llamastack · stainless-app · Nov 4, 2025 · Nov 4, 2025 · Nov 4, 2025
diff --git 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/.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/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/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.
@@ -97,18 +93,49 @@ 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())
 ```
 
 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
@@ -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:
 
-- <code title="get /v1/models/{model_id}">client.models.<a href="./src/llama_stack_client/resources/models/models.py">retrieve</a>(model_id) -> <a href="./src/llama_stack_client/types/model.py">Model</a></code>
-- <code title="get /v1/openai/v1/models">client.models.<a href="./src/llama_stack_client/resources/models/models.py">list</a>() -> <a href="./src/llama_stack_client/types/model_list_response.py">ModelListResponse</a></code>
-- <code title="post /v1/models">client.models.<a href="./src/llama_stack_client/resources/models/models.py">register</a>(\*\*<a href="src/llama_stack_client/types/model_register_params.py">params</a>) -> <a href="./src/llama_stack_client/types/model.py">Model</a></code>
+- <code title="get /v1/models/{model_id}">client.models.<a href="./src/llama_stack_client/resources/models/models.py">retrieve</a>(model_id) -> <a href="./src/llama_stack_client/types/model_retrieve_response.py">ModelRetrieveResponse</a></code>
+- <code title="get /v1/models">client.models.<a href="./src/llama_stack_client/resources/models/models.py">list</a>() -> <a href="./src/llama_stack_client/types/model_list_response.py">ModelListResponse</a></code>
+- <code title="post /v1/models">client.models.<a href="./src/llama_stack_client/resources/models/models.py">register</a>(\*\*<a href="src/llama_stack_client/types/model_register_params.py">params</a>) -> <a href="./src/llama_stack_client/types/model_register_response.py">ModelRegisterResponse</a></code>
 - <code title="delete /v1/models/{model_id}">client.models.<a href="./src/llama_stack_client/resources/models/models.py">unregister</a>(model_id) -> None</code>
 
 ## OpenAI
 
-Types:
-
-```python
-from llama_stack_client.types.models import OpenAIListResponse
-```
-
 Methods:
 
-- <code title="get /v1/models">client.models.openai.<a href="./src/llama_stack_client/resources/models/openai.py">list</a>() -> <a href="./src/llama_stack_client/types/models/openai_list_response.py">OpenAIListResponse</a></code>
+- <code title="get /v1/models">client.models.openai.<a href="./src/llama_stack_client/resources/models/openai.py">list</a>() -> <a href="./src/llama_stack_client/types/model_list_response.py">ModelListResponse</a></code>
 
 # Providers
 
@@ -386,18 +385,6 @@ Methods:
 - <code title="delete /v1/shields/{identifier}">client.shields.<a href="./src/llama_stack_client/resources/shields.py">delete</a>(identifier) -> None</code>
 - <code title="post /v1/shields">client.shields.<a href="./src/llama_stack_client/resources/shields.py">register</a>(\*\*<a href="src/llama_stack_client/types/shield_register_params.py">params</a>) -> <a href="./src/llama_stack_client/types/shield.py">Shield</a></code>
 
-# SyntheticDataGeneration
-
-Types:
-
-```python
-from llama_stack_client.types import SyntheticDataGenerationResponse
-```
-
-Methods:
-
-- <code title="post /v1/synthetic-data-generation/generate">client.synthetic_data_generation.<a href="./src/llama_stack_client/resources/synthetic_data_generation.py">generate</a>(\*\*<a href="src/llama_stack_client/types/synthetic_data_generation_generate_params.py">params</a>) -> <a href="./src/llama_stack_client/types/synthetic_data_generation_response.py">SyntheticDataGenerationResponse</a></code>
-
 # Scoring
 
 Types:

diff --git 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"

diff --git 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
@@ -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",