release: 0.3.0-alpha.6

.release-please-manifest.json

@@ -1,3 +1,3 @@
 {
-  ".": "0.3.0-alpha.5"
+  ".": "0.3.0-alpha.6"
 }

.stats.yml

@@ -1,4 +1,4 @@
-configured_endpoints: 115
-openapi_spec_url: https://storage.googleapis.com/stainless-sdk-openapi-specs/llamastack%2Fllama-stack-client-8a12a05ba6892999ac506f69d5cbbc7218f28ee1a11bf8e0e548c603435bb643.yml
-openapi_spec_hash: 871ce212a98bdad4a44ec7fbf58d9fcb
-config_hash: 4c1ba9dc45c31189cd1b039d003a3544
+configured_endpoints: 111
+openapi_spec_url: https://storage.googleapis.com/stainless-sdk-openapi-specs/llamastack%2Fllama-stack-client-15a929a0b71de779accc56bd09d1e5f580e216affdb408cf9890bc7a37847e9e.yml
+openapi_spec_hash: 5db9f7c7e80427cfa0298cbb01689559
+config_hash: 06758df5c4f261f9c97eafcef7e0028f

CHANGELOG.md

@@ -1,5 +1,18 @@
 # Changelog
 
+## 0.3.0-alpha.6 (2025-10-13)
+
+Full Changelog: [v0.3.0-alpha.5...v0.3.0-alpha.6](https://github.com/llamastack/llama-stack-client-python/compare/v0.3.0-alpha.5...v0.3.0-alpha.6)
+
+### Features
+
+* **api:** updates to vector_store, etc. ([6c796ca](https://github.com/llamastack/llama-stack-client-python/commit/6c796ca49ee5e38c2951216558151fe349a303bf))
+
+
+### Chores
+
+* **internal:** detect missing future annotations with ruff ([e497f03](https://github.com/llamastack/llama-stack-client-python/commit/e497f0391aad3e75dceee288e299e0f74bd7f294))
+
 ## 0.3.0-alpha.5 (2025-10-10)
 
 Full Changelog: [v0.3.0-alpha.4...v0.3.0-alpha.5](https://github.com/llamastack/llama-stack-client-python/compare/v0.3.0-alpha.4...v0.3.0-alpha.5)

api.md

@@ -234,26 +234,6 @@ Methods:
 - <code title="post /v1/vector-io/insert">client.vector_io.<a href="./src/llama_stack_client/resources/vector_io.py">insert</a>(\*\*<a href="src/llama_stack_client/types/vector_io_insert_params.py">params</a>) -> None</code>
 - <code title="post /v1/vector-io/query">client.vector_io.<a href="./src/llama_stack_client/resources/vector_io.py">query</a>(\*\*<a href="src/llama_stack_client/types/vector_io_query_params.py">params</a>) -> <a href="./src/llama_stack_client/types/query_chunks_response.py">QueryChunksResponse</a></code>
 
-# VectorDBs
-
-Types:
-
-```python
-from llama_stack_client.types import (
-    ListVectorDBsResponse,
-    VectorDBRetrieveResponse,
-    VectorDBListResponse,
-    VectorDBRegisterResponse,
-)
-```
-
-Methods:
-
-- <code title="get /v1/vector-dbs/{vector_db_id}">client.vector_dbs.<a href="./src/llama_stack_client/resources/vector_dbs.py">retrieve</a>(vector_db_id) -> <a href="./src/llama_stack_client/types/vector_db_retrieve_response.py">VectorDBRetrieveResponse</a></code>
-- <code title="get /v1/vector-dbs">client.vector_dbs.<a href="./src/llama_stack_client/resources/vector_dbs.py">list</a>() -> <a href="./src/llama_stack_client/types/vector_db_list_response.py">VectorDBListResponse</a></code>
-- <code title="post /v1/vector-dbs">client.vector_dbs.<a href="./src/llama_stack_client/resources/vector_dbs.py">register</a>(\*\*<a href="src/llama_stack_client/types/vector_db_register_params.py">params</a>) -> <a href="./src/llama_stack_client/types/vector_db_register_response.py">VectorDBRegisterResponse</a></code>
-- <code title="delete /v1/vector-dbs/{vector_db_id}">client.vector_dbs.<a href="./src/llama_stack_client/resources/vector_dbs.py">unregister</a>(vector_db_id) -> None</code>
-
 # VectorStores
 
 Types:

pyproject.toml

@@ -1,6 +1,6 @@
 [project]
 name = "llama_stack_client"
-version = "0.3.0-alpha.5"
+version = "0.3.0-alpha.6"
 description = "The official Python library for the llama-stack-client API"
 dynamic = ["readme"]
 license = "MIT"
@@ -194,6 +194,8 @@ select = [
   "B",
   # remove unused imports
   "F401",
+  # check for missing future annotations
+  "FA102",
   # bare except statements
   "E722",
   # unused arguments
@@ -216,6 +218,8 @@ unfixable = [
   "T203",
 ]
 
+extend-safe-fixes = ["FA102"]
+
 [tool.ruff.lint.flake8-tidy-imports.banned-api]
 "functools.lru_cache".msg = "This function does not retain type information for the wrapped function's arguments; The `lru_cache` function from `_utils` should be used instead"
 

src/llama_stack_client/_client.py

@@ -51,7 +51,6 @@
         benchmarks,
         embeddings,
         toolgroups,
-        vector_dbs,
         completions,
         moderations,
         tool_runtime,
@@ -75,7 +74,6 @@
     from .resources.benchmarks import BenchmarksResource, AsyncBenchmarksResource
     from .resources.embeddings import EmbeddingsResource, AsyncEmbeddingsResource
     from .resources.toolgroups import ToolgroupsResource, AsyncToolgroupsResource
-    from .resources.vector_dbs import VectorDBsResource, AsyncVectorDBsResource
     from .resources.alpha.alpha import AlphaResource, AsyncAlphaResource
     from .resources.completions import CompletionsResource, AsyncCompletionsResource
     from .resources.moderations import ModerationsResource, AsyncModerationsResource
@@ -225,12 +223,6 @@ def vector_io(self) -> VectorIoResource:
 
         return VectorIoResource(self)
 
-    @cached_property
-    def vector_dbs(self) -> VectorDBsResource:
-        from .resources.vector_dbs import VectorDBsResource
-
-        return VectorDBsResource(self)
-
     @cached_property
     def vector_stores(self) -> VectorStoresResource:
         from .resources.vector_stores import VectorStoresResource
@@ -553,12 +545,6 @@ def vector_io(self) -> AsyncVectorIoResource:
 
         return AsyncVectorIoResource(self)
 
-    @cached_property
-    def vector_dbs(self) -> AsyncVectorDBsResource:
-        from .resources.vector_dbs import AsyncVectorDBsResource
-
-        return AsyncVectorDBsResource(self)
-
     @cached_property
     def vector_stores(self) -> AsyncVectorStoresResource:
         from .resources.vector_stores import AsyncVectorStoresResource
@@ -830,12 +816,6 @@ def vector_io(self) -> vector_io.VectorIoResourceWithRawResponse:
 
         return VectorIoResourceWithRawResponse(self._client.vector_io)
 
-    @cached_property
-    def vector_dbs(self) -> vector_dbs.VectorDBsResourceWithRawResponse:
-        from .resources.vector_dbs import VectorDBsResourceWithRawResponse
-
-        return VectorDBsResourceWithRawResponse(self._client.vector_dbs)
-
     @cached_property
     def vector_stores(self) -> vector_stores.VectorStoresResourceWithRawResponse:
         from .resources.vector_stores import VectorStoresResourceWithRawResponse
@@ -993,12 +973,6 @@ def vector_io(self) -> vector_io.AsyncVectorIoResourceWithRawResponse:
 
         return AsyncVectorIoResourceWithRawResponse(self._client.vector_io)
 
-    @cached_property
-    def vector_dbs(self) -> vector_dbs.AsyncVectorDBsResourceWithRawResponse:
-        from .resources.vector_dbs import AsyncVectorDBsResourceWithRawResponse
-
-        return AsyncVectorDBsResourceWithRawResponse(self._client.vector_dbs)
-
     @cached_property
     def vector_stores(self) -> vector_stores.AsyncVectorStoresResourceWithRawResponse:
         from .resources.vector_stores import AsyncVectorStoresResourceWithRawResponse
@@ -1158,12 +1132,6 @@ def vector_io(self) -> vector_io.VectorIoResourceWithStreamingResponse:
 
         return VectorIoResourceWithStreamingResponse(self._client.vector_io)
 
-    @cached_property
-    def vector_dbs(self) -> vector_dbs.VectorDBsResourceWithStreamingResponse:
-        from .resources.vector_dbs import VectorDBsResourceWithStreamingResponse
-
-        return VectorDBsResourceWithStreamingResponse(self._client.vector_dbs)
-
     @cached_property
     def vector_stores(self) -> vector_stores.VectorStoresResourceWithStreamingResponse:
         from .resources.vector_stores import VectorStoresResourceWithStreamingResponse
@@ -1323,12 +1291,6 @@ def vector_io(self) -> vector_io.AsyncVectorIoResourceWithStreamingResponse:
 
         return AsyncVectorIoResourceWithStreamingResponse(self._client.vector_io)
 
-    @cached_property
-    def vector_dbs(self) -> vector_dbs.AsyncVectorDBsResourceWithStreamingResponse:
-        from .resources.vector_dbs import AsyncVectorDBsResourceWithStreamingResponse
-
-        return AsyncVectorDBsResourceWithStreamingResponse(self._client.vector_dbs)
-
     @cached_property
     def vector_stores(self) -> vector_stores.AsyncVectorStoresResourceWithStreamingResponse:
         from .resources.vector_stores import AsyncVectorStoresResourceWithStreamingResponse

src/llama_stack_client/resources/__init__.py

@@ -144,14 +144,6 @@
     ToolgroupsResourceWithStreamingResponse,
     AsyncToolgroupsResourceWithStreamingResponse,
 )
-from .vector_dbs import (
-    VectorDBsResource,
-    AsyncVectorDBsResource,
-    VectorDBsResourceWithRawResponse,
-    AsyncVectorDBsResourceWithRawResponse,
-    VectorDBsResourceWithStreamingResponse,
-    AsyncVectorDBsResourceWithStreamingResponse,
-)
 from .completions import (
     CompletionsResource,
     AsyncCompletionsResource,
@@ -276,12 +268,6 @@
     "AsyncVectorIoResourceWithRawResponse",
     "VectorIoResourceWithStreamingResponse",
     "AsyncVectorIoResourceWithStreamingResponse",
-    "VectorDBsResource",
-    "AsyncVectorDBsResource",
-    "VectorDBsResourceWithRawResponse",
-    "AsyncVectorDBsResourceWithRawResponse",
-    "VectorDBsResourceWithStreamingResponse",
-    "AsyncVectorDBsResourceWithStreamingResponse",
     "VectorStoresResource",
     "AsyncVectorStoresResource",
     "VectorStoresResourceWithRawResponse",

src/llama_stack_client/resources/completions.py

@@ -54,13 +54,11 @@ def create(
         best_of: int | Omit = omit,
         echo: bool | Omit = omit,
         frequency_penalty: float | Omit = omit,
-        guided_choice: SequenceNotStr[str] | Omit = omit,
         logit_bias: Dict[str, float] | Omit = omit,
         logprobs: bool | Omit = omit,
         max_tokens: int | Omit = omit,
         n: int | Omit = omit,
         presence_penalty: float | Omit = omit,
-        prompt_logprobs: int | Omit = omit,
         seed: int | Omit = omit,
         stop: Union[str, SequenceNotStr[str]] | Omit = omit,
         stream: Literal[False] | Omit = omit,
@@ -139,13 +137,11 @@ def create(
         best_of: int | Omit = omit,
         echo: bool | Omit = omit,
         frequency_penalty: float | Omit = omit,
-        guided_choice: SequenceNotStr[str] | Omit = omit,
         logit_bias: Dict[str, float] | Omit = omit,
         logprobs: bool | Omit = omit,
         max_tokens: int | Omit = omit,
         n: int | Omit = omit,
         presence_penalty: float | Omit = omit,
-        prompt_logprobs: int | Omit = omit,
         seed: int | Omit = omit,
         stop: Union[str, SequenceNotStr[str]] | Omit = omit,
         stream_options: Dict[str, Union[bool, float, str, Iterable[object], object, None]] | Omit = omit,
@@ -223,13 +219,11 @@ def create(
         best_of: int | Omit = omit,
         echo: bool | Omit = omit,
         frequency_penalty: float | Omit = omit,
-        guided_choice: SequenceNotStr[str] | Omit = omit,
         logit_bias: Dict[str, float] | Omit = omit,
         logprobs: bool | Omit = omit,
         max_tokens: int | Omit = omit,
         n: int | Omit = omit,
         presence_penalty: float | Omit = omit,
-        prompt_logprobs: int | Omit = omit,
         seed: int | Omit = omit,
         stop: Union[str, SequenceNotStr[str]] | Omit = omit,
         stream_options: Dict[str, Union[bool, float, str, Iterable[object], object, None]] | Omit = omit,
@@ -306,13 +300,11 @@ def create(
         best_of: int | Omit = omit,
         echo: bool | Omit = omit,
         frequency_penalty: float | Omit = omit,
-        guided_choice: SequenceNotStr[str] | Omit = omit,
         logit_bias: Dict[str, float] | Omit = omit,
         logprobs: bool | Omit = omit,
         max_tokens: int | Omit = omit,
         n: int | Omit = omit,
         presence_penalty: float | Omit = omit,
-        prompt_logprobs: int | Omit = omit,
         seed: int | Omit = omit,
         stop: Union[str, SequenceNotStr[str]] | Omit = omit,
         stream: Literal[False] | Literal[True] | Omit = omit,
@@ -337,13 +329,11 @@ def create(
                     "best_of": best_of,
                     "echo": echo,
                     "frequency_penalty": frequency_penalty,
-                    "guided_choice": guided_choice,
                     "logit_bias": logit_bias,
                     "logprobs": logprobs,
                     "max_tokens": max_tokens,
                     "n": n,
                     "presence_penalty": presence_penalty,
-                    "prompt_logprobs": prompt_logprobs,
                     "seed": seed,
                     "stop": stop,
                     "stream": stream,
@@ -395,13 +385,11 @@ async def create(
         best_of: int | Omit = omit,
         echo: bool | Omit = omit,
         frequency_penalty: float | Omit = omit,
-        guided_choice: SequenceNotStr[str] | Omit = omit,
         logit_bias: Dict[str, float] | Omit = omit,
         logprobs: bool | Omit = omit,
         max_tokens: int | Omit = omit,
         n: int | Omit = omit,
         presence_penalty: float | Omit = omit,
-        prompt_logprobs: int | Omit = omit,
         seed: int | Omit = omit,
         stop: Union[str, SequenceNotStr[str]] | Omit = omit,
         stream: Literal[False] | Omit = omit,
@@ -480,13 +468,11 @@ async def create(
         best_of: int | Omit = omit,
         echo: bool | Omit = omit,
         frequency_penalty: float | Omit = omit,
-        guided_choice: SequenceNotStr[str] | Omit = omit,
         logit_bias: Dict[str, float] | Omit = omit,
         logprobs: bool | Omit = omit,
         max_tokens: int | Omit = omit,
         n: int | Omit = omit,
         presence_penalty: float | Omit = omit,
-        prompt_logprobs: int | Omit = omit,
         seed: int | Omit = omit,
         stop: Union[str, SequenceNotStr[str]] | Omit = omit,
         stream_options: Dict[str, Union[bool, float, str, Iterable[object], object, None]] | Omit = omit,
@@ -564,13 +550,11 @@ async def create(
         best_of: int | Omit = omit,
         echo: bool | Omit = omit,
         frequency_penalty: float | Omit = omit,
-        guided_choice: SequenceNotStr[str] | Omit = omit,
         logit_bias: Dict[str, float] | Omit = omit,
         logprobs: bool | Omit = omit,
         max_tokens: int | Omit = omit,
         n: int | Omit = omit,
         presence_penalty: float | Omit = omit,
-        prompt_logprobs: int | Omit = omit,
         seed: int | Omit = omit,
         stop: Union[str, SequenceNotStr[str]] | Omit = omit,
         stream_options: Dict[str, Union[bool, float, str, Iterable[object], object, None]] | Omit = omit,
@@ -647,13 +631,11 @@ async def create(
         best_of: int | Omit = omit,
         echo: bool | Omit = omit,
         frequency_penalty: float | Omit = omit,
-        guided_choice: SequenceNotStr[str] | Omit = omit,
         logit_bias: Dict[str, float] | Omit = omit,
         logprobs: bool | Omit = omit,
         max_tokens: int | Omit = omit,
         n: int | Omit = omit,
         presence_penalty: float | Omit = omit,
-        prompt_logprobs: int | Omit = omit,
         seed: int | Omit = omit,
         stop: Union[str, SequenceNotStr[str]] | Omit = omit,
         stream: Literal[False] | Literal[True] | Omit = omit,
@@ -678,13 +660,11 @@ async def create(
                     "best_of": best_of,
                     "echo": echo,
                     "frequency_penalty": frequency_penalty,
-                    "guided_choice": guided_choice,
                     "logit_bias": logit_bias,
                     "logprobs": logprobs,
                     "max_tokens": max_tokens,
                     "n": n,
                     "presence_penalty": presence_penalty,
-                    "prompt_logprobs": prompt_logprobs,
                     "seed": seed,
                     "stop": stop,
                     "stream": stream,

src/llama_stack_client/resources/safety.py

@@ -19,7 +19,6 @@
 )
 from .._base_client import make_request_options
 from ..types.run_shield_response import RunShieldResponse
-from ..types.shared_params.message import Message
 
 __all__ = ["SafetyResource", "AsyncSafetyResource"]
 
@@ -47,7 +46,7 @@ def with_streaming_response(self) -> SafetyResourceWithStreamingResponse:
     def run_shield(
         self,
         *,
-        messages: Iterable[Message],
+        messages: Iterable[safety_run_shield_params.Message],
         params: Dict[str, Union[bool, float, str, Iterable[object], object, None]],
         shield_id: str,
         # Use the following arguments if you need to pass additional parameters to the API that aren't available via kwargs.
@@ -116,7 +115,7 @@ def with_streaming_response(self) -> AsyncSafetyResourceWithStreamingResponse:
     async def run_shield(
         self,
         *,
-        messages: Iterable[Message],
+        messages: Iterable[safety_run_shield_params.Message],
         params: Dict[str, Union[bool, float, str, Iterable[object], object, None]],
         shield_id: str,
         # Use the following arguments if you need to pass additional parameters to the API that aren't available via kwargs.