feat(api): several updates including Conversations, Responses changes, etc.

Author: stainless-app[bot]

.stats.yml

@@ -1,4 +1,4 @@
-configured_endpoints: 108
-openapi_spec_url: https://storage.googleapis.com/stainless-sdk-openapi-specs/llamastack%2Fllama-stack-client-b220f9f8667d2af8007134d0403b24452c20c9c512ca87d0b69b20b761272609.yml
-openapi_spec_hash: cde1096a830f2081d68f858f020fd53f
-config_hash: 8800bdff1a087b9d5211dda2a7b9f66f
+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: 85d9db5422f2cf897267c0e4825ce1bf

api.md

@@ -102,6 +102,39 @@ Methods:
 
 - <code title="get /v1/responses/{response_id}/input_items">client.responses.input_items.<a href="./src/llama_stack_client/resources/responses/input_items.py">list</a>(response_id, \*\*<a href="src/llama_stack_client/types/responses/input_item_list_params.py">params</a>) -> <a href="./src/llama_stack_client/types/responses/input_item_list_response.py">InputItemListResponse</a></code>
 
+# Conversations
+
+Types:
+
+```python
+from llama_stack_client.types import ConversationObject, ConversationDeleteResponse
+```
+
+Methods:
+
+- <code title="post /v1/conversations">client.conversations.<a href="./src/llama_stack_client/resources/conversations/conversations.py">create</a>(\*\*<a href="src/llama_stack_client/types/conversation_create_params.py">params</a>) -> <a href="./src/llama_stack_client/types/conversation_object.py">ConversationObject</a></code>
+- <code title="get /v1/conversations/{conversation_id}">client.conversations.<a href="./src/llama_stack_client/resources/conversations/conversations.py">retrieve</a>(conversation_id) -> <a href="./src/llama_stack_client/types/conversation_object.py">ConversationObject</a></code>
+- <code title="post /v1/conversations/{conversation_id}">client.conversations.<a href="./src/llama_stack_client/resources/conversations/conversations.py">update</a>(conversation_id, \*\*<a href="src/llama_stack_client/types/conversation_update_params.py">params</a>) -> <a href="./src/llama_stack_client/types/conversation_object.py">ConversationObject</a></code>
+- <code title="delete /v1/conversations/{conversation_id}">client.conversations.<a href="./src/llama_stack_client/resources/conversations/conversations.py">delete</a>(conversation_id) -> <a href="./src/llama_stack_client/types/conversation_delete_response.py">ConversationDeleteResponse</a></code>
+
+## Items
+
+Types:
+
+```python
+from llama_stack_client.types.conversations import (
+    ItemCreateResponse,
+    ItemListResponse,
+    ItemGetResponse,
+)
+```
+
+Methods:
+
+- <code title="post /v1/conversations/{conversation_id}/items">client.conversations.items.<a href="./src/llama_stack_client/resources/conversations/items.py">create</a>(conversation_id, \*\*<a href="src/llama_stack_client/types/conversations/item_create_params.py">params</a>) -> <a href="./src/llama_stack_client/types/conversations/item_create_response.py">ItemCreateResponse</a></code>
+- <code title="get /v1/conversations/{conversation_id}/items">client.conversations.items.<a href="./src/llama_stack_client/resources/conversations/items.py">list</a>(conversation_id, \*\*<a href="src/llama_stack_client/types/conversations/item_list_params.py">params</a>) -> <a href="./src/llama_stack_client/types/conversations/item_list_response.py">ItemListResponse</a></code>
+- <code title="get /v1/conversations/{conversation_id}/items/{item_id}">client.conversations.items.<a href="./src/llama_stack_client/resources/conversations/items.py">get</a>(item_id, \*, conversation_id) -> <a href="./src/llama_stack_client/types/conversations/item_get_response.py">ItemGetResponse</a></code>
+
 # Datasets
 
 Types:

src/llama_stack_client/_client.py

@@ -55,6 +55,7 @@
         completions,
         moderations,
         tool_runtime,
+        conversations,
         vector_stores,
         scoring_functions,
         synthetic_data_generation,
@@ -86,6 +87,7 @@
         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
 
 __all__ = [
@@ -181,6 +183,12 @@ def responses(self) -> ResponsesResource:
 
         return ResponsesResource(self)
 
+    @cached_property
+    def conversations(self) -> ConversationsResource:
+        from .resources.conversations import ConversationsResource
+
+        return ConversationsResource(self)
+
     @cached_property
     def datasets(self) -> DatasetsResource:
         from .resources.datasets import DatasetsResource
@@ -503,6 +511,12 @@ def responses(self) -> AsyncResponsesResource:
 
         return AsyncResponsesResource(self)
 
+    @cached_property
+    def conversations(self) -> AsyncConversationsResource:
+        from .resources.conversations import AsyncConversationsResource
+
+        return AsyncConversationsResource(self)
+
     @cached_property
     def datasets(self) -> AsyncDatasetsResource:
         from .resources.datasets import AsyncDatasetsResource
@@ -774,6 +788,12 @@ def responses(self) -> responses.ResponsesResourceWithRawResponse:
 
         return ResponsesResourceWithRawResponse(self._client.responses)
 
+    @cached_property
+    def conversations(self) -> conversations.ConversationsResourceWithRawResponse:
+        from .resources.conversations import ConversationsResourceWithRawResponse
+
+        return ConversationsResourceWithRawResponse(self._client.conversations)
+
     @cached_property
     def datasets(self) -> datasets.DatasetsResourceWithRawResponse:
         from .resources.datasets import DatasetsResourceWithRawResponse
@@ -931,6 +951,12 @@ def responses(self) -> responses.AsyncResponsesResourceWithRawResponse:
 
         return AsyncResponsesResourceWithRawResponse(self._client.responses)
 
+    @cached_property
+    def conversations(self) -> conversations.AsyncConversationsResourceWithRawResponse:
+        from .resources.conversations import AsyncConversationsResourceWithRawResponse
+
+        return AsyncConversationsResourceWithRawResponse(self._client.conversations)
+
     @cached_property
     def datasets(self) -> datasets.AsyncDatasetsResourceWithRawResponse:
         from .resources.datasets import AsyncDatasetsResourceWithRawResponse
@@ -1090,6 +1116,12 @@ def responses(self) -> responses.ResponsesResourceWithStreamingResponse:
 
         return ResponsesResourceWithStreamingResponse(self._client.responses)
 
+    @cached_property
+    def conversations(self) -> conversations.ConversationsResourceWithStreamingResponse:
+        from .resources.conversations import ConversationsResourceWithStreamingResponse
+
+        return ConversationsResourceWithStreamingResponse(self._client.conversations)
+
     @cached_property
     def datasets(self) -> datasets.DatasetsResourceWithStreamingResponse:
         from .resources.datasets import DatasetsResourceWithStreamingResponse
@@ -1249,6 +1281,12 @@ def responses(self) -> responses.AsyncResponsesResourceWithStreamingResponse:
 
         return AsyncResponsesResourceWithStreamingResponse(self._client.responses)
 
+    @cached_property
+    def conversations(self) -> conversations.AsyncConversationsResourceWithStreamingResponse:
+        from .resources.conversations import AsyncConversationsResourceWithStreamingResponse
+
+        return AsyncConversationsResourceWithStreamingResponse(self._client.conversations)
+
     @cached_property
     def datasets(self) -> datasets.AsyncDatasetsResourceWithStreamingResponse:
         from .resources.datasets import AsyncDatasetsResourceWithStreamingResponse

src/llama_stack_client/resources/__init__.py

@@ -176,6 +176,14 @@
     ToolRuntimeResourceWithStreamingResponse,
     AsyncToolRuntimeResourceWithStreamingResponse,
 )
+from .conversations import (
+    ConversationsResource,
+    AsyncConversationsResource,
+    ConversationsResourceWithRawResponse,
+    AsyncConversationsResourceWithRawResponse,
+    ConversationsResourceWithStreamingResponse,
+    AsyncConversationsResourceWithStreamingResponse,
+)
 from .vector_stores import (
     VectorStoresResource,
     AsyncVectorStoresResource,
@@ -226,6 +234,12 @@
     "AsyncResponsesResourceWithRawResponse",
     "ResponsesResourceWithStreamingResponse",
     "AsyncResponsesResourceWithStreamingResponse",
+    "ConversationsResource",
+    "AsyncConversationsResource",
+    "ConversationsResourceWithRawResponse",
+    "AsyncConversationsResourceWithRawResponse",
+    "ConversationsResourceWithStreamingResponse",
+    "AsyncConversationsResourceWithStreamingResponse",
     "DatasetsResource",
     "AsyncDatasetsResource",
     "DatasetsResourceWithRawResponse",

src/llama_stack_client/resources/chat/completions.py

@@ -83,9 +83,10 @@ def create(
         extra_body: Body | None = None,
         timeout: float | httpx.Timeout | None | NotGiven = not_given,
     ) -> CompletionCreateResponse:
-        """
-        Generate an OpenAI-compatible chat completion for the given messages using the
-        specified model.
+        """Create chat completions.
+
+        Generate an OpenAI-compatible chat completion for the
+        given messages using the specified model.
 
         Args:
           messages: List of messages in the conversation.
@@ -179,9 +180,10 @@ def create(
         extra_body: Body | None = None,
         timeout: float | httpx.Timeout | None | NotGiven = not_given,
     ) -> Stream[ChatCompletionChunk]:
-        """
-        Generate an OpenAI-compatible chat completion for the given messages using the
-        specified model.
+        """Create chat completions.
+
+        Generate an OpenAI-compatible chat completion for the
+        given messages using the specified model.
 
         Args:
           messages: List of messages in the conversation.
@@ -275,9 +277,10 @@ def create(
         extra_body: Body | None = None,
         timeout: float | httpx.Timeout | None | NotGiven = not_given,
     ) -> CompletionCreateResponse | Stream[ChatCompletionChunk]:
-        """
-        Generate an OpenAI-compatible chat completion for the given messages using the
-        specified model.
+        """Create chat completions.
+
+        Generate an OpenAI-compatible chat completion for the
+        given messages using the specified model.
 
         Args:
           messages: List of messages in the conversation.
@@ -424,7 +427,8 @@ def retrieve(
         extra_body: Body | None = None,
         timeout: float | httpx.Timeout | None | NotGiven = not_given,
     ) -> CompletionRetrieveResponse:
-        """
+        """Get chat completion.
+
         Describe a chat completion by its ID.
 
         Args:
@@ -461,7 +465,7 @@ def list(
         timeout: float | httpx.Timeout | None | NotGiven = not_given,
     ) -> SyncOpenAICursorPage[CompletionListResponse]:
         """
-        List all chat completions.
+        List chat completions.
 
         Args:
           after: The ID of the last chat completion to return.
@@ -556,9 +560,10 @@ async def create(
         extra_body: Body | None = None,
         timeout: float | httpx.Timeout | None | NotGiven = not_given,
     ) -> CompletionCreateResponse:
-        """
-        Generate an OpenAI-compatible chat completion for the given messages using the
-        specified model.
+        """Create chat completions.
+
+        Generate an OpenAI-compatible chat completion for the
+        given messages using the specified model.
 
         Args:
           messages: List of messages in the conversation.
@@ -652,9 +657,10 @@ async def create(
         extra_body: Body | None = None,
         timeout: float | httpx.Timeout | None | NotGiven = not_given,
     ) -> AsyncStream[ChatCompletionChunk]:
-        """
-        Generate an OpenAI-compatible chat completion for the given messages using the
-        specified model.
+        """Create chat completions.
+
+        Generate an OpenAI-compatible chat completion for the
+        given messages using the specified model.
 
         Args:
           messages: List of messages in the conversation.
@@ -748,9 +754,10 @@ async def create(
         extra_body: Body | None = None,
         timeout: float | httpx.Timeout | None | NotGiven = not_given,
     ) -> CompletionCreateResponse | AsyncStream[ChatCompletionChunk]:
-        """
-        Generate an OpenAI-compatible chat completion for the given messages using the
-        specified model.
+        """Create chat completions.
+
+        Generate an OpenAI-compatible chat completion for the
+        given messages using the specified model.
 
         Args:
           messages: List of messages in the conversation.
@@ -897,7 +904,8 @@ async def retrieve(
         extra_body: Body | None = None,
         timeout: float | httpx.Timeout | None | NotGiven = not_given,
     ) -> CompletionRetrieveResponse:
-        """
+        """Get chat completion.
+
         Describe a chat completion by its ID.
 
         Args:
@@ -934,7 +942,7 @@ def list(
         timeout: float | httpx.Timeout | None | NotGiven = not_given,
     ) -> AsyncPaginator[CompletionListResponse, AsyncOpenAICursorPage[CompletionListResponse]]:
         """
-        List all chat completions.
+        List chat completions.
 
         Args:
           after: The ID of the last chat completion to return.

src/llama_stack_client/resources/completions.py

@@ -76,9 +76,10 @@ def create(
         extra_body: Body | None = None,
         timeout: float | httpx.Timeout | None | NotGiven = not_given,
     ) -> CompletionCreateResponse:
-        """
-        Generate an OpenAI-compatible completion for the given prompt using the
-        specified model.
+        """Create completion.
+
+        Generate an OpenAI-compatible completion for the given prompt
+        using the specified model.
 
         Args:
           model: The identifier of the model to use. The model must be registered with Llama
@@ -159,9 +160,10 @@ def create(
         extra_body: Body | None = None,
         timeout: float | httpx.Timeout | None | NotGiven = not_given,
     ) -> Stream[CompletionCreateResponse]:
-        """
-        Generate an OpenAI-compatible completion for the given prompt using the
-        specified model.
+        """Create completion.
+
+        Generate an OpenAI-compatible completion for the given prompt
+        using the specified model.
 
         Args:
           model: The identifier of the model to use. The model must be registered with Llama
@@ -242,9 +244,10 @@ def create(
         extra_body: Body | None = None,
         timeout: float | httpx.Timeout | None | NotGiven = not_given,
     ) -> CompletionCreateResponse | Stream[CompletionCreateResponse]:
-        """
-        Generate an OpenAI-compatible completion for the given prompt using the
-        specified model.
+        """Create completion.
+
+        Generate an OpenAI-compatible completion for the given prompt
+        using the specified model.
 
         Args:
           model: The identifier of the model to use. The model must be registered with Llama
@@ -414,9 +417,10 @@ async def create(
         extra_body: Body | None = None,
         timeout: float | httpx.Timeout | None | NotGiven = not_given,
     ) -> CompletionCreateResponse:
-        """
-        Generate an OpenAI-compatible completion for the given prompt using the
-        specified model.
+        """Create completion.
+
+        Generate an OpenAI-compatible completion for the given prompt
+        using the specified model.
 
         Args:
           model: The identifier of the model to use. The model must be registered with Llama
@@ -497,9 +501,10 @@ async def create(
         extra_body: Body | None = None,
         timeout: float | httpx.Timeout | None | NotGiven = not_given,
     ) -> AsyncStream[CompletionCreateResponse]:
-        """
-        Generate an OpenAI-compatible completion for the given prompt using the
-        specified model.
+        """Create completion.
+
+        Generate an OpenAI-compatible completion for the given prompt
+        using the specified model.
 
         Args:
           model: The identifier of the model to use. The model must be registered with Llama
@@ -580,9 +585,10 @@ async def create(
         extra_body: Body | None = None,
         timeout: float | httpx.Timeout | None | NotGiven = not_given,
     ) -> CompletionCreateResponse | AsyncStream[CompletionCreateResponse]:
-        """
-        Generate an OpenAI-compatible completion for the given prompt using the
-        specified model.
+        """Create completion.
+
+        Generate an OpenAI-compatible completion for the given prompt
+        using the specified model.
 
         Args:
           model: The identifier of the model to use. The model must be registered with Llama