azure updates

providers/src/azure/v00.00.00000/services/ai_inference.yaml

@@ -0,0 +1,349 @@
+openapi: 3.0.0
+servers:
+  - url: https://{endpoint}
+    variables:
+      endpoint:
+        default: ""
+        description: The service endpoint host (no scheme), e.g. myaccount.table.cosmos.azure.com:443 - value of the client `endpoint` parameter.
+info:
+  title: Chat Completions Client
+  description: ChatCompletionsClient.
+  contact:
+    name: StackQL Studios
+    url: https://stackql.io/
+    email: info@stackql.io
+  version: 2024-05-01-preview-stackql-generated
+  x-serviceAlias: ai_inference
+  x-sdkPackage: azure-ai-inference
+  x-plane: data
+security:
+  - azure_auth:
+      - user_impersonation
+components:
+  securitySchemes:
+    azure_auth:
+      description: Azure Active Directory OAuth2 Flow.
+      type: oauth2
+      flows:
+        implicit:
+          authorizationUrl: https://login.microsoftonline.com/common/oauth2/authorize
+          scopes:
+            user_impersonation: impersonate your user account
+  schemas:
+    ModelType:
+      type: string
+      enum:
+        - embeddings
+        - image_generation
+        - text_generation
+        - image_embeddings
+        - audio_generation
+        - chat_completion
+    ModelInfo:
+      type: object
+      description: Represents some basic information about the AI model.
+      properties:
+        model_name:
+          type: string
+          description: "The name of the AI model. For example: `Phi21`. Required."
+        model_type:
+          $ref: "#/components/schemas/ModelType"
+          description: 'The type of the AI model. A Unique identifier for the profile. Required. Known values are: "embeddings", "image_generation", "text_generation", "image_embeddings", "audio_generation", and "chat_completion".'
+        model_provider_name:
+          type: string
+          description: "The model provider name. For example: `Microsoft Research`. Required."
+      required:
+        - model_name
+        - model_type
+        - model_provider_name
+    ChatCompletions:
+      type: object
+      description: Representation of the response data from a chat completions request. Completions support a wide variety of tasks and generate text that continues from or "completes" provided prompt data.
+      properties:
+        id:
+          type: string
+          description: A unique identifier associated with this chat completions response. Required.
+        created:
+          type: string
+          format: date-time
+          description: The first timestamp associated with generation activity for this completions response, represented as seconds since the beginning of the Unix epoch of 00:00 on 1 Jan 1970. Required.
+        model:
+          type: string
+          description: The model used for the chat completion. Required.
+        choices:
+          type: array
+          items:
+            $ref: "#/components/schemas/ChatChoice"
+          description: The collection of completions choices associated with this completions response. Generally, `n` choices are generated per provided prompt with a default value of 1. Token limits and other settings may limit the number of choices generated. Required.
+        usage:
+          $ref: "#/components/schemas/CompletionsUsage"
+          description: Usage information for tokens processed and generated as part of this completions operation. Required.
+      required:
+        - id
+        - created
+        - model
+        - choices
+        - usage
+    ChatChoice:
+      type: object
+      description: The representation of a single prompt completion as part of an overall chat completions request. Generally, `n` choices are generated per provided prompt with a default value of 1. Token limits and other settings may limit the number of choices generated.
+      properties:
+        index:
+          type: integer
+          description: The ordered index associated with this chat completions choice. Required.
+        finish_reason:
+          $ref: "#/components/schemas/CompletionsFinishReason"
+          description: 'The reason that this chat completions choice completed its generated. Required. Known values are: "stop", "length", "content_filter", and "tool_calls".'
+        message:
+          $ref: "#/components/schemas/ChatResponseMessage"
+          description: The chat message for a given chat completions prompt. Required.
+      required:
+        - index
+        - finish_reason
+        - message
+    CompletionsFinishReason:
+      type: string
+      enum:
+        - stop
+        - length
+        - content_filter
+        - tool_calls
+    ChatResponseMessage:
+      type: object
+      description: A representation of a chat message as received in a response.
+      properties:
+        role:
+          $ref: "#/components/schemas/ChatRole"
+          description: 'The chat role associated with the message. Required. Known values are: "system", "user", "assistant", "tool", and "developer".'
+        content:
+          type: string
+          description: The content of the message. Required.
+        tool_calls:
+          type: array
+          items:
+            $ref: "#/components/schemas/ChatCompletionsToolCall"
+          description: The tool calls that must be resolved and have their outputs appended to subsequent input messages for the chat completions request to resolve as configured.
+      required:
+        - role
+        - content
+    ChatRole:
+      type: string
+      enum:
+        - system
+        - user
+        - assistant
+        - tool
+        - developer
+    ChatCompletionsToolCall:
+      type: object
+      description: A function tool call requested by the AI model.
+      properties:
+        id:
+          type: string
+          description: The ID of the tool call. Required.
+        type:
+          type: string
+          description: The type of tool call. Currently, only `function` is supported. Required. Default value is "function".
+        function:
+          $ref: "#/components/schemas/FunctionCall"
+          description: The details of the function call requested by the AI model. Required.
+      required:
+        - id
+        - type
+        - function
+    FunctionCall:
+      type: object
+      description: The name and arguments of a function that should be called, as generated by the model.
+      properties:
+        name:
+          type: string
+          description: The name of the function to call. Required.
+        arguments:
+          type: string
+          description: The arguments to call the function with, as generated by the model in JSON format. Note that the model does not always generate valid JSON, and may hallucinate parameters not defined by your function schema. Validate the arguments in your code before calling your function. Required.
+      required:
+        - name
+        - arguments
+    CompletionsUsage:
+      type: object
+      description: Representation of the token counts processed for a completions request. Counts consider all tokens across prompts, choices, choice alternates, best_of generations, and other consumers.
+      properties:
+        completion_tokens:
+          type: integer
+          description: The number of tokens generated across all completions emissions. Required.
+        prompt_tokens:
+          type: integer
+          description: The number of tokens in the provided prompts for the completions request. Required.
+        total_tokens:
+          type: integer
+          description: The total number of tokens processed for the completions request and response. Required.
+      required:
+        - completion_tokens
+        - prompt_tokens
+        - total_tokens
+    EmbeddingsResult:
+      type: object
+      description: Representation of the response data from an embeddings request. Embeddings measure the relatedness of text strings and are commonly used for search, clustering, recommendations, and other similar scenarios.
+      properties:
+        id:
+          type: string
+          description: Unique identifier for the embeddings result. Required.
+        data:
+          type: array
+          items:
+            $ref: "#/components/schemas/EmbeddingItem"
+          description: Embedding values for the prompts submitted in the request. Required.
+        usage:
+          $ref: "#/components/schemas/EmbeddingsUsage"
+          description: Usage counts for tokens input using the embeddings API. Required.
+        model:
+          type: string
+          description: The model ID used to generate this result. Required.
+      required:
+        - id
+        - data
+        - usage
+        - model
+    EmbeddingItem:
+      type: object
+      description: Representation of a single embeddings relatedness comparison.
+      properties:
+        embedding:
+          type: string
+          description: List of embedding values for the input prompt. These represent a measurement of the vector-based relatedness of the provided input. Or a base64 encoded string of the embedding vector. Required. Is either a str type or a [float] type.
+        index:
+          type: integer
+          description: Index of the prompt to which the EmbeddingItem corresponds. Required.
+      required:
+        - embedding
+        - index
+    EmbeddingsUsage:
+      type: object
+      description: Measurement of the amount of tokens used in this request and response.
+      properties:
+        prompt_tokens:
+          type: integer
+          description: Number of tokens in the request. Required.
+        total_tokens:
+          type: integer
+          description: Total number of tokens transacted in this request/response. Should equal the number of tokens in the request. Required.
+      required:
+        - prompt_tokens
+        - total_tokens
+  x-stackQL-resources:
+    model_infos:
+      id: azure.ai_inference.model_infos
+      name: model_infos
+      title: model_infos
+      methods:
+        get_model_info:
+          operation:
+            $ref: "#/paths/~1info?api-version=2024-05-01-preview/get"
+          response:
+            openAPIDocKey: "200"
+            mediaType: application/json
+      sqlVerbs:
+        select:
+          - $ref: "#/components/x-stackQL-resources/model_infos/methods/get_model_info"
+        insert: []
+        update: []
+        delete: []
+    completes:
+      id: azure.ai_inference.completes
+      name: completes
+      title: completes
+      methods:
+        complete:
+          operation:
+            $ref: "#/paths/~1chat~1completions?api-version=2024-05-01-preview/post"
+          response:
+            openAPIDocKey: "200"
+            mediaType: application/json
+      sqlVerbs:
+        select: []
+        insert: []
+        update: []
+        delete: []
+    embeds:
+      id: azure.ai_inference.embeds
+      name: embeds
+      title: embeds
+      methods:
+        embed:
+          operation:
+            $ref: "#/paths/~1embeddings?api-version=2024-05-01-preview/post"
+          response:
+            openAPIDocKey: "200"
+            mediaType: application/json
+      sqlVerbs:
+        select: []
+        insert: []
+        update: []
+        delete: []
+paths:
+  /info?api-version=2024-05-01-preview:
+    get:
+      operationId: ChatCompletionsClient_get_model_info
+      description: Returns information about the AI model. The method makes a REST API call to the `/info` route on the given endpoint. This method will only work when using Serverless API or Managed Compute endpoint. It will not work for GitHub Models endpoint or Azure OpenAI endpoint.
+      parameters: []
+      responses:
+        "200":
+          description: Success
+          content:
+            application/json:
+              schema:
+                $ref: "#/components/schemas/ModelInfo"
+  /chat/completions?api-version=2024-05-01-preview:
+    post:
+      operationId: ChatCompletionsClient_complete
+      description: Gets chat completions for the provided chat messages. Completions support a wide variety of tasks and generate text that continues from or "completes" provided prompt data. The method makes a REST API call to the `/chat/completions` route on the given endpoint.
+      parameters:
+        - name: extra-parameters
+          in: header
+          required: false
+          schema:
+            type: string
+          description: 'Controls what happens if extra parameters, undefined by the REST API, are passed in the JSON request payload. This sets the HTTP request header `extra-parameters`. Known values are: "error", "drop", and "pass-through". Default value is None.'
+      responses:
+        "200":
+          description: Success
+          content:
+            application/json:
+              schema:
+                $ref: "#/components/schemas/ChatCompletions"
+  /embeddings?api-version=2024-05-01-preview:
+    post:
+      operationId: EmbeddingsClient_embed
+      description: Return the embedding vectors for given text prompts. The method makes a REST API call to the `/embeddings` route on the given endpoint.
+      parameters:
+        - name: extra-parameters
+          in: header
+          required: false
+          schema:
+            type: string
+          description: 'Controls what happens if extra parameters, undefined by the REST API, are passed in the JSON request payload. This sets the HTTP request header `extra-parameters`. Known values are: "error", "drop", and "pass-through". Default value is None.'
+      responses:
+        "200":
+          description: Success
+          content:
+            application/json:
+              schema:
+                $ref: "#/components/schemas/EmbeddingsResult"
+  /images/embeddings?api-version=2024-05-01-preview:
+    post:
+      operationId: ImageEmbeddingsClient_embed
+      description: Return the embedding vectors for given images. The method makes a REST API call to the `/images/embeddings` route on the given endpoint.
+      parameters:
+        - name: extra-parameters
+          in: header
+          required: false
+          schema:
+            type: string
+          description: 'Controls what happens if extra parameters, undefined by the REST API, are passed in the JSON request payload. This sets the HTTP request header `extra-parameters`. Known values are: "error", "drop", and "pass-through". Default value is None.'
+      responses:
+        "200":
+          description: Success
+          content:
+            application/json:
+              schema:
+                $ref: "#/components/schemas/EmbeddingsResult"