diff --git a/client-sdks/stainless/openapi.yml b/client-sdks/stainless/openapi.yml index 93049a14a..bd22f2129 100644 --- a/client-sdks/stainless/openapi.yml +++ b/client-sdks/stainless/openapi.yml @@ -350,146 +350,46 @@ paths: in: query description: >- An item ID to list items after, used in pagination. - required: true + required: false schema: - oneOf: - - type: string - - type: object - title: NotGiven - description: >- - A sentinel singleton class used to distinguish omitted keyword arguments - from those passed in with the value None (which may have different - behavior). - - For example: - - - ```py - - def get(timeout: Union[int, NotGiven, None] = NotGiven()) -> Response: - ... - - - - get(timeout=1) # 1s timeout - - get(timeout=None) # No timeout - - get() # Default timeout behavior, which may not be statically known - at the method definition. - - ``` + type: string - name: include in: query description: >- Specify additional output data to include in the response. - required: true + required: false schema: - oneOf: - - type: array - items: - type: string - enum: - - code_interpreter_call.outputs - - computer_call_output.output.image_url - - file_search_call.results - - message.input_image.image_url - - message.output_text.logprobs - - reasoning.encrypted_content - - type: object - title: NotGiven - description: >- - A sentinel singleton class used to distinguish omitted keyword arguments - from those passed in with the value None (which may have different - behavior). - - For example: - - - ```py - - def get(timeout: Union[int, NotGiven, None] = NotGiven()) -> Response: - ... - - - - get(timeout=1) # 1s timeout - - get(timeout=None) # No timeout - - get() # Default timeout behavior, which may not be statically known - at the method definition. - - ``` + type: array + items: + type: string + enum: + - web_search_call.action.sources + - code_interpreter_call.outputs + - computer_call_output.output.image_url + - file_search_call.results + - message.input_image.image_url + - message.output_text.logprobs + - reasoning.encrypted_content + title: ConversationItemInclude + description: >- + Specify additional output data to include in the model response. - name: limit in: query description: >- A limit on the number of objects to be returned (1-100, default 20). - required: true + required: false schema: - oneOf: - - type: integer - - type: object - title: NotGiven - description: >- - A sentinel singleton class used to distinguish omitted keyword arguments - from those passed in with the value None (which may have different - behavior). - - For example: - - - ```py - - def get(timeout: Union[int, NotGiven, None] = NotGiven()) -> Response: - ... - - - - get(timeout=1) # 1s timeout - - get(timeout=None) # No timeout - - get() # Default timeout behavior, which may not be statically known - at the method definition. - - ``` + type: integer - name: order in: query description: >- The order to return items in (asc or desc, default desc). - required: true + required: false schema: - oneOf: - - type: string - enum: - - asc - - desc - - type: object - title: NotGiven - description: >- - A sentinel singleton class used to distinguish omitted keyword arguments - from those passed in with the value None (which may have different - behavior). - - For example: - - - ```py - - def get(timeout: Union[int, NotGiven, None] = NotGiven()) -> Response: - ... - - - - get(timeout=1) # 1s timeout - - get(timeout=None) # No timeout - - get() # Default timeout behavior, which may not be statically known - at the method definition. - - ``` + type: string + enum: + - asc + - desc deprecated: false post: responses: @@ -6482,6 +6382,7 @@ components: enum: - llm - embedding + - rerank title: ModelType description: >- Enumeration of supported model types in Llama Stack. @@ -13585,13 +13486,16 @@ tags: embeddings. - This API provides the raw interface to the underlying models. Two kinds of models - are supported: + This API provides the raw interface to the underlying models. Three kinds of + models are supported: - LLM models: these models generate "raw" and "chat" (conversational) completions. - Embedding models: these models generate embeddings to be used for semantic search. + + - Rerank models: these models reorder the documents based on their relevance + to a query. x-displayName: Inference - name: Inspect description: >-