", + body=await async_maybe_transform( + { + "memory_bank_id": memory_bank_id, + "params": params, + "provider_id": provider_id, + "provider_memory_bank_id": provider_memory_bank_id, + }, + memory_bank_register_params.MemoryBankRegisterParams, + ), + options=make_request_options( + extra_headers=extra_headers, extra_query=extra_query, extra_body=extra_body, timeout=timeout + ), + cast_to=cast( + Any, MemoryBankRegisterResponse + ), # Union types cannot be passed in as arguments in the type system ), - cast_to=NoneType, ) async def unregister( @@ -449,7 +458,7 @@ async def unregister( **(extra_headers or {}), } return await self._post( - "/alpha/memory-banks/unregister", + "/v1/memory-banks/unregister", body=await async_maybe_transform( {"memory_bank_id": memory_bank_id}, memory_bank_unregister_params.MemoryBankUnregisterParams ), diff --git a/src/llama_stack_client/resources/models.py b/src/llama_stack_client/resources/models.py index be5ab120..9fe03ccd 100644 --- a/src/llama_stack_client/resources/models.py +++ b/src/llama_stack_client/resources/models.py @@ -81,7 +81,7 @@ def retrieve( **(extra_headers or {}), } return self._get( - "/alpha/models/get", + "/v1/models/get", options=make_request_options( extra_headers=extra_headers, extra_query=extra_query, @@ -125,7 +125,7 @@ def list( **(extra_headers or {}), } return self._get( - "/alpha/models/list", + "/v1/models/list", options=make_request_options( extra_headers=extra_headers, extra_query=extra_query, extra_body=extra_body, timeout=timeout ), @@ -169,7 +169,7 @@ def register( **(extra_headers or {}), } return self._post( - "/alpha/models/register", + "/v1/models/register", body=maybe_transform( { "model_id": model_id, @@ -220,7 +220,7 @@ def unregister( **(extra_headers or {}), } return self._post( - "/alpha/models/unregister", + "/v1/models/unregister", body=maybe_transform({"model_id": model_id}, model_unregister_params.ModelUnregisterParams), options=make_request_options( extra_headers=extra_headers, extra_query=extra_query, extra_body=extra_body, timeout=timeout @@ -282,7 +282,7 @@ async def retrieve( **(extra_headers or {}), } return await self._get( - "/alpha/models/get", + "/v1/models/get", options=make_request_options( extra_headers=extra_headers, extra_query=extra_query, @@ -328,7 +328,7 @@ async def list( **(extra_headers or {}), } return await self._get( - "/alpha/models/list", + "/v1/models/list", options=make_request_options( extra_headers=extra_headers, extra_query=extra_query, extra_body=extra_body, timeout=timeout ), @@ -372,7 +372,7 @@ async def register( **(extra_headers or {}), } return await self._post( - "/alpha/models/register", + "/v1/models/register", body=await async_maybe_transform( { "model_id": model_id, @@ -423,7 +423,7 @@ async def unregister( **(extra_headers or {}), } return await self._post( - "/alpha/models/unregister", + "/v1/models/unregister", body=await async_maybe_transform({"model_id": model_id}, model_unregister_params.ModelUnregisterParams), options=make_request_options( extra_headers=extra_headers, extra_query=extra_query, extra_body=extra_body, timeout=timeout diff --git a/src/llama_stack_client/resources/post_training/job.py b/src/llama_stack_client/resources/post_training/job.py index 3b86ed0e..74b65c27 100644 --- a/src/llama_stack_client/resources/post_training/job.py +++ b/src/llama_stack_client/resources/post_training/job.py @@ -82,7 +82,7 @@ def list( **(extra_headers or {}), } return self._get( - "/alpha/post-training/jobs", + "/v1/post-training/jobs", options=make_request_options( extra_headers=extra_headers, extra_query=extra_query, extra_body=extra_body, timeout=timeout ), @@ -122,7 +122,7 @@ def artifacts( **(extra_headers or {}), } return self._get( - "/alpha/post-training/job/artifacts", + "/v1/post-training/job/artifacts", options=make_request_options( extra_headers=extra_headers, extra_query=extra_query, @@ -167,7 +167,7 @@ def cancel( **(extra_headers or {}), } return self._post( - "/alpha/post-training/job/cancel", + "/v1/post-training/job/cancel", body=maybe_transform({"job_uuid": job_uuid}, job_cancel_params.JobCancelParams), options=make_request_options( extra_headers=extra_headers, extra_query=extra_query, extra_body=extra_body, timeout=timeout @@ -208,7 +208,7 @@ def status( **(extra_headers or {}), } return self._get( - "/alpha/post-training/job/status", + "/v1/post-training/job/status", options=make_request_options( extra_headers=extra_headers, extra_query=extra_query, @@ -273,7 +273,7 @@ async def list( **(extra_headers or {}), } return await self._get( - "/alpha/post-training/jobs", + "/v1/post-training/jobs", options=make_request_options( extra_headers=extra_headers, extra_query=extra_query, extra_body=extra_body, timeout=timeout ), @@ -313,7 +313,7 @@ async def artifacts( **(extra_headers or {}), } return await self._get( - "/alpha/post-training/job/artifacts", + "/v1/post-training/job/artifacts", options=make_request_options( extra_headers=extra_headers, extra_query=extra_query, @@ -358,7 +358,7 @@ async def cancel( **(extra_headers or {}), } return await self._post( - "/alpha/post-training/job/cancel", + "/v1/post-training/job/cancel", body=await async_maybe_transform({"job_uuid": job_uuid}, job_cancel_params.JobCancelParams), options=make_request_options( extra_headers=extra_headers, extra_query=extra_query, extra_body=extra_body, timeout=timeout @@ -399,7 +399,7 @@ async def status( **(extra_headers or {}), } return await self._get( - "/alpha/post-training/job/status", + "/v1/post-training/job/status", options=make_request_options( extra_headers=extra_headers, extra_query=extra_query, diff --git a/src/llama_stack_client/resources/post_training/post_training.py b/src/llama_stack_client/resources/post_training/post_training.py index e2922813..36b4cd2a 100644 --- a/src/llama_stack_client/resources/post_training/post_training.py +++ b/src/llama_stack_client/resources/post_training/post_training.py @@ -97,7 +97,7 @@ def preference_optimize( **(extra_headers or {}), } return self._post( - "/alpha/post-training/preference-optimize", + "/v1/post-training/preference-optimize", body=maybe_transform( { "algorithm_config": algorithm_config, @@ -154,7 +154,7 @@ def supervised_fine_tune( **(extra_headers or {}), } return self._post( - "/alpha/post-training/supervised-fine-tune", + "/v1/post-training/supervised-fine-tune", body=maybe_transform( { "hyperparam_search_config": hyperparam_search_config, @@ -236,7 +236,7 @@ async def preference_optimize( **(extra_headers or {}), } return await self._post( - "/alpha/post-training/preference-optimize", + "/v1/post-training/preference-optimize", body=await async_maybe_transform( { "algorithm_config": algorithm_config, @@ -293,7 +293,7 @@ async def supervised_fine_tune( **(extra_headers or {}), } return await self._post( - "/alpha/post-training/supervised-fine-tune", + "/v1/post-training/supervised-fine-tune", body=await async_maybe_transform( { "hyperparam_search_config": hyperparam_search_config, diff --git a/src/llama_stack_client/resources/providers.py b/src/llama_stack_client/resources/providers.py index 9a228744..2b85dcde 100644 --- a/src/llama_stack_client/resources/providers.py +++ b/src/llama_stack_client/resources/providers.py @@ -72,7 +72,7 @@ def list( **(extra_headers or {}), } return self._get( - "/alpha/providers/list", + "/v1/providers/list", options=make_request_options( extra_headers=extra_headers, extra_query=extra_query, extra_body=extra_body, timeout=timeout ), @@ -132,7 +132,7 @@ async def list( **(extra_headers or {}), } return await self._get( - "/alpha/providers/list", + "/v1/providers/list", options=make_request_options( extra_headers=extra_headers, extra_query=extra_query, extra_body=extra_body, timeout=timeout ), diff --git a/src/llama_stack_client/resources/routes.py b/src/llama_stack_client/resources/routes.py index 8f8d4a25..c6ff989d 100644 --- a/src/llama_stack_client/resources/routes.py +++ b/src/llama_stack_client/resources/routes.py @@ -72,7 +72,7 @@ def list( **(extra_headers or {}), } return self._get( - "/alpha/routes/list", + "/v1/routes/list", options=make_request_options( extra_headers=extra_headers, extra_query=extra_query, extra_body=extra_body, timeout=timeout ), @@ -132,7 +132,7 @@ async def list( **(extra_headers or {}), } return await self._get( - "/alpha/routes/list", + "/v1/routes/list", options=make_request_options( extra_headers=extra_headers, extra_query=extra_query, extra_body=extra_body, timeout=timeout ), diff --git a/src/llama_stack_client/resources/safety.py b/src/llama_stack_client/resources/safety.py index 843f67c0..88128af6 100644 --- a/src/llama_stack_client/resources/safety.py +++ b/src/llama_stack_client/resources/safety.py @@ -82,7 +82,7 @@ def run_shield( **(extra_headers or {}), } return self._post( - "/alpha/safety/run-shield", + "/v1/safety/run-shield", body=maybe_transform( { "messages": messages, @@ -153,7 +153,7 @@ async def run_shield( **(extra_headers or {}), } return await self._post( - "/alpha/safety/run-shield", + "/v1/safety/run-shield", body=await async_maybe_transform( { "messages": messages, diff --git a/src/llama_stack_client/resources/scoring.py b/src/llama_stack_client/resources/scoring.py index 6e8cc3a6..8d2e7efb 100644 --- a/src/llama_stack_client/resources/scoring.py +++ b/src/llama_stack_client/resources/scoring.py @@ -82,7 +82,7 @@ def score( **(extra_headers or {}), } return self._post( - "/alpha/scoring/score", + "/v1/scoring/score", body=maybe_transform( { "input_rows": input_rows, @@ -131,7 +131,7 @@ def score_batch( **(extra_headers or {}), } return self._post( - "/alpha/scoring/score-batch", + "/v1/scoring/score-batch", body=maybe_transform( { "dataset_id": dataset_id, @@ -201,7 +201,7 @@ async def score( **(extra_headers or {}), } return await self._post( - "/alpha/scoring/score", + "/v1/scoring/score", body=await async_maybe_transform( { "input_rows": input_rows, @@ -250,7 +250,7 @@ async def score_batch( **(extra_headers or {}), } return await self._post( - "/alpha/scoring/score-batch", + "/v1/scoring/score-batch", body=await async_maybe_transform( { "dataset_id": dataset_id, diff --git a/src/llama_stack_client/resources/scoring_functions.py b/src/llama_stack_client/resources/scoring_functions.py index 8db31ead..2b46e592 100644 --- a/src/llama_stack_client/resources/scoring_functions.py +++ b/src/llama_stack_client/resources/scoring_functions.py @@ -81,7 +81,7 @@ def retrieve( **(extra_headers or {}), } return self._get( - "/alpha/scoring-functions/get", + "/v1/scoring-functions/get", options=make_request_options( extra_headers=extra_headers, extra_query=extra_query, @@ -127,7 +127,7 @@ def list( **(extra_headers or {}), } return self._get( - "/alpha/scoring-functions/list", + "/v1/scoring-functions/list", options=make_request_options( extra_headers=extra_headers, extra_query=extra_query, extra_body=extra_body, timeout=timeout ), @@ -173,7 +173,7 @@ def register( **(extra_headers or {}), } return self._post( - "/alpha/scoring-functions/register", + "/v1/scoring-functions/register", body=maybe_transform( { "description": description, @@ -245,7 +245,7 @@ async def retrieve( **(extra_headers or {}), } return await self._get( - "/alpha/scoring-functions/get", + "/v1/scoring-functions/get", options=make_request_options( extra_headers=extra_headers, extra_query=extra_query, @@ -291,7 +291,7 @@ async def list( **(extra_headers or {}), } return await self._get( - "/alpha/scoring-functions/list", + "/v1/scoring-functions/list", options=make_request_options( extra_headers=extra_headers, extra_query=extra_query, extra_body=extra_body, timeout=timeout ), @@ -337,7 +337,7 @@ async def register( **(extra_headers or {}), } return await self._post( - "/alpha/scoring-functions/register", + "/v1/scoring-functions/register", body=await async_maybe_transform( { "description": description, diff --git a/src/llama_stack_client/resources/shields.py b/src/llama_stack_client/resources/shields.py index 16f0c03e..07b85a8a 100644 --- a/src/llama_stack_client/resources/shields.py +++ b/src/llama_stack_client/resources/shields.py @@ -80,7 +80,7 @@ def retrieve( **(extra_headers or {}), } return self._get( - "/alpha/shields/get", + "/v1/shields/get", options=make_request_options( extra_headers=extra_headers, extra_query=extra_query, @@ -124,7 +124,7 @@ def list( **(extra_headers or {}), } return self._get( - "/alpha/shields/list", + "/v1/shields/list", options=make_request_options( extra_headers=extra_headers, extra_query=extra_query, extra_body=extra_body, timeout=timeout ), @@ -167,7 +167,7 @@ def register( **(extra_headers or {}), } return self._post( - "/alpha/shields/register", + "/v1/shields/register", body=maybe_transform( { "shield_id": shield_id, @@ -237,7 +237,7 @@ async def retrieve( **(extra_headers or {}), } return await self._get( - "/alpha/shields/get", + "/v1/shields/get", options=make_request_options( extra_headers=extra_headers, extra_query=extra_query, @@ -283,7 +283,7 @@ async def list( **(extra_headers or {}), } return await self._get( - "/alpha/shields/list", + "/v1/shields/list", options=make_request_options( extra_headers=extra_headers, extra_query=extra_query, extra_body=extra_body, timeout=timeout ), @@ -326,7 +326,7 @@ async def register( **(extra_headers or {}), } return await self._post( - "/alpha/shields/register", + "/v1/shields/register", body=await async_maybe_transform( { "shield_id": shield_id, diff --git a/src/llama_stack_client/resources/synthetic_data_generation.py b/src/llama_stack_client/resources/synthetic_data_generation.py index e93cccde..29151ce1 100644 --- a/src/llama_stack_client/resources/synthetic_data_generation.py +++ b/src/llama_stack_client/resources/synthetic_data_generation.py @@ -83,7 +83,7 @@ def generate( **(extra_headers or {}), } return self._post( - "/alpha/synthetic-data-generation/generate", + "/v1/synthetic-data-generation/generate", body=maybe_transform( { "dialogs": dialogs, @@ -154,7 +154,7 @@ async def generate( **(extra_headers or {}), } return await self._post( - "/alpha/synthetic-data-generation/generate", + "/v1/synthetic-data-generation/generate", body=await async_maybe_transform( { "dialogs": dialogs, diff --git a/src/llama_stack_client/resources/telemetry.py b/src/llama_stack_client/resources/telemetry.py index 3d45c1a6..0cb7b71f 100644 --- a/src/llama_stack_client/resources/telemetry.py +++ b/src/llama_stack_client/resources/telemetry.py @@ -90,7 +90,7 @@ def get_span_tree( **(extra_headers or {}), } return self._post( - "/alpha/telemetry/get-span-tree", + "/v1/telemetry/get-span-tree", body=maybe_transform( {"attributes_to_return": attributes_to_return}, telemetry_get_span_tree_params.TelemetryGetSpanTreeParams, @@ -146,7 +146,7 @@ def log_event( **(extra_headers or {}), } return self._post( - "/alpha/telemetry/log-event", + "/v1/telemetry/log-event", body=maybe_transform( { "event": event, @@ -196,7 +196,7 @@ def query_spans( **(extra_headers or {}), } return self._post( - "/alpha/telemetry/query-spans", + "/v1/telemetry/query-spans", body=maybe_transform( { "attribute_filters": attribute_filters, @@ -248,7 +248,7 @@ def query_traces( **(extra_headers or {}), } return self._post( - "/alpha/telemetry/query-traces", + "/v1/telemetry/query-traces", body=maybe_transform( { "attribute_filters": attribute_filters, @@ -301,7 +301,7 @@ def save_spans_to_dataset( **(extra_headers or {}), } return self._post( - "/alpha/telemetry/save-spans-to-dataset", + "/v1/telemetry/save-spans-to-dataset", body=maybe_transform( { "attribute_filters": attribute_filters, @@ -373,7 +373,7 @@ async def get_span_tree( **(extra_headers or {}), } return await self._post( - "/alpha/telemetry/get-span-tree", + "/v1/telemetry/get-span-tree", body=await async_maybe_transform( {"attributes_to_return": attributes_to_return}, telemetry_get_span_tree_params.TelemetryGetSpanTreeParams, @@ -429,7 +429,7 @@ async def log_event( **(extra_headers or {}), } return await self._post( - "/alpha/telemetry/log-event", + "/v1/telemetry/log-event", body=await async_maybe_transform( { "event": event, @@ -479,7 +479,7 @@ async def query_spans( **(extra_headers or {}), } return await self._post( - "/alpha/telemetry/query-spans", + "/v1/telemetry/query-spans", body=await async_maybe_transform( { "attribute_filters": attribute_filters, @@ -531,7 +531,7 @@ async def query_traces( **(extra_headers or {}), } return await self._post( - "/alpha/telemetry/query-traces", + "/v1/telemetry/query-traces", body=await async_maybe_transform( { "attribute_filters": attribute_filters, @@ -584,7 +584,7 @@ async def save_spans_to_dataset( **(extra_headers or {}), } return await self._post( - "/alpha/telemetry/save-spans-to-dataset", + "/v1/telemetry/save-spans-to-dataset", body=await async_maybe_transform( { "attribute_filters": attribute_filters, diff --git a/src/llama_stack_client/resources/tool_runtime.py b/src/llama_stack_client/resources/tool_runtime.py index 94d04db7..401896eb 100644 --- a/src/llama_stack_client/resources/tool_runtime.py +++ b/src/llama_stack_client/resources/tool_runtime.py @@ -85,7 +85,7 @@ def invoke_tool( **(extra_headers or {}), } return self._post( - "/alpha/tool-runtime/invoke", + "/v1/tool-runtime/invoke", body=maybe_transform( { "args": args, @@ -134,7 +134,7 @@ def list_tools( **(extra_headers or {}), } return self._post( - "/alpha/tool-runtime/list-tools", + "/v1/tool-runtime/list-tools", body=maybe_transform( {"mcp_endpoint": mcp_endpoint}, tool_runtime_list_tools_params.ToolRuntimeListToolsParams ), @@ -207,7 +207,7 @@ async def invoke_tool( **(extra_headers or {}), } return await self._post( - "/alpha/tool-runtime/invoke", + "/v1/tool-runtime/invoke", body=await async_maybe_transform( { "args": args, @@ -256,7 +256,7 @@ async def list_tools( **(extra_headers or {}), } return await self._post( - "/alpha/tool-runtime/list-tools", + "/v1/tool-runtime/list-tools", body=await async_maybe_transform( {"mcp_endpoint": mcp_endpoint}, tool_runtime_list_tools_params.ToolRuntimeListToolsParams ), diff --git a/src/llama_stack_client/resources/toolgroups.py b/src/llama_stack_client/resources/toolgroups.py index 437158a5..e2748f21 100644 --- a/src/llama_stack_client/resources/toolgroups.py +++ b/src/llama_stack_client/resources/toolgroups.py @@ -83,7 +83,7 @@ def list( **(extra_headers or {}), } return self._get( - "/alpha/toolgroups/list", + "/v1/toolgroups/list", options=make_request_options( extra_headers=extra_headers, extra_query=extra_query, extra_body=extra_body, timeout=timeout ), @@ -123,7 +123,7 @@ def get( **(extra_headers or {}), } return self._get( - "/alpha/toolgroups/get", + "/v1/toolgroups/get", options=make_request_options( extra_headers=extra_headers, extra_query=extra_query, @@ -173,7 +173,7 @@ def register( **(extra_headers or {}), } return self._post( - "/alpha/toolgroups/register", + "/v1/toolgroups/register", body=maybe_transform( { "provider_id": provider_id, @@ -225,7 +225,7 @@ def unregister( **(extra_headers or {}), } return self._post( - "/alpha/toolgroups/unregister", + "/v1/toolgroups/unregister", body=maybe_transform( {"tool_group_id": tool_group_id}, toolgroup_unregister_params.ToolgroupUnregisterParams ), @@ -291,7 +291,7 @@ async def list( **(extra_headers or {}), } return await self._get( - "/alpha/toolgroups/list", + "/v1/toolgroups/list", options=make_request_options( extra_headers=extra_headers, extra_query=extra_query, extra_body=extra_body, timeout=timeout ), @@ -331,7 +331,7 @@ async def get( **(extra_headers or {}), } return await self._get( - "/alpha/toolgroups/get", + "/v1/toolgroups/get", options=make_request_options( extra_headers=extra_headers, extra_query=extra_query, @@ -383,7 +383,7 @@ async def register( **(extra_headers or {}), } return await self._post( - "/alpha/toolgroups/register", + "/v1/toolgroups/register", body=await async_maybe_transform( { "provider_id": provider_id, @@ -435,7 +435,7 @@ async def unregister( **(extra_headers or {}), } return await self._post( - "/alpha/toolgroups/unregister", + "/v1/toolgroups/unregister", body=await async_maybe_transform( {"tool_group_id": tool_group_id}, toolgroup_unregister_params.ToolgroupUnregisterParams ), diff --git a/src/llama_stack_client/resources/tools.py b/src/llama_stack_client/resources/tools.py index 29a7dbd1..cb7d434e 100644 --- a/src/llama_stack_client/resources/tools.py +++ b/src/llama_stack_client/resources/tools.py @@ -81,7 +81,7 @@ def list( **(extra_headers or {}), } return self._get( - "/alpha/tools/list", + "/v1/tools/list", options=make_request_options( extra_headers=extra_headers, extra_query=extra_query, @@ -125,7 +125,7 @@ def get( **(extra_headers or {}), } return self._get( - "/alpha/tools/get", + "/v1/tools/get", options=make_request_options( extra_headers=extra_headers, extra_query=extra_query, @@ -193,7 +193,7 @@ async def list( **(extra_headers or {}), } return await self._get( - "/alpha/tools/list", + "/v1/tools/list", options=make_request_options( extra_headers=extra_headers, extra_query=extra_query, @@ -237,7 +237,7 @@ async def get( **(extra_headers or {}), } return await self._get( - "/alpha/tools/get", + "/v1/tools/get", options=make_request_options( extra_headers=extra_headers, extra_query=extra_query, diff --git a/src/llama_stack_client/types/__init__.py b/src/llama_stack_client/types/__init__.py index c141c4db..cb9cf18d 100644 --- a/src/llama_stack_client/types/__init__.py +++ b/src/llama_stack_client/types/__init__.py @@ -89,6 +89,7 @@ from .scoring_score_batch_response import ScoringScoreBatchResponse as ScoringScoreBatchResponse from .telemetry_query_spans_params import TelemetryQuerySpansParams as TelemetryQuerySpansParams from .inference_completion_response import InferenceCompletionResponse as InferenceCompletionResponse +from .memory_bank_register_response import MemoryBankRegisterResponse as MemoryBankRegisterResponse from .memory_bank_retrieve_response import MemoryBankRetrieveResponse as MemoryBankRetrieveResponse from .memory_bank_unregister_params import MemoryBankUnregisterParams as MemoryBankUnregisterParams from .telemetry_query_traces_params import TelemetryQueryTracesParams as TelemetryQueryTracesParams diff --git a/src/llama_stack_client/types/memory_bank_register_response.py b/src/llama_stack_client/types/memory_bank_register_response.py new file mode 100644 index 00000000..391a5f28 --- /dev/null +++ b/src/llama_stack_client/types/memory_bank_register_response.py @@ -0,0 +1,73 @@ +# File generated from our OpenAPI spec by Stainless. See CONTRIBUTING.md for details. + +from typing import Union, Optional +from typing_extensions import Literal, TypeAlias + +from .._models import BaseModel + +__all__ = [ + "MemoryBankRegisterResponse", + "VectorMemoryBank", + "KeyValueMemoryBank", + "KeywordMemoryBank", + "GraphMemoryBank", +] + + +class VectorMemoryBank(BaseModel): + chunk_size_in_tokens: int + + embedding_model: str + + identifier: str + + memory_bank_type: Literal["vector"] + + provider_id: str + + provider_resource_id: str + + type: Literal["memory_bank"] + + embedding_dimension: Optional[int] = None + + overlap_size_in_tokens: Optional[int] = None + + +class KeyValueMemoryBank(BaseModel): + identifier: str + + memory_bank_type: Literal["keyvalue"] + + provider_id: str + + provider_resource_id: str + + type: Literal["memory_bank"] + + +class KeywordMemoryBank(BaseModel): + identifier: str + + memory_bank_type: Literal["keyword"] + + provider_id: str + + provider_resource_id: str + + type: Literal["memory_bank"] + + +class GraphMemoryBank(BaseModel): + identifier: str + + memory_bank_type: Literal["graph"] + + provider_id: str + + provider_resource_id: str + + type: Literal["memory_bank"] + + +MemoryBankRegisterResponse: TypeAlias = Union[VectorMemoryBank, KeyValueMemoryBank, KeywordMemoryBank, GraphMemoryBank] diff --git a/src/llama_stack_client/types/post_training_preference_optimize_params.py b/src/llama_stack_client/types/post_training_preference_optimize_params.py index 49986aef..33540e88 100644 --- a/src/llama_stack_client/types/post_training_preference_optimize_params.py +++ b/src/llama_stack_client/types/post_training_preference_optimize_params.py @@ -48,6 +48,8 @@ class AlgorithmConfig(TypedDict, total=False): class TrainingConfigDataConfig(TypedDict, total=False): batch_size: Required[int] + data_format: Required[Literal["instruct", "dialog"]] + dataset_id: Required[str] shuffle: Required[bool] diff --git a/src/llama_stack_client/types/post_training_supervised_fine_tune_params.py b/src/llama_stack_client/types/post_training_supervised_fine_tune_params.py index 855efbda..d3c3437a 100644 --- a/src/llama_stack_client/types/post_training_supervised_fine_tune_params.py +++ b/src/llama_stack_client/types/post_training_supervised_fine_tune_params.py @@ -42,6 +42,8 @@ class PostTrainingSupervisedFineTuneParams(TypedDict, total=False): class TrainingConfigDataConfig(TypedDict, total=False): batch_size: Required[int] + data_format: Required[Literal["instruct", "dialog"]] + dataset_id: Required[str] shuffle: Required[bool] diff --git a/src/llama_stack_client/types/shared/content_delta.py b/src/llama_stack_client/types/shared/content_delta.py index f4f03a68..7985f4b3 100644 --- a/src/llama_stack_client/types/shared/content_delta.py +++ b/src/llama_stack_client/types/shared/content_delta.py @@ -6,16 +6,16 @@ from ..._models import BaseModel from .tool_call import ToolCall -__all__ = ["ContentDelta", "UnionMember0", "UnionMember1", "ToolCallDelta", "ToolCallDeltaContent"] +__all__ = ["ContentDelta", "TextDelta", "ImageDelta", "ToolCallDelta", "ToolCallDeltaContent"] -class UnionMember0(BaseModel): +class TextDelta(BaseModel): text: str type: Literal["text"] -class UnionMember1(BaseModel): +class ImageDelta(BaseModel): data: str type: Literal["image"] @@ -32,4 +32,4 @@ class ToolCallDelta(BaseModel): type: Literal["tool_call"] -ContentDelta: TypeAlias = Union[UnionMember0, UnionMember1, ToolCallDelta] +ContentDelta: TypeAlias = Union[TextDelta, ImageDelta, ToolCallDelta] diff --git a/tests/api_resources/test_memory_banks.py b/tests/api_resources/test_memory_banks.py index 88fa402c..697c4a16 100644 --- a/tests/api_resources/test_memory_banks.py +++ b/tests/api_resources/test_memory_banks.py @@ -11,6 +11,7 @@ from llama_stack_client import LlamaStackClient, AsyncLlamaStackClient from llama_stack_client.types import ( MemoryBankListResponse, + MemoryBankRegisterResponse, MemoryBankRetrieveResponse, ) @@ -115,7 +116,7 @@ def test_method_register(self, client: LlamaStackClient) -> None: "memory_bank_type": "vector", }, ) - assert memory_bank is None + assert_matches_type(MemoryBankRegisterResponse, memory_bank, path=["response"]) @parametrize def test_method_register_with_all_params(self, client: LlamaStackClient) -> None: @@ -132,7 +133,7 @@ def test_method_register_with_all_params(self, client: LlamaStackClient) -> None x_llama_stack_client_version="X-LlamaStack-Client-Version", x_llama_stack_provider_data="X-LlamaStack-Provider-Data", ) - assert memory_bank is None + assert_matches_type(MemoryBankRegisterResponse, memory_bank, path=["response"]) @parametrize def test_raw_response_register(self, client: LlamaStackClient) -> None: @@ -148,7 +149,7 @@ def test_raw_response_register(self, client: LlamaStackClient) -> None: assert response.is_closed is True assert response.http_request.headers.get("X-Stainless-Lang") == "python" memory_bank = response.parse() - assert memory_bank is None + assert_matches_type(MemoryBankRegisterResponse, memory_bank, path=["response"]) @parametrize def test_streaming_response_register(self, client: LlamaStackClient) -> None: @@ -164,7 +165,7 @@ def test_streaming_response_register(self, client: LlamaStackClient) -> None: assert response.http_request.headers.get("X-Stainless-Lang") == "python" memory_bank = response.parse() - assert memory_bank is None + assert_matches_type(MemoryBankRegisterResponse, memory_bank, path=["response"]) assert cast(Any, response.is_closed) is True @@ -307,7 +308,7 @@ async def test_method_register(self, async_client: AsyncLlamaStackClient) -> Non "memory_bank_type": "vector", }, ) - assert memory_bank is None + assert_matches_type(MemoryBankRegisterResponse, memory_bank, path=["response"]) @parametrize async def test_method_register_with_all_params(self, async_client: AsyncLlamaStackClient) -> None: @@ -324,7 +325,7 @@ async def test_method_register_with_all_params(self, async_client: AsyncLlamaSta x_llama_stack_client_version="X-LlamaStack-Client-Version", x_llama_stack_provider_data="X-LlamaStack-Provider-Data", ) - assert memory_bank is None + assert_matches_type(MemoryBankRegisterResponse, memory_bank, path=["response"]) @parametrize async def test_raw_response_register(self, async_client: AsyncLlamaStackClient) -> None: @@ -340,7 +341,7 @@ async def test_raw_response_register(self, async_client: AsyncLlamaStackClient) assert response.is_closed is True assert response.http_request.headers.get("X-Stainless-Lang") == "python" memory_bank = await response.parse() - assert memory_bank is None + assert_matches_type(MemoryBankRegisterResponse, memory_bank, path=["response"]) @parametrize async def test_streaming_response_register(self, async_client: AsyncLlamaStackClient) -> None: @@ -356,7 +357,7 @@ async def test_streaming_response_register(self, async_client: AsyncLlamaStackCl assert response.http_request.headers.get("X-Stainless-Lang") == "python" memory_bank = await response.parse() - assert memory_bank is None + assert_matches_type(MemoryBankRegisterResponse, memory_bank, path=["response"]) assert cast(Any, response.is_closed) is True diff --git a/tests/api_resources/test_post_training.py b/tests/api_resources/test_post_training.py index 71f48a40..68041f24 100644 --- a/tests/api_resources/test_post_training.py +++ b/tests/api_resources/test_post_training.py @@ -35,6 +35,7 @@ def test_method_preference_optimize(self, client: LlamaStackClient) -> None: training_config={ "data_config": { "batch_size": 0, + "data_format": "instruct", "dataset_id": "dataset_id", "shuffle": True, }, @@ -68,6 +69,7 @@ def test_method_preference_optimize_with_all_params(self, client: LlamaStackClie training_config={ "data_config": { "batch_size": 0, + "data_format": "instruct", "dataset_id": "dataset_id", "shuffle": True, "packed": True, @@ -113,6 +115,7 @@ def test_raw_response_preference_optimize(self, client: LlamaStackClient) -> Non training_config={ "data_config": { "batch_size": 0, + "data_format": "instruct", "dataset_id": "dataset_id", "shuffle": True, }, @@ -150,6 +153,7 @@ def test_streaming_response_preference_optimize(self, client: LlamaStackClient) training_config={ "data_config": { "batch_size": 0, + "data_format": "instruct", "dataset_id": "dataset_id", "shuffle": True, }, @@ -183,6 +187,7 @@ def test_method_supervised_fine_tune(self, client: LlamaStackClient) -> None: training_config={ "data_config": { "batch_size": 0, + "data_format": "instruct", "dataset_id": "dataset_id", "shuffle": True, }, @@ -210,6 +215,7 @@ def test_method_supervised_fine_tune_with_all_params(self, client: LlamaStackCli training_config={ "data_config": { "batch_size": 0, + "data_format": "instruct", "dataset_id": "dataset_id", "shuffle": True, "packed": True, @@ -260,6 +266,7 @@ def test_raw_response_supervised_fine_tune(self, client: LlamaStackClient) -> No training_config={ "data_config": { "batch_size": 0, + "data_format": "instruct", "dataset_id": "dataset_id", "shuffle": True, }, @@ -291,6 +298,7 @@ def test_streaming_response_supervised_fine_tune(self, client: LlamaStackClient) training_config={ "data_config": { "batch_size": 0, + "data_format": "instruct", "dataset_id": "dataset_id", "shuffle": True, }, @@ -334,6 +342,7 @@ async def test_method_preference_optimize(self, async_client: AsyncLlamaStackCli training_config={ "data_config": { "batch_size": 0, + "data_format": "instruct", "dataset_id": "dataset_id", "shuffle": True, }, @@ -367,6 +376,7 @@ async def test_method_preference_optimize_with_all_params(self, async_client: As training_config={ "data_config": { "batch_size": 0, + "data_format": "instruct", "dataset_id": "dataset_id", "shuffle": True, "packed": True, @@ -412,6 +422,7 @@ async def test_raw_response_preference_optimize(self, async_client: AsyncLlamaSt training_config={ "data_config": { "batch_size": 0, + "data_format": "instruct", "dataset_id": "dataset_id", "shuffle": True, }, @@ -449,6 +460,7 @@ async def test_streaming_response_preference_optimize(self, async_client: AsyncL training_config={ "data_config": { "batch_size": 0, + "data_format": "instruct", "dataset_id": "dataset_id", "shuffle": True, }, @@ -482,6 +494,7 @@ async def test_method_supervised_fine_tune(self, async_client: AsyncLlamaStackCl training_config={ "data_config": { "batch_size": 0, + "data_format": "instruct", "dataset_id": "dataset_id", "shuffle": True, }, @@ -509,6 +522,7 @@ async def test_method_supervised_fine_tune_with_all_params(self, async_client: A training_config={ "data_config": { "batch_size": 0, + "data_format": "instruct", "dataset_id": "dataset_id", "shuffle": True, "packed": True, @@ -559,6 +573,7 @@ async def test_raw_response_supervised_fine_tune(self, async_client: AsyncLlamaS training_config={ "data_config": { "batch_size": 0, + "data_format": "instruct", "dataset_id": "dataset_id", "shuffle": True, }, @@ -590,6 +605,7 @@ async def test_streaming_response_supervised_fine_tune(self, async_client: Async training_config={ "data_config": { "batch_size": 0, + "data_format": "instruct", "dataset_id": "dataset_id", "shuffle": True, }, diff --git a/tests/test_client.py b/tests/test_client.py index 921151ef..ef74b88a 100644 --- a/tests/test_client.py +++ b/tests/test_client.py @@ -675,13 +675,11 @@ def test_parse_retry_after_header(self, remaining_retries: int, retry_after: str @mock.patch("llama_stack_client._base_client.BaseClient._calculate_retry_timeout", _low_retry_timeout) @pytest.mark.respx(base_url=base_url) def test_retrying_timeout_errors_doesnt_leak(self, respx_mock: MockRouter) -> None: - respx_mock.post("/alpha/inference/chat-completion").mock( - side_effect=httpx.TimeoutException("Test timeout error") - ) + respx_mock.post("/v1/inference/chat-completion").mock(side_effect=httpx.TimeoutException("Test timeout error")) with pytest.raises(APITimeoutError): self.client.post( - "/alpha/inference/chat-completion", + "/v1/inference/chat-completion", body=cast( object, dict( @@ -703,11 +701,11 @@ def test_retrying_timeout_errors_doesnt_leak(self, respx_mock: MockRouter) -> No @mock.patch("llama_stack_client._base_client.BaseClient._calculate_retry_timeout", _low_retry_timeout) @pytest.mark.respx(base_url=base_url) def test_retrying_status_errors_doesnt_leak(self, respx_mock: MockRouter) -> None: - respx_mock.post("/alpha/inference/chat-completion").mock(return_value=httpx.Response(500)) + respx_mock.post("/v1/inference/chat-completion").mock(return_value=httpx.Response(500)) with pytest.raises(APIStatusError): self.client.post( - "/alpha/inference/chat-completion", + "/v1/inference/chat-completion", body=cast( object, dict( @@ -750,7 +748,7 @@ def retry_handler(_request: httpx.Request) -> httpx.Response: return httpx.Response(500) return httpx.Response(200) - respx_mock.post("/alpha/inference/chat-completion").mock(side_effect=retry_handler) + respx_mock.post("/v1/inference/chat-completion").mock(side_effect=retry_handler) response = client.inference.with_raw_response.chat_completion( messages=[ @@ -782,7 +780,7 @@ def retry_handler(_request: httpx.Request) -> httpx.Response: return httpx.Response(500) return httpx.Response(200) - respx_mock.post("/alpha/inference/chat-completion").mock(side_effect=retry_handler) + respx_mock.post("/v1/inference/chat-completion").mock(side_effect=retry_handler) response = client.inference.with_raw_response.chat_completion( messages=[ @@ -814,7 +812,7 @@ def retry_handler(_request: httpx.Request) -> httpx.Response: return httpx.Response(500) return httpx.Response(200) - respx_mock.post("/alpha/inference/chat-completion").mock(side_effect=retry_handler) + respx_mock.post("/v1/inference/chat-completion").mock(side_effect=retry_handler) response = client.inference.with_raw_response.chat_completion( messages=[ @@ -1462,13 +1460,11 @@ async def test_parse_retry_after_header(self, remaining_retries: int, retry_afte @mock.patch("llama_stack_client._base_client.BaseClient._calculate_retry_timeout", _low_retry_timeout) @pytest.mark.respx(base_url=base_url) async def test_retrying_timeout_errors_doesnt_leak(self, respx_mock: MockRouter) -> None: - respx_mock.post("/alpha/inference/chat-completion").mock( - side_effect=httpx.TimeoutException("Test timeout error") - ) + respx_mock.post("/v1/inference/chat-completion").mock(side_effect=httpx.TimeoutException("Test timeout error")) with pytest.raises(APITimeoutError): await self.client.post( - "/alpha/inference/chat-completion", + "/v1/inference/chat-completion", body=cast( object, dict( @@ -1490,11 +1486,11 @@ async def test_retrying_timeout_errors_doesnt_leak(self, respx_mock: MockRouter) @mock.patch("llama_stack_client._base_client.BaseClient._calculate_retry_timeout", _low_retry_timeout) @pytest.mark.respx(base_url=base_url) async def test_retrying_status_errors_doesnt_leak(self, respx_mock: MockRouter) -> None: - respx_mock.post("/alpha/inference/chat-completion").mock(return_value=httpx.Response(500)) + respx_mock.post("/v1/inference/chat-completion").mock(return_value=httpx.Response(500)) with pytest.raises(APIStatusError): await self.client.post( - "/alpha/inference/chat-completion", + "/v1/inference/chat-completion", body=cast( object, dict( @@ -1538,7 +1534,7 @@ def retry_handler(_request: httpx.Request) -> httpx.Response: return httpx.Response(500) return httpx.Response(200) - respx_mock.post("/alpha/inference/chat-completion").mock(side_effect=retry_handler) + respx_mock.post("/v1/inference/chat-completion").mock(side_effect=retry_handler) response = await client.inference.with_raw_response.chat_completion( messages=[ @@ -1571,7 +1567,7 @@ def retry_handler(_request: httpx.Request) -> httpx.Response: return httpx.Response(500) return httpx.Response(200) - respx_mock.post("/alpha/inference/chat-completion").mock(side_effect=retry_handler) + respx_mock.post("/v1/inference/chat-completion").mock(side_effect=retry_handler) response = await client.inference.with_raw_response.chat_completion( messages=[ @@ -1604,7 +1600,7 @@ def retry_handler(_request: httpx.Request) -> httpx.Response: return httpx.Response(500) return httpx.Response(200) - respx_mock.post("/alpha/inference/chat-completion").mock(side_effect=retry_handler) + respx_mock.post("/v1/inference/chat-completion").mock(side_effect=retry_handler) response = await client.inference.with_raw_response.chat_completion( messages=[ @@ -1631,7 +1627,7 @@ def test_get_platform(self) -> None: import threading from llama_stack_client._utils import asyncify - from llama_stack_client._base_client import get_platform + from llama_stack_client._base_client import get_platform async def test_main() -> None: result = await asyncify(get_platform)() From c1f7828549d4ab9b4c53b7a7db693713227bc724 Mon Sep 17 00:00:00 2001 From: Xi Yan Date: Wed, 15 Jan 2025 11:13:44 -0800 Subject: [PATCH 2/2] precommit & fix --- src/llama_stack_client/_client.py | 3 +-- tests/test_client.py | 2 +- 2 files changed, 2 insertions(+), 3 deletions(-) diff --git a/src/llama_stack_client/_client.py b/src/llama_stack_client/_client.py index 25d14254..429826ad 100644 --- a/src/llama_stack_client/_client.py +++ b/src/llama_stack_client/_client.py @@ -1,8 +1,7 @@ # File generated from our OpenAPI spec by Stainless. See CONTRIBUTING.md for details. - -import json from __future__ import annotations +import json import os from typing import Any, Union, Mapping from typing_extensions import Self, override diff --git a/tests/test_client.py b/tests/test_client.py index ef74b88a..3fb2935f 100644 --- a/tests/test_client.py +++ b/tests/test_client.py @@ -1627,7 +1627,7 @@ def test_get_platform(self) -> None: import threading from llama_stack_client._utils import asyncify - from llama_stack_client._base_client import get_platform + from llama_stack_client._base_client import get_platform async def test_main() -> None: result = await asyncify(get_platform)()