openapi: 3.1.0
info:
  title: LLM Bridge API with OpenAI API compitable
  description: API reference for YoMo LLM Bridge
  version: 1.0.0
servers:
  - url: http://localhost:9000/
    description: Local development server
paths:
  /v1/chat/completions:
    post:
      operationId: createChatCompletion
      summary: Create a chat completion
      description: |
        Creates a completion for the chat message
      requestBody:
        required: true
        content:
          application/json:
            schema:
              $ref: "#/components/schemas/CreateChatCompletionRequest"
      responses:
        '200':
          description: OK
          content:
            application/json:
              schema:
                $ref: "#/components/schemas/CreateChatCompletionResponse"
components:
  schemas:
    CreateChatCompletionRequest:
      allOf:
        - $ref: "#/components/schemas/CreateModelResponseProperties"
    CreateChatCompletionResponse:
      type: object
      description: |
        Represents a chat completion response returned by model, based on
        the provided input.
      properties:
        id:
          type: string
          description: A unique identifier for the chat completion.
        object:
          type: string
          enum: [chat.completion]
          description: The object type, which is always "chat.completion"
        created:
          type: integer
          description: The Unix timestamp (in seconds) of when the chat completion was created.
        model:
          type: string
          description: The model used for the chat completion.
        choices:
          type: array
          description: A list of chat completion choices.
          items:
            type: object
            properties:
              index:
                type: integer
                description: The index of the choice in the list of choices.
              message:
                $ref: "#/components/schemas/ChatCompletionResponseMessage"
              finish_reason:
                type: string
                enum: [stop, length, function_call, content_filter, tool_calls]
                description: The reason the chat completion finished.
        usage:
          $ref: "#/components/schemas/CompletionUsage"
      required:
        - choices
        - object
    ChatCompletionResponseMessage:
      type: object
      properties:
        role:
          type: string
          enum: [assistant]
          description: The role of the message sender, always "assistant" for responses.
        content:
          type: string
          nullable: true
          description: The content of the message.
      required:
        - role
    CompletionUsage:
      type: object
      properties:
        prompt_tokens:
          type: integer
          description: Number of tokens in the prompt.
        completion_tokens:
          type: integer
          description: Number of tokens in the completion.
        total_tokens:
          type: integer
          description: Total number of tokens used (prompt + completion).
    CreateModelResponseProperties:
      type: object
      properties:
        model:
          type: string
          description: ID of the model to use.
        messages:
          type: array
          description: A list of messages comprising the conversation so far.
          items:
            $ref: "#/components/schemas/ChatCompletionRequestMessage"
        temperature:
          type: number
          minimum: 0
          maximum: 2
          default: 1
          description: What sampling temperature to use, between 0 and 2.
        top_p:
          type: number
          minimum: 0
          maximum: 1
          default: 1
          description: An alternative to sampling with temperature, called nucleus sampling
        stream:
          type: boolean
          default: false
          description: If set, partial message deltas will be sent.
      required:
        - messages
    ChatCompletionRequestMessage:
      oneOf:
        - $ref: "#/components/schemas/ChatCompletionRequestSystemMessage"
        - $ref: "#/components/schemas/ChatCompletionRequestUserMessage"
        - $ref: "#/components/schemas/ChatCompletionRequestAssistantMessage"
    ChatCompletionRequestSystemMessage:
      type: object
      properties:
        role:
          type: string
          enum: [system]
          description: The role of the message sender, "system" in this case.
        content:
          type: string
          description: The content of the message.
      required:
        - role
        - content
    ChatCompletionRequestUserMessage:
      type: object
      properties:
        role:
          type: string
          enum: [user]
          description: The role of the message sender, "user" in this case.
        content:
          type: string
          description: The content of the message.
      required:
        - role
        - content
    ChatCompletionRequestAssistantMessage:
      type: object
      properties:
        role:
          type: string
          enum: [assistant]
          description: The role of the message sender, "assistant" in this case.
        content:
          type: string
          nullable: true
          description: The content of the message.
      required:
        - role
security:
  - ApiKeyAuth: []