From e391af5b47f10ca2c3fa7d36cacae1900af711b4 Mon Sep 17 00:00:00 2001 From: "stainless-app[bot]" <142633134+stainless-app[bot]@users.noreply.github.com> Date: Tue, 4 Nov 2025 02:01:56 +0000 Subject: [PATCH 1/2] feat(api): remove openai/v1 endpoints --- .stats.yml | 8 +- README.md | 51 ++++- api.md | 35 +-- src/llama_stack_client/_client.py | 47 ---- src/llama_stack_client/resources/__init__.py | 14 -- .../resources/models/models.py | 23 +- .../resources/models/openai.py | 18 +- .../resources/synthetic_data_generation.py | 205 ------------------ src/llama_stack_client/types/__init__.py | 7 +- src/llama_stack_client/types/model.py | 21 +- .../types/model_list_response.py | 24 +- .../types/model_register_response.py | 30 +++ .../types/model_retrieve_response.py | 30 +++ .../types/models/__init__.py | 2 - .../types/models/openai_list_response.py | 10 - .../types/shared/__init__.py | 1 - .../types/shared/message.py | 22 -- .../types/shared_params/__init__.py | 3 - .../types/shared_params/completion_message.py | 38 ---- .../types/shared_params/message.py | 21 -- .../types/shared_params/tool_call.py | 22 -- ...nthetic_data_generation_generate_params.py | 31 --- .../synthetic_data_generation_response.py | 24 -- tests/api_resources/models/test_openai.py | 14 +- tests/api_resources/test_models.py | 34 +-- .../test_synthetic_data_generation.py | 158 -------------- 26 files changed, 174 insertions(+), 719 deletions(-) delete mode 100644 src/llama_stack_client/resources/synthetic_data_generation.py create mode 100644 src/llama_stack_client/types/model_register_response.py create mode 100644 src/llama_stack_client/types/model_retrieve_response.py delete mode 100644 src/llama_stack_client/types/models/openai_list_response.py delete mode 100644 src/llama_stack_client/types/shared/message.py delete mode 100644 src/llama_stack_client/types/shared_params/completion_message.py delete mode 100644 src/llama_stack_client/types/shared_params/message.py delete mode 100644 src/llama_stack_client/types/shared_params/tool_call.py delete mode 100644 src/llama_stack_client/types/synthetic_data_generation_generate_params.py delete mode 100644 src/llama_stack_client/types/synthetic_data_generation_response.py delete mode 100644 tests/api_resources/test_synthetic_data_generation.py diff --git a/.stats.yml b/.stats.yml index 29bc5044..8df73aad 100644 --- a/.stats.yml +++ b/.stats.yml @@ -1,4 +1,4 @@ -configured_endpoints: 112 -openapi_spec_url: https://storage.googleapis.com/stainless-sdk-openapi-specs/llamastack%2Fllama-stack-client-a9f69d4a5f5d9bf957497cac83fdad1f72c8a44614098447762c53883e8bd987.yml -openapi_spec_hash: 75de5bdff8e70591d6033b609fc24e5d -config_hash: 34558d5f6e265184d712d43e231eb693 +configured_endpoints: 110 +openapi_spec_url: https://storage.googleapis.com/stainless-sdk-openapi-specs/llamastack%2Fllama-stack-client-d95665c12a4155ef6ae80f76545152ac241d3ccab18148e4add99c0f528b9634.yml +openapi_spec_hash: b6073c3436942c3ea6cd6c23f71a1cc4 +config_hash: 597b56196f814dd58c2cb2465aab9c9e diff --git a/README.md b/README.md index ceb18678..44184d41 100644 --- a/README.md +++ b/README.md @@ -31,16 +31,12 @@ The full API of this library can be found in [api.md](api.md). You may find basi ```python from llama_stack_client import LlamaStackClient -client = LlamaStackClient( - base_url=f"http://{host}:{port}", -) +client = LlamaStackClient() -response = client.chat.completions.create( - messages=[{"role": "user", "content": "hello world, write me a 2 sentence poem about the moon"}], - model="meta-llama/Llama-3.2-3B-Instruct", - stream=False, +response = client.models.register( + model_id="model_id", ) -print(response) +print(response.identifier) ``` While you can provide an `api_key` keyword argument, we recommend using [python-dotenv](https://pypi.org/project/python-dotenv/) to add `LLAMA_STACK_CLIENT_API_KEY="My API Key"` to your `.env` file so that your API Key is not stored in source control. @@ -97,11 +93,10 @@ client = AsyncLlamaStackClient( async def main() -> None: - session = await client.agents.sessions.create( - agent_id="agent_id", - session_name="session_name", + response = await client.models.register( + model_id="model_id", ) - print(session.session_id) + print(response.identifier) asyncio.run(main()) @@ -109,6 +104,38 @@ asyncio.run(main()) Functionality between the synchronous and asynchronous clients is otherwise identical. +### With aiohttp + +By default, the async client uses `httpx` for HTTP requests. However, for improved concurrency performance you may also use `aiohttp` as the HTTP backend. + +You can enable this by installing `aiohttp`: + +```sh +# install from PyPI +pip install --pre llama_stack_client[aiohttp] +``` + +Then you can enable it by instantiating the client with `http_client=DefaultAioHttpClient()`: + +```python +import asyncio +from llama_stack_client import DefaultAioHttpClient +from llama_stack_client import AsyncLlamaStackClient + + +async def main() -> None: + async with AsyncLlamaStackClient( + http_client=DefaultAioHttpClient(), + ) as client: + response = await client.models.register( + model_id="model_id", + ) + print(response.identifier) + + +asyncio.run(main()) +``` + ## Streaming responses We provide support for streaming responses using Server Side Events (SSE). diff --git a/api.md b/api.md index bd1949f8..f57f325f 100644 --- a/api.md +++ b/api.md @@ -7,7 +7,6 @@ from llama_stack_client.types import ( Document, InterleavedContent, InterleavedContentItem, - Message, ParamType, QueryConfig, QueryResult, @@ -300,27 +299,27 @@ Methods: Types: ```python -from llama_stack_client.types import ListModelsResponse, Model, ModelListResponse +from llama_stack_client.types import ( + ListModelsResponse, + Model, + ModelRetrieveResponse, + ModelListResponse, + ModelRegisterResponse, +) ``` Methods: -- client.models.retrieve(model_id) -> Model -- client.models.list() -> ModelListResponse -- client.models.register(\*\*params) -> Model +- client.models.retrieve(model_id) -> ModelRetrieveResponse +- client.models.list() -> ModelListResponse +- client.models.register(\*\*params) -> ModelRegisterResponse - client.models.unregister(model_id) -> None ## OpenAI -Types: - -```python -from llama_stack_client.types.models import OpenAIListResponse -``` - Methods: -- client.models.openai.list() -> OpenAIListResponse +- client.models.openai.list() -> ModelListResponse # Providers @@ -386,18 +385,6 @@ Methods: - client.shields.delete(identifier) -> None - client.shields.register(\*\*params) -> Shield -# SyntheticDataGeneration - -Types: - -```python -from llama_stack_client.types import SyntheticDataGenerationResponse -``` - -Methods: - -- client.synthetic_data_generation.generate(\*\*params) -> SyntheticDataGenerationResponse - # Scoring Types: diff --git a/src/llama_stack_client/_client.py b/src/llama_stack_client/_client.py index b1880a7e..d42e6fb0 100644 --- a/src/llama_stack_client/_client.py +++ b/src/llama_stack_client/_client.py @@ -62,7 +62,6 @@ conversations, vector_stores, scoring_functions, - synthetic_data_generation, ) from .resources.files import FilesResource, AsyncFilesResource from .resources.tools import ToolsResource, AsyncToolsResource @@ -84,10 +83,6 @@ from .resources.prompts.prompts import PromptsResource, AsyncPromptsResource from .resources.scoring_functions import ScoringFunctionsResource, AsyncScoringFunctionsResource from .resources.responses.responses import ResponsesResource, AsyncResponsesResource - from .resources.synthetic_data_generation import ( - SyntheticDataGenerationResource, - AsyncSyntheticDataGenerationResource, - ) from .resources.tool_runtime.tool_runtime import ToolRuntimeResource, AsyncToolRuntimeResource from .resources.conversations.conversations import ConversationsResource, AsyncConversationsResource from .resources.vector_stores.vector_stores import VectorStoresResource, AsyncVectorStoresResource @@ -269,12 +264,6 @@ def shields(self) -> ShieldsResource: return ShieldsResource(self) - @cached_property - def synthetic_data_generation(self) -> SyntheticDataGenerationResource: - from .resources.synthetic_data_generation import SyntheticDataGenerationResource - - return SyntheticDataGenerationResource(self) - @cached_property def scoring(self) -> ScoringResource: from .resources.scoring import ScoringResource @@ -585,12 +574,6 @@ def shields(self) -> AsyncShieldsResource: return AsyncShieldsResource(self) - @cached_property - def synthetic_data_generation(self) -> AsyncSyntheticDataGenerationResource: - from .resources.synthetic_data_generation import AsyncSyntheticDataGenerationResource - - return AsyncSyntheticDataGenerationResource(self) - @cached_property def scoring(self) -> AsyncScoringResource: from .resources.scoring import AsyncScoringResource @@ -850,12 +833,6 @@ def shields(self) -> shields.ShieldsResourceWithRawResponse: return ShieldsResourceWithRawResponse(self._client.shields) - @cached_property - def synthetic_data_generation(self) -> synthetic_data_generation.SyntheticDataGenerationResourceWithRawResponse: - from .resources.synthetic_data_generation import SyntheticDataGenerationResourceWithRawResponse - - return SyntheticDataGenerationResourceWithRawResponse(self._client.synthetic_data_generation) - @cached_property def scoring(self) -> scoring.ScoringResourceWithRawResponse: from .resources.scoring import ScoringResourceWithRawResponse @@ -1001,14 +978,6 @@ def shields(self) -> shields.AsyncShieldsResourceWithRawResponse: return AsyncShieldsResourceWithRawResponse(self._client.shields) - @cached_property - def synthetic_data_generation( - self, - ) -> synthetic_data_generation.AsyncSyntheticDataGenerationResourceWithRawResponse: - from .resources.synthetic_data_generation import AsyncSyntheticDataGenerationResourceWithRawResponse - - return AsyncSyntheticDataGenerationResourceWithRawResponse(self._client.synthetic_data_generation) - @cached_property def scoring(self) -> scoring.AsyncScoringResourceWithRawResponse: from .resources.scoring import AsyncScoringResourceWithRawResponse @@ -1154,14 +1123,6 @@ def shields(self) -> shields.ShieldsResourceWithStreamingResponse: return ShieldsResourceWithStreamingResponse(self._client.shields) - @cached_property - def synthetic_data_generation( - self, - ) -> synthetic_data_generation.SyntheticDataGenerationResourceWithStreamingResponse: - from .resources.synthetic_data_generation import SyntheticDataGenerationResourceWithStreamingResponse - - return SyntheticDataGenerationResourceWithStreamingResponse(self._client.synthetic_data_generation) - @cached_property def scoring(self) -> scoring.ScoringResourceWithStreamingResponse: from .resources.scoring import ScoringResourceWithStreamingResponse @@ -1307,14 +1268,6 @@ def shields(self) -> shields.AsyncShieldsResourceWithStreamingResponse: return AsyncShieldsResourceWithStreamingResponse(self._client.shields) - @cached_property - def synthetic_data_generation( - self, - ) -> synthetic_data_generation.AsyncSyntheticDataGenerationResourceWithStreamingResponse: - from .resources.synthetic_data_generation import AsyncSyntheticDataGenerationResourceWithStreamingResponse - - return AsyncSyntheticDataGenerationResourceWithStreamingResponse(self._client.synthetic_data_generation) - @cached_property def scoring(self) -> scoring.AsyncScoringResourceWithStreamingResponse: from .resources.scoring import AsyncScoringResourceWithStreamingResponse diff --git a/src/llama_stack_client/resources/__init__.py b/src/llama_stack_client/resources/__init__.py index 807ed6c8..0255b3e3 100644 --- a/src/llama_stack_client/resources/__init__.py +++ b/src/llama_stack_client/resources/__init__.py @@ -190,14 +190,6 @@ ScoringFunctionsResourceWithStreamingResponse, AsyncScoringFunctionsResourceWithStreamingResponse, ) -from .synthetic_data_generation import ( - SyntheticDataGenerationResource, - AsyncSyntheticDataGenerationResource, - SyntheticDataGenerationResourceWithRawResponse, - AsyncSyntheticDataGenerationResourceWithRawResponse, - SyntheticDataGenerationResourceWithStreamingResponse, - AsyncSyntheticDataGenerationResourceWithStreamingResponse, -) __all__ = [ "ToolgroupsResource", @@ -308,12 +300,6 @@ "AsyncShieldsResourceWithRawResponse", "ShieldsResourceWithStreamingResponse", "AsyncShieldsResourceWithStreamingResponse", - "SyntheticDataGenerationResource", - "AsyncSyntheticDataGenerationResource", - "SyntheticDataGenerationResourceWithRawResponse", - "AsyncSyntheticDataGenerationResourceWithRawResponse", - "SyntheticDataGenerationResourceWithStreamingResponse", - "AsyncSyntheticDataGenerationResourceWithStreamingResponse", "ScoringResource", "AsyncScoringResource", "ScoringResourceWithRawResponse", diff --git a/src/llama_stack_client/resources/models/models.py b/src/llama_stack_client/resources/models/models.py index dc7e0f4d..0b0dc2dd 100644 --- a/src/llama_stack_client/resources/models/models.py +++ b/src/llama_stack_client/resources/models/models.py @@ -33,9 +33,10 @@ async_to_streamed_response_wrapper, ) from ..._wrappers import DataWrapper -from ...types.model import Model from ..._base_client import make_request_options from ...types.model_list_response import ModelListResponse +from ...types.model_register_response import ModelRegisterResponse +from ...types.model_retrieve_response import ModelRetrieveResponse __all__ = ["ModelsResource", "AsyncModelsResource"] @@ -74,7 +75,7 @@ def retrieve( extra_query: Query | None = None, extra_body: Body | None = None, timeout: float | httpx.Timeout | None | NotGiven = not_given, - ) -> Model: + ) -> ModelRetrieveResponse: """Get model. Get a model by its identifier. @@ -95,7 +96,7 @@ def retrieve( options=make_request_options( extra_headers=extra_headers, extra_query=extra_query, extra_body=extra_body, timeout=timeout ), - cast_to=Model, + cast_to=ModelRetrieveResponse, ) def list( @@ -110,7 +111,7 @@ def list( ) -> ModelListResponse: """List models using the OpenAI API.""" return self._get( - "/v1/openai/v1/models", + "/v1/models", options=make_request_options( extra_headers=extra_headers, extra_query=extra_query, @@ -135,7 +136,7 @@ def register( extra_query: Query | None = None, extra_body: Body | None = None, timeout: float | httpx.Timeout | None | NotGiven = not_given, - ) -> Model: + ) -> ModelRegisterResponse: """Register model. Register a model. @@ -174,7 +175,7 @@ def register( options=make_request_options( extra_headers=extra_headers, extra_query=extra_query, extra_body=extra_body, timeout=timeout ), - cast_to=Model, + cast_to=ModelRegisterResponse, ) def unregister( @@ -247,7 +248,7 @@ async def retrieve( extra_query: Query | None = None, extra_body: Body | None = None, timeout: float | httpx.Timeout | None | NotGiven = not_given, - ) -> Model: + ) -> ModelRetrieveResponse: """Get model. Get a model by its identifier. @@ -268,7 +269,7 @@ async def retrieve( options=make_request_options( extra_headers=extra_headers, extra_query=extra_query, extra_body=extra_body, timeout=timeout ), - cast_to=Model, + cast_to=ModelRetrieveResponse, ) async def list( @@ -283,7 +284,7 @@ async def list( ) -> ModelListResponse: """List models using the OpenAI API.""" return await self._get( - "/v1/openai/v1/models", + "/v1/models", options=make_request_options( extra_headers=extra_headers, extra_query=extra_query, @@ -308,7 +309,7 @@ async def register( extra_query: Query | None = None, extra_body: Body | None = None, timeout: float | httpx.Timeout | None | NotGiven = not_given, - ) -> Model: + ) -> ModelRegisterResponse: """Register model. Register a model. @@ -347,7 +348,7 @@ async def register( options=make_request_options( extra_headers=extra_headers, extra_query=extra_query, extra_body=extra_body, timeout=timeout ), - cast_to=Model, + cast_to=ModelRegisterResponse, ) async def unregister( diff --git a/src/llama_stack_client/resources/models/openai.py b/src/llama_stack_client/resources/models/openai.py index c581f714..954d3c6b 100644 --- a/src/llama_stack_client/resources/models/openai.py +++ b/src/llama_stack_client/resources/models/openai.py @@ -23,7 +23,7 @@ ) from ..._wrappers import DataWrapper from ..._base_client import make_request_options -from ...types.models.openai_list_response import OpenAIListResponse +from ...types.model_list_response import ModelListResponse __all__ = ["OpenAIResource", "AsyncOpenAIResource"] @@ -57,8 +57,8 @@ def list( extra_query: Query | None = None, extra_body: Body | None = None, timeout: float | httpx.Timeout | None | NotGiven = not_given, - ) -> OpenAIListResponse: - """List all models.""" + ) -> ModelListResponse: + """List models using the OpenAI API.""" return self._get( "/v1/models", options=make_request_options( @@ -66,9 +66,9 @@ def list( extra_query=extra_query, extra_body=extra_body, timeout=timeout, - post_parser=DataWrapper[OpenAIListResponse]._unwrapper, + post_parser=DataWrapper[ModelListResponse]._unwrapper, ), - cast_to=cast(Type[OpenAIListResponse], DataWrapper[OpenAIListResponse]), + cast_to=cast(Type[ModelListResponse], DataWrapper[ModelListResponse]), ) @@ -101,8 +101,8 @@ async def list( extra_query: Query | None = None, extra_body: Body | None = None, timeout: float | httpx.Timeout | None | NotGiven = not_given, - ) -> OpenAIListResponse: - """List all models.""" + ) -> ModelListResponse: + """List models using the OpenAI API.""" return await self._get( "/v1/models", options=make_request_options( @@ -110,9 +110,9 @@ async def list( extra_query=extra_query, extra_body=extra_body, timeout=timeout, - post_parser=DataWrapper[OpenAIListResponse]._unwrapper, + post_parser=DataWrapper[ModelListResponse]._unwrapper, ), - cast_to=cast(Type[OpenAIListResponse], DataWrapper[OpenAIListResponse]), + cast_to=cast(Type[ModelListResponse], DataWrapper[ModelListResponse]), ) diff --git a/src/llama_stack_client/resources/synthetic_data_generation.py b/src/llama_stack_client/resources/synthetic_data_generation.py deleted file mode 100644 index c8c3d431..00000000 --- a/src/llama_stack_client/resources/synthetic_data_generation.py +++ /dev/null @@ -1,205 +0,0 @@ -# Copyright (c) Meta Platforms, Inc. and affiliates. -# All rights reserved. -# -# This source code is licensed under the terms described in the LICENSE file in -# the root directory of this source tree. - -# File generated from our OpenAPI spec by Stainless. See CONTRIBUTING.md for details. - -from __future__ import annotations - -from typing import Iterable -from typing_extensions import Literal - -import httpx - -from ..types import synthetic_data_generation_generate_params -from .._types import Body, Omit, Query, Headers, NotGiven, omit, not_given -from .._utils import maybe_transform, async_maybe_transform -from .._compat import cached_property -from .._resource import SyncAPIResource, AsyncAPIResource -from .._response import ( - to_raw_response_wrapper, - to_streamed_response_wrapper, - async_to_raw_response_wrapper, - async_to_streamed_response_wrapper, -) -from .._base_client import make_request_options -from ..types.shared_params.message import Message -from ..types.synthetic_data_generation_response import SyntheticDataGenerationResponse - -__all__ = ["SyntheticDataGenerationResource", "AsyncSyntheticDataGenerationResource"] - - -class SyntheticDataGenerationResource(SyncAPIResource): - @cached_property - def with_raw_response(self) -> SyntheticDataGenerationResourceWithRawResponse: - """ - This property can be used as a prefix for any HTTP method call to return - the raw response object instead of the parsed content. - - For more information, see https://www.github.com/llamastack/llama-stack-client-python#accessing-raw-response-data-eg-headers - """ - return SyntheticDataGenerationResourceWithRawResponse(self) - - @cached_property - def with_streaming_response(self) -> SyntheticDataGenerationResourceWithStreamingResponse: - """ - An alternative to `.with_raw_response` that doesn't eagerly read the response body. - - For more information, see https://www.github.com/llamastack/llama-stack-client-python#with_streaming_response - """ - return SyntheticDataGenerationResourceWithStreamingResponse(self) - - def generate( - self, - *, - dialogs: Iterable[Message], - filtering_function: Literal["none", "random", "top_k", "top_p", "top_k_top_p", "sigmoid"], - model: str | Omit = omit, - # Use the following arguments if you need to pass additional parameters to the API that aren't available via kwargs. - # The extra values given here take precedence over values defined on the client or passed to this method. - extra_headers: Headers | None = None, - extra_query: Query | None = None, - extra_body: Body | None = None, - timeout: float | httpx.Timeout | None | NotGiven = not_given, - ) -> SyntheticDataGenerationResponse: - """ - Generate synthetic data based on input dialogs and apply filtering. - - Args: - dialogs: List of conversation messages to use as input for synthetic data generation - - filtering_function: Type of filtering to apply to generated synthetic data samples - - model: (Optional) The identifier of the model to use. The model must be registered with - Llama Stack and available via the /models endpoint - - extra_headers: Send extra headers - - extra_query: Add additional query parameters to the request - - extra_body: Add additional JSON properties to the request - - timeout: Override the client-level default timeout for this request, in seconds - """ - return self._post( - "/v1/synthetic-data-generation/generate", - body=maybe_transform( - { - "dialogs": dialogs, - "filtering_function": filtering_function, - "model": model, - }, - synthetic_data_generation_generate_params.SyntheticDataGenerationGenerateParams, - ), - options=make_request_options( - extra_headers=extra_headers, extra_query=extra_query, extra_body=extra_body, timeout=timeout - ), - cast_to=SyntheticDataGenerationResponse, - ) - - -class AsyncSyntheticDataGenerationResource(AsyncAPIResource): - @cached_property - def with_raw_response(self) -> AsyncSyntheticDataGenerationResourceWithRawResponse: - """ - This property can be used as a prefix for any HTTP method call to return - the raw response object instead of the parsed content. - - For more information, see https://www.github.com/llamastack/llama-stack-client-python#accessing-raw-response-data-eg-headers - """ - return AsyncSyntheticDataGenerationResourceWithRawResponse(self) - - @cached_property - def with_streaming_response(self) -> AsyncSyntheticDataGenerationResourceWithStreamingResponse: - """ - An alternative to `.with_raw_response` that doesn't eagerly read the response body. - - For more information, see https://www.github.com/llamastack/llama-stack-client-python#with_streaming_response - """ - return AsyncSyntheticDataGenerationResourceWithStreamingResponse(self) - - async def generate( - self, - *, - dialogs: Iterable[Message], - filtering_function: Literal["none", "random", "top_k", "top_p", "top_k_top_p", "sigmoid"], - model: str | Omit = omit, - # Use the following arguments if you need to pass additional parameters to the API that aren't available via kwargs. - # The extra values given here take precedence over values defined on the client or passed to this method. - extra_headers: Headers | None = None, - extra_query: Query | None = None, - extra_body: Body | None = None, - timeout: float | httpx.Timeout | None | NotGiven = not_given, - ) -> SyntheticDataGenerationResponse: - """ - Generate synthetic data based on input dialogs and apply filtering. - - Args: - dialogs: List of conversation messages to use as input for synthetic data generation - - filtering_function: Type of filtering to apply to generated synthetic data samples - - model: (Optional) The identifier of the model to use. The model must be registered with - Llama Stack and available via the /models endpoint - - extra_headers: Send extra headers - - extra_query: Add additional query parameters to the request - - extra_body: Add additional JSON properties to the request - - timeout: Override the client-level default timeout for this request, in seconds - """ - return await self._post( - "/v1/synthetic-data-generation/generate", - body=await async_maybe_transform( - { - "dialogs": dialogs, - "filtering_function": filtering_function, - "model": model, - }, - synthetic_data_generation_generate_params.SyntheticDataGenerationGenerateParams, - ), - options=make_request_options( - extra_headers=extra_headers, extra_query=extra_query, extra_body=extra_body, timeout=timeout - ), - cast_to=SyntheticDataGenerationResponse, - ) - - -class SyntheticDataGenerationResourceWithRawResponse: - def __init__(self, synthetic_data_generation: SyntheticDataGenerationResource) -> None: - self._synthetic_data_generation = synthetic_data_generation - - self.generate = to_raw_response_wrapper( - synthetic_data_generation.generate, - ) - - -class AsyncSyntheticDataGenerationResourceWithRawResponse: - def __init__(self, synthetic_data_generation: AsyncSyntheticDataGenerationResource) -> None: - self._synthetic_data_generation = synthetic_data_generation - - self.generate = async_to_raw_response_wrapper( - synthetic_data_generation.generate, - ) - - -class SyntheticDataGenerationResourceWithStreamingResponse: - def __init__(self, synthetic_data_generation: SyntheticDataGenerationResource) -> None: - self._synthetic_data_generation = synthetic_data_generation - - self.generate = to_streamed_response_wrapper( - synthetic_data_generation.generate, - ) - - -class AsyncSyntheticDataGenerationResourceWithStreamingResponse: - def __init__(self, synthetic_data_generation: AsyncSyntheticDataGenerationResource) -> None: - self._synthetic_data_generation = synthetic_data_generation - - self.generate = async_to_streamed_response_wrapper( - synthetic_data_generation.generate, - ) diff --git a/src/llama_stack_client/types/__init__.py b/src/llama_stack_client/types/__init__.py index 1a67f6c4..03e243a5 100644 --- a/src/llama_stack_client/types/__init__.py +++ b/src/llama_stack_client/types/__init__.py @@ -12,7 +12,6 @@ from .model import Model as Model from .prompt import Prompt as Prompt from .shared import ( - Message as Message, Document as Document, ToolCall as ToolCall, ParamType as ParamType, @@ -78,6 +77,8 @@ from .vector_io_query_params import VectorIoQueryParams as VectorIoQueryParams from .embedding_create_params import EmbeddingCreateParams as EmbeddingCreateParams from .list_providers_response import ListProvidersResponse as ListProvidersResponse +from .model_register_response import ModelRegisterResponse as ModelRegisterResponse +from .model_retrieve_response import ModelRetrieveResponse as ModelRetrieveResponse from .scoring_fn_params_param import ScoringFnParamsParam as ScoringFnParamsParam from .toolgroup_list_response import ToolgroupListResponse as ToolgroupListResponse from .vector_io_insert_params import VectorIoInsertParams as VectorIoInsertParams @@ -108,7 +109,3 @@ from .scoring_function_register_params import ScoringFunctionRegisterParams as ScoringFunctionRegisterParams from .tool_runtime_list_tools_response import ToolRuntimeListToolsResponse as ToolRuntimeListToolsResponse from .prompt_set_default_version_params import PromptSetDefaultVersionParams as PromptSetDefaultVersionParams -from .synthetic_data_generation_response import SyntheticDataGenerationResponse as SyntheticDataGenerationResponse -from .synthetic_data_generation_generate_params import ( - SyntheticDataGenerationGenerateParams as SyntheticDataGenerationGenerateParams, -) diff --git a/src/llama_stack_client/types/model.py b/src/llama_stack_client/types/model.py index 5807b0ed..5a2f4305 100644 --- a/src/llama_stack_client/types/model.py +++ b/src/llama_stack_client/types/model.py @@ -6,31 +6,22 @@ # File generated from our OpenAPI spec by Stainless. See CONTRIBUTING.md for details. +import builtins from typing import Dict, List, Union, Optional from typing_extensions import Literal -from pydantic import Field as FieldInfo - from .._models import BaseModel __all__ = ["Model"] class Model(BaseModel): - identifier: str - """Unique identifier for this resource in llama stack""" - - metadata: Dict[str, Union[bool, float, str, List[object], object, None]] - """Any additional metadata for this model""" + id: str - api_model_type: Literal["llm", "embedding", "rerank"] = FieldInfo(alias="model_type") - """The type of model (LLM or embedding model)""" + created: int - provider_id: str - """ID of the provider that owns this resource""" + object: Literal["model"] - type: Literal["model"] - """The resource type, always 'model' for model resources""" + owned_by: str - provider_resource_id: Optional[str] = None - """Unique identifier for this resource in the provider""" + custom_metadata: Optional[Dict[str, Union[bool, float, str, List[builtins.object], builtins.object, None]]] = None diff --git a/src/llama_stack_client/types/model_list_response.py b/src/llama_stack_client/types/model_list_response.py index c42b3310..b53ae421 100644 --- a/src/llama_stack_client/types/model_list_response.py +++ b/src/llama_stack_client/types/model_list_response.py @@ -6,25 +6,11 @@ # File generated from our OpenAPI spec by Stainless. See CONTRIBUTING.md for details. -import builtins -from typing import Dict, List, Union, Optional -from typing_extensions import Literal, TypeAlias +from typing import List +from typing_extensions import TypeAlias -from .._models import BaseModel +from .model import Model -__all__ = ["ModelListResponse", "ModelListResponseItem"] +__all__ = ["ModelListResponse"] - -class ModelListResponseItem(BaseModel): - id: str - - created: int - - object: Literal["model"] - - owned_by: str - - custom_metadata: Optional[Dict[str, Union[bool, float, str, List[builtins.object], builtins.object, None]]] = None - - -ModelListResponse: TypeAlias = List[ModelListResponseItem] +ModelListResponse: TypeAlias = List[Model] diff --git a/src/llama_stack_client/types/model_register_response.py b/src/llama_stack_client/types/model_register_response.py new file mode 100644 index 00000000..08b0e8d6 --- /dev/null +++ b/src/llama_stack_client/types/model_register_response.py @@ -0,0 +1,30 @@ +# File generated from our OpenAPI spec by Stainless. See CONTRIBUTING.md for details. + +from typing import Dict, List, Union, Optional +from typing_extensions import Literal + +from pydantic import Field as FieldInfo + +from .._models import BaseModel + +__all__ = ["ModelRegisterResponse"] + + +class ModelRegisterResponse(BaseModel): + identifier: str + """Unique identifier for this resource in llama stack""" + + metadata: Dict[str, Union[bool, float, str, List[object], object, None]] + """Any additional metadata for this model""" + + api_model_type: Literal["llm", "embedding", "rerank"] = FieldInfo(alias="model_type") + """The type of model (LLM or embedding model)""" + + provider_id: str + """ID of the provider that owns this resource""" + + type: Literal["model"] + """The resource type, always 'model' for model resources""" + + provider_resource_id: Optional[str] = None + """Unique identifier for this resource in the provider""" diff --git a/src/llama_stack_client/types/model_retrieve_response.py b/src/llama_stack_client/types/model_retrieve_response.py new file mode 100644 index 00000000..58f477d8 --- /dev/null +++ b/src/llama_stack_client/types/model_retrieve_response.py @@ -0,0 +1,30 @@ +# File generated from our OpenAPI spec by Stainless. See CONTRIBUTING.md for details. + +from typing import Dict, List, Union, Optional +from typing_extensions import Literal + +from pydantic import Field as FieldInfo + +from .._models import BaseModel + +__all__ = ["ModelRetrieveResponse"] + + +class ModelRetrieveResponse(BaseModel): + identifier: str + """Unique identifier for this resource in llama stack""" + + metadata: Dict[str, Union[bool, float, str, List[object], object, None]] + """Any additional metadata for this model""" + + api_model_type: Literal["llm", "embedding", "rerank"] = FieldInfo(alias="model_type") + """The type of model (LLM or embedding model)""" + + provider_id: str + """ID of the provider that owns this resource""" + + type: Literal["model"] + """The resource type, always 'model' for model resources""" + + provider_resource_id: Optional[str] = None + """Unique identifier for this resource in the provider""" diff --git a/src/llama_stack_client/types/models/__init__.py b/src/llama_stack_client/types/models/__init__.py index bba1f3e9..d14ed874 100644 --- a/src/llama_stack_client/types/models/__init__.py +++ b/src/llama_stack_client/types/models/__init__.py @@ -7,5 +7,3 @@ # File generated from our OpenAPI spec by Stainless. See CONTRIBUTING.md for details. from __future__ import annotations - -from .openai_list_response import OpenAIListResponse as OpenAIListResponse diff --git a/src/llama_stack_client/types/models/openai_list_response.py b/src/llama_stack_client/types/models/openai_list_response.py deleted file mode 100644 index 5b6c0358..00000000 --- a/src/llama_stack_client/types/models/openai_list_response.py +++ /dev/null @@ -1,10 +0,0 @@ -# File generated from our OpenAPI spec by Stainless. See CONTRIBUTING.md for details. - -from typing import List -from typing_extensions import TypeAlias - -from ..model import Model - -__all__ = ["OpenAIListResponse"] - -OpenAIListResponse: TypeAlias = List[Model] diff --git a/src/llama_stack_client/types/shared/__init__.py b/src/llama_stack_client/types/shared/__init__.py index c18a9358..6ba732f0 100644 --- a/src/llama_stack_client/types/shared/__init__.py +++ b/src/llama_stack_client/types/shared/__init__.py @@ -6,7 +6,6 @@ # File generated from our OpenAPI spec by Stainless. See CONTRIBUTING.md for details. -from .message import Message as Message from .document import Document as Document from .tool_call import ToolCall as ToolCall from .param_type import ParamType as ParamType diff --git a/src/llama_stack_client/types/shared/message.py b/src/llama_stack_client/types/shared/message.py deleted file mode 100644 index bb47f940..00000000 --- a/src/llama_stack_client/types/shared/message.py +++ /dev/null @@ -1,22 +0,0 @@ -# Copyright (c) Meta Platforms, Inc. and affiliates. -# All rights reserved. -# -# This source code is licensed under the terms described in the LICENSE file in -# the root directory of this source tree. - -# File generated from our OpenAPI spec by Stainless. See CONTRIBUTING.md for details. - -from typing import Union -from typing_extensions import Annotated, TypeAlias - -from ..._utils import PropertyInfo -from .user_message import UserMessage -from .system_message import SystemMessage -from .completion_message import CompletionMessage -from .tool_response_message import ToolResponseMessage - -__all__ = ["Message"] - -Message: TypeAlias = Annotated[ - Union[UserMessage, SystemMessage, ToolResponseMessage, CompletionMessage], PropertyInfo(discriminator="role") -] diff --git a/src/llama_stack_client/types/shared_params/__init__.py b/src/llama_stack_client/types/shared_params/__init__.py index 12061849..f25d2430 100644 --- a/src/llama_stack_client/types/shared_params/__init__.py +++ b/src/llama_stack_client/types/shared_params/__init__.py @@ -6,16 +6,13 @@ # File generated from our OpenAPI spec by Stainless. See CONTRIBUTING.md for details. -from .message import Message as Message from .document import Document as Document -from .tool_call import ToolCall as ToolCall from .agent_config import AgentConfig as AgentConfig from .query_config import QueryConfig as QueryConfig from .user_message import UserMessage as UserMessage from .system_message import SystemMessage as SystemMessage from .response_format import ResponseFormat as ResponseFormat from .sampling_params import SamplingParams as SamplingParams -from .completion_message import CompletionMessage as CompletionMessage from .interleaved_content import InterleavedContent as InterleavedContent from .tool_response_message import ToolResponseMessage as ToolResponseMessage from .interleaved_content_item import InterleavedContentItem as InterleavedContentItem diff --git a/src/llama_stack_client/types/shared_params/completion_message.py b/src/llama_stack_client/types/shared_params/completion_message.py deleted file mode 100644 index 61c3fc08..00000000 --- a/src/llama_stack_client/types/shared_params/completion_message.py +++ /dev/null @@ -1,38 +0,0 @@ -# Copyright (c) Meta Platforms, Inc. and affiliates. -# All rights reserved. -# -# This source code is licensed under the terms described in the LICENSE file in -# the root directory of this source tree. - -# File generated from our OpenAPI spec by Stainless. See CONTRIBUTING.md for details. - -from __future__ import annotations - -from typing import Iterable -from typing_extensions import Literal, Required, TypedDict - -from .tool_call import ToolCall -from .interleaved_content import InterleavedContent - -__all__ = ["CompletionMessage"] - - -class CompletionMessage(TypedDict, total=False): - content: Required[InterleavedContent] - """The content of the model's response""" - - role: Required[Literal["assistant"]] - """Must be "assistant" to identify this as the model's response""" - - stop_reason: Required[Literal["end_of_turn", "end_of_message", "out_of_tokens"]] - """Reason why the model stopped generating. - - Options are: - `StopReason.end_of_turn`: The model finished generating the - entire response. - `StopReason.end_of_message`: The model finished generating - but generated a partial response -- usually, a tool call. The user may call the - tool and continue the conversation with the tool's response. - - `StopReason.out_of_tokens`: The model ran out of token budget. - """ - - tool_calls: Iterable[ToolCall] - """List of tool calls. Each tool call is a ToolCall object.""" diff --git a/src/llama_stack_client/types/shared_params/message.py b/src/llama_stack_client/types/shared_params/message.py deleted file mode 100644 index 2a2c0f75..00000000 --- a/src/llama_stack_client/types/shared_params/message.py +++ /dev/null @@ -1,21 +0,0 @@ -# Copyright (c) Meta Platforms, Inc. and affiliates. -# All rights reserved. -# -# This source code is licensed under the terms described in the LICENSE file in -# the root directory of this source tree. - -# File generated from our OpenAPI spec by Stainless. See CONTRIBUTING.md for details. - -from __future__ import annotations - -from typing import Union -from typing_extensions import TypeAlias - -from .user_message import UserMessage -from .system_message import SystemMessage -from .completion_message import CompletionMessage -from .tool_response_message import ToolResponseMessage - -__all__ = ["Message"] - -Message: TypeAlias = Union[UserMessage, SystemMessage, ToolResponseMessage, CompletionMessage] diff --git a/src/llama_stack_client/types/shared_params/tool_call.py b/src/llama_stack_client/types/shared_params/tool_call.py deleted file mode 100644 index 320b5a8e..00000000 --- a/src/llama_stack_client/types/shared_params/tool_call.py +++ /dev/null @@ -1,22 +0,0 @@ -# Copyright (c) Meta Platforms, Inc. and affiliates. -# All rights reserved. -# -# This source code is licensed under the terms described in the LICENSE file in -# the root directory of this source tree. - -# File generated from our OpenAPI spec by Stainless. See CONTRIBUTING.md for details. - -from __future__ import annotations - -from typing import Union -from typing_extensions import Literal, Required, TypedDict - -__all__ = ["ToolCall"] - - -class ToolCall(TypedDict, total=False): - arguments: Required[str] - - call_id: Required[str] - - tool_name: Required[Union[Literal["brave_search", "wolfram_alpha", "photogen", "code_interpreter"], str]] diff --git a/src/llama_stack_client/types/synthetic_data_generation_generate_params.py b/src/llama_stack_client/types/synthetic_data_generation_generate_params.py deleted file mode 100644 index 2f817132..00000000 --- a/src/llama_stack_client/types/synthetic_data_generation_generate_params.py +++ /dev/null @@ -1,31 +0,0 @@ -# Copyright (c) Meta Platforms, Inc. and affiliates. -# All rights reserved. -# -# This source code is licensed under the terms described in the LICENSE file in -# the root directory of this source tree. - -# File generated from our OpenAPI spec by Stainless. See CONTRIBUTING.md for details. - -from __future__ import annotations - -from typing import Iterable -from typing_extensions import Literal, Required, TypedDict - -from .shared_params.message import Message - -__all__ = ["SyntheticDataGenerationGenerateParams"] - - -class SyntheticDataGenerationGenerateParams(TypedDict, total=False): - dialogs: Required[Iterable[Message]] - """List of conversation messages to use as input for synthetic data generation""" - - filtering_function: Required[Literal["none", "random", "top_k", "top_p", "top_k_top_p", "sigmoid"]] - """Type of filtering to apply to generated synthetic data samples""" - - model: str - """(Optional) The identifier of the model to use. - - The model must be registered with Llama Stack and available via the /models - endpoint - """ diff --git a/src/llama_stack_client/types/synthetic_data_generation_response.py b/src/llama_stack_client/types/synthetic_data_generation_response.py deleted file mode 100644 index 9332562f..00000000 --- a/src/llama_stack_client/types/synthetic_data_generation_response.py +++ /dev/null @@ -1,24 +0,0 @@ -# Copyright (c) Meta Platforms, Inc. and affiliates. -# All rights reserved. -# -# This source code is licensed under the terms described in the LICENSE file in -# the root directory of this source tree. - -# File generated from our OpenAPI spec by Stainless. See CONTRIBUTING.md for details. - -from typing import Dict, List, Union, Optional - -from .._models import BaseModel - -__all__ = ["SyntheticDataGenerationResponse"] - - -class SyntheticDataGenerationResponse(BaseModel): - synthetic_data: List[Dict[str, Union[bool, float, str, List[object], object, None]]] - """List of generated synthetic data samples that passed the filtering criteria""" - - statistics: Optional[Dict[str, Union[bool, float, str, List[object], object, None]]] = None - """ - (Optional) Statistical information about the generation process and filtering - results - """ diff --git a/tests/api_resources/models/test_openai.py b/tests/api_resources/models/test_openai.py index 96955333..6a9acf23 100644 --- a/tests/api_resources/models/test_openai.py +++ b/tests/api_resources/models/test_openai.py @@ -15,7 +15,7 @@ from tests.utils import assert_matches_type from llama_stack_client import LlamaStackClient, AsyncLlamaStackClient -from llama_stack_client.types.models import OpenAIListResponse +from llama_stack_client.types import ModelListResponse base_url = os.environ.get("TEST_API_BASE_URL", "http://127.0.0.1:4010") @@ -26,7 +26,7 @@ class TestOpenAI: @parametrize def test_method_list(self, client: LlamaStackClient) -> None: openai = client.models.openai.list() - assert_matches_type(OpenAIListResponse, openai, path=["response"]) + assert_matches_type(ModelListResponse, openai, path=["response"]) @parametrize def test_raw_response_list(self, client: LlamaStackClient) -> None: @@ -35,7 +35,7 @@ def test_raw_response_list(self, client: LlamaStackClient) -> None: assert response.is_closed is True assert response.http_request.headers.get("X-Stainless-Lang") == "python" openai = response.parse() - assert_matches_type(OpenAIListResponse, openai, path=["response"]) + assert_matches_type(ModelListResponse, openai, path=["response"]) @parametrize def test_streaming_response_list(self, client: LlamaStackClient) -> None: @@ -44,7 +44,7 @@ def test_streaming_response_list(self, client: LlamaStackClient) -> None: assert response.http_request.headers.get("X-Stainless-Lang") == "python" openai = response.parse() - assert_matches_type(OpenAIListResponse, openai, path=["response"]) + assert_matches_type(ModelListResponse, openai, path=["response"]) assert cast(Any, response.is_closed) is True @@ -57,7 +57,7 @@ class TestAsyncOpenAI: @parametrize async def test_method_list(self, async_client: AsyncLlamaStackClient) -> None: openai = await async_client.models.openai.list() - assert_matches_type(OpenAIListResponse, openai, path=["response"]) + assert_matches_type(ModelListResponse, openai, path=["response"]) @parametrize async def test_raw_response_list(self, async_client: AsyncLlamaStackClient) -> None: @@ -66,7 +66,7 @@ async def test_raw_response_list(self, async_client: AsyncLlamaStackClient) -> N assert response.is_closed is True assert response.http_request.headers.get("X-Stainless-Lang") == "python" openai = await response.parse() - assert_matches_type(OpenAIListResponse, openai, path=["response"]) + assert_matches_type(ModelListResponse, openai, path=["response"]) @parametrize async def test_streaming_response_list(self, async_client: AsyncLlamaStackClient) -> None: @@ -75,6 +75,6 @@ async def test_streaming_response_list(self, async_client: AsyncLlamaStackClient assert response.http_request.headers.get("X-Stainless-Lang") == "python" openai = await response.parse() - assert_matches_type(OpenAIListResponse, openai, path=["response"]) + assert_matches_type(ModelListResponse, openai, path=["response"]) assert cast(Any, response.is_closed) is True diff --git a/tests/api_resources/test_models.py b/tests/api_resources/test_models.py index 13e98aa3..89fb7e7c 100644 --- a/tests/api_resources/test_models.py +++ b/tests/api_resources/test_models.py @@ -15,7 +15,11 @@ from tests.utils import assert_matches_type from llama_stack_client import LlamaStackClient, AsyncLlamaStackClient -from llama_stack_client.types import Model, ModelListResponse +from llama_stack_client.types import ( + ModelListResponse, + ModelRegisterResponse, + ModelRetrieveResponse, +) base_url = os.environ.get("TEST_API_BASE_URL", "http://127.0.0.1:4010") @@ -28,7 +32,7 @@ def test_method_retrieve(self, client: LlamaStackClient) -> None: model = client.models.retrieve( "model_id", ) - assert_matches_type(Model, model, path=["response"]) + assert_matches_type(ModelRetrieveResponse, model, path=["response"]) @parametrize def test_raw_response_retrieve(self, client: LlamaStackClient) -> None: @@ -39,7 +43,7 @@ def test_raw_response_retrieve(self, client: LlamaStackClient) -> None: assert response.is_closed is True assert response.http_request.headers.get("X-Stainless-Lang") == "python" model = response.parse() - assert_matches_type(Model, model, path=["response"]) + assert_matches_type(ModelRetrieveResponse, model, path=["response"]) @parametrize def test_streaming_response_retrieve(self, client: LlamaStackClient) -> None: @@ -50,7 +54,7 @@ def test_streaming_response_retrieve(self, client: LlamaStackClient) -> None: assert response.http_request.headers.get("X-Stainless-Lang") == "python" model = response.parse() - assert_matches_type(Model, model, path=["response"]) + assert_matches_type(ModelRetrieveResponse, model, path=["response"]) assert cast(Any, response.is_closed) is True @@ -91,7 +95,7 @@ def test_method_register(self, client: LlamaStackClient) -> None: model = client.models.register( model_id="model_id", ) - assert_matches_type(Model, model, path=["response"]) + assert_matches_type(ModelRegisterResponse, model, path=["response"]) @parametrize def test_method_register_with_all_params(self, client: LlamaStackClient) -> None: @@ -102,7 +106,7 @@ def test_method_register_with_all_params(self, client: LlamaStackClient) -> None provider_id="provider_id", provider_model_id="provider_model_id", ) - assert_matches_type(Model, model, path=["response"]) + assert_matches_type(ModelRegisterResponse, model, path=["response"]) @parametrize def test_raw_response_register(self, client: LlamaStackClient) -> None: @@ -113,7 +117,7 @@ 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" model = response.parse() - assert_matches_type(Model, model, path=["response"]) + assert_matches_type(ModelRegisterResponse, model, path=["response"]) @parametrize def test_streaming_response_register(self, client: LlamaStackClient) -> None: @@ -124,7 +128,7 @@ def test_streaming_response_register(self, client: LlamaStackClient) -> None: assert response.http_request.headers.get("X-Stainless-Lang") == "python" model = response.parse() - assert_matches_type(Model, model, path=["response"]) + assert_matches_type(ModelRegisterResponse, model, path=["response"]) assert cast(Any, response.is_closed) is True @@ -177,7 +181,7 @@ async def test_method_retrieve(self, async_client: AsyncLlamaStackClient) -> Non model = await async_client.models.retrieve( "model_id", ) - assert_matches_type(Model, model, path=["response"]) + assert_matches_type(ModelRetrieveResponse, model, path=["response"]) @parametrize async def test_raw_response_retrieve(self, async_client: AsyncLlamaStackClient) -> None: @@ -188,7 +192,7 @@ async def test_raw_response_retrieve(self, async_client: AsyncLlamaStackClient) assert response.is_closed is True assert response.http_request.headers.get("X-Stainless-Lang") == "python" model = await response.parse() - assert_matches_type(Model, model, path=["response"]) + assert_matches_type(ModelRetrieveResponse, model, path=["response"]) @parametrize async def test_streaming_response_retrieve(self, async_client: AsyncLlamaStackClient) -> None: @@ -199,7 +203,7 @@ async def test_streaming_response_retrieve(self, async_client: AsyncLlamaStackCl assert response.http_request.headers.get("X-Stainless-Lang") == "python" model = await response.parse() - assert_matches_type(Model, model, path=["response"]) + assert_matches_type(ModelRetrieveResponse, model, path=["response"]) assert cast(Any, response.is_closed) is True @@ -240,7 +244,7 @@ async def test_method_register(self, async_client: AsyncLlamaStackClient) -> Non model = await async_client.models.register( model_id="model_id", ) - assert_matches_type(Model, model, path=["response"]) + assert_matches_type(ModelRegisterResponse, model, path=["response"]) @parametrize async def test_method_register_with_all_params(self, async_client: AsyncLlamaStackClient) -> None: @@ -251,7 +255,7 @@ async def test_method_register_with_all_params(self, async_client: AsyncLlamaSta provider_id="provider_id", provider_model_id="provider_model_id", ) - assert_matches_type(Model, model, path=["response"]) + assert_matches_type(ModelRegisterResponse, model, path=["response"]) @parametrize async def test_raw_response_register(self, async_client: AsyncLlamaStackClient) -> None: @@ -262,7 +266,7 @@ 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" model = await response.parse() - assert_matches_type(Model, model, path=["response"]) + assert_matches_type(ModelRegisterResponse, model, path=["response"]) @parametrize async def test_streaming_response_register(self, async_client: AsyncLlamaStackClient) -> None: @@ -273,7 +277,7 @@ async def test_streaming_response_register(self, async_client: AsyncLlamaStackCl assert response.http_request.headers.get("X-Stainless-Lang") == "python" model = await response.parse() - assert_matches_type(Model, model, path=["response"]) + assert_matches_type(ModelRegisterResponse, model, path=["response"]) assert cast(Any, response.is_closed) is True diff --git a/tests/api_resources/test_synthetic_data_generation.py b/tests/api_resources/test_synthetic_data_generation.py deleted file mode 100644 index c40ddede..00000000 --- a/tests/api_resources/test_synthetic_data_generation.py +++ /dev/null @@ -1,158 +0,0 @@ -# Copyright (c) Meta Platforms, Inc. and affiliates. -# All rights reserved. -# -# This source code is licensed under the terms described in the LICENSE file in -# the root directory of this source tree. - -# File generated from our OpenAPI spec by Stainless. See CONTRIBUTING.md for details. - -from __future__ import annotations - -import os -from typing import Any, cast - -import pytest - -from tests.utils import assert_matches_type -from llama_stack_client import LlamaStackClient, AsyncLlamaStackClient -from llama_stack_client.types import SyntheticDataGenerationResponse - -base_url = os.environ.get("TEST_API_BASE_URL", "http://127.0.0.1:4010") - - -class TestSyntheticDataGeneration: - parametrize = pytest.mark.parametrize("client", [False, True], indirect=True, ids=["loose", "strict"]) - - @parametrize - def test_method_generate(self, client: LlamaStackClient) -> None: - synthetic_data_generation = client.synthetic_data_generation.generate( - dialogs=[ - { - "content": "string", - "role": "user", - } - ], - filtering_function="none", - ) - assert_matches_type(SyntheticDataGenerationResponse, synthetic_data_generation, path=["response"]) - - @parametrize - def test_method_generate_with_all_params(self, client: LlamaStackClient) -> None: - synthetic_data_generation = client.synthetic_data_generation.generate( - dialogs=[ - { - "content": "string", - "role": "user", - "context": "string", - } - ], - filtering_function="none", - model="model", - ) - assert_matches_type(SyntheticDataGenerationResponse, synthetic_data_generation, path=["response"]) - - @parametrize - def test_raw_response_generate(self, client: LlamaStackClient) -> None: - response = client.synthetic_data_generation.with_raw_response.generate( - dialogs=[ - { - "content": "string", - "role": "user", - } - ], - filtering_function="none", - ) - - assert response.is_closed is True - assert response.http_request.headers.get("X-Stainless-Lang") == "python" - synthetic_data_generation = response.parse() - assert_matches_type(SyntheticDataGenerationResponse, synthetic_data_generation, path=["response"]) - - @parametrize - def test_streaming_response_generate(self, client: LlamaStackClient) -> None: - with client.synthetic_data_generation.with_streaming_response.generate( - dialogs=[ - { - "content": "string", - "role": "user", - } - ], - filtering_function="none", - ) as response: - assert not response.is_closed - assert response.http_request.headers.get("X-Stainless-Lang") == "python" - - synthetic_data_generation = response.parse() - assert_matches_type(SyntheticDataGenerationResponse, synthetic_data_generation, path=["response"]) - - assert cast(Any, response.is_closed) is True - - -class TestAsyncSyntheticDataGeneration: - parametrize = pytest.mark.parametrize( - "async_client", [False, True, {"http_client": "aiohttp"}], indirect=True, ids=["loose", "strict", "aiohttp"] - ) - - @parametrize - async def test_method_generate(self, async_client: AsyncLlamaStackClient) -> None: - synthetic_data_generation = await async_client.synthetic_data_generation.generate( - dialogs=[ - { - "content": "string", - "role": "user", - } - ], - filtering_function="none", - ) - assert_matches_type(SyntheticDataGenerationResponse, synthetic_data_generation, path=["response"]) - - @parametrize - async def test_method_generate_with_all_params(self, async_client: AsyncLlamaStackClient) -> None: - synthetic_data_generation = await async_client.synthetic_data_generation.generate( - dialogs=[ - { - "content": "string", - "role": "user", - "context": "string", - } - ], - filtering_function="none", - model="model", - ) - assert_matches_type(SyntheticDataGenerationResponse, synthetic_data_generation, path=["response"]) - - @parametrize - async def test_raw_response_generate(self, async_client: AsyncLlamaStackClient) -> None: - response = await async_client.synthetic_data_generation.with_raw_response.generate( - dialogs=[ - { - "content": "string", - "role": "user", - } - ], - filtering_function="none", - ) - - assert response.is_closed is True - assert response.http_request.headers.get("X-Stainless-Lang") == "python" - synthetic_data_generation = await response.parse() - assert_matches_type(SyntheticDataGenerationResponse, synthetic_data_generation, path=["response"]) - - @parametrize - async def test_streaming_response_generate(self, async_client: AsyncLlamaStackClient) -> None: - async with async_client.synthetic_data_generation.with_streaming_response.generate( - dialogs=[ - { - "content": "string", - "role": "user", - } - ], - filtering_function="none", - ) as response: - assert not response.is_closed - assert response.http_request.headers.get("X-Stainless-Lang") == "python" - - synthetic_data_generation = await response.parse() - assert_matches_type(SyntheticDataGenerationResponse, synthetic_data_generation, path=["response"]) - - assert cast(Any, response.is_closed) is True From 92bc34e5cb82a2353604617ed2c872453820b261 Mon Sep 17 00:00:00 2001 From: "stainless-app[bot]" <142633134+stainless-app[bot]@users.noreply.github.com> Date: Tue, 4 Nov 2025 02:40:57 +0000 Subject: [PATCH 2/2] release: 0.4.0-alpha.3 --- .release-please-manifest.json | 2 +- CHANGELOG.md | 13 +++++++++++++ pyproject.toml | 2 +- 3 files changed, 15 insertions(+), 2 deletions(-) diff --git a/.release-please-manifest.json b/.release-please-manifest.json index 24b05bc4..4c5c3821 100644 --- a/.release-please-manifest.json +++ b/.release-please-manifest.json @@ -1,3 +1,3 @@ { - ".": "0.4.0-alpha.2" + ".": "0.4.0-alpha.3" } diff --git a/CHANGELOG.md b/CHANGELOG.md index 236e5da7..b69b08da 100644 --- a/CHANGELOG.md +++ b/CHANGELOG.md @@ -1,5 +1,18 @@ # Changelog +## 0.4.0-alpha.3 (2025-11-04) + +Full Changelog: [v0.4.0-alpha.2...v0.4.0-alpha.3](https://github.com/llamastack/llama-stack-client-python/compare/v0.4.0-alpha.2...v0.4.0-alpha.3) + +### Features + +* **api:** remove openai/v1 endpoints ([e391af5](https://github.com/llamastack/llama-stack-client-python/commit/e391af5b47f10ca2c3fa7d36cacae1900af711b4)) + + +### Bug Fixes + +* update post_training CLI import path to use alpha subdirectory ([#293](https://github.com/llamastack/llama-stack-client-python/issues/293)) ([65cbe68](https://github.com/llamastack/llama-stack-client-python/commit/65cbe680ebeb30bf7e7cfebd1238f57bef792f5d)) + ## 0.4.0-alpha.2 (2025-11-03) Full Changelog: [v0.4.0-alpha.1...v0.4.0-alpha.2](https://github.com/llamastack/llama-stack-client-python/compare/v0.4.0-alpha.1...v0.4.0-alpha.2) diff --git a/pyproject.toml b/pyproject.toml index c75fa9fe..b85a739b 100644 --- a/pyproject.toml +++ b/pyproject.toml @@ -1,6 +1,6 @@ [project] name = "llama_stack_client" -version = "0.4.0-alpha.2" +version = "0.4.0-alpha.3" description = "The official Python library for the llama-stack-client API" dynamic = ["readme"] license = "MIT"