> ## Documentation Index
> Fetch the complete documentation index at: https://docs.synapsai.cloud/llms.txt
> Use this file to discover all available pages before exploring further.

# Visual question answering



## OpenAPI

````yaml /api-reference/openapi.json post /v1/question-answering/visual
openapi: 3.1.0
info:
  title: SynapsAI Inference API
  version: 1.0.0
servers:
  - url: https://api.synapsai.cloud
    description: Production server
security: []
paths:
  /v1/question-answering/visual:
    post:
      summary: Visual question answering
      requestBody:
        required: true
        content:
          application/json:
            schema:
              $ref: '#/components/schemas/VisualQuestionAnsweringRequest'
      responses:
        '200':
          description: VQA results (list of label/score dicts)
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/ClassificationListLabelScore'
components:
  schemas:
    VisualQuestionAnsweringRequest:
      allOf:
        - type: object
          description: Request to answer questions about images.
          properties:
            image:
              oneOf:
                - type: string
                - type: array
                  items: {}
                - type: string
                  format: binary
              description: >-
                Image or list of images to be queried (base64, URL or binary).
                Required.
            question:
              oneOf:
                - type: string
                - type: array
                  items:
                    type: string
              description: >-
                Question or list of questions to ask about the image(s).
                Required.
            top_k:
              type: integer
              default: 5
              description: Number of top responses/labels to return.
            timeout:
              type: number
              nullable: true
              description: >-
                Maximum time in seconds for fetching remote images or
                processing; null for indefinite.
          required:
            - image
            - question
    ClassificationListLabelScore:
      type: array
      description: 'Standard classification response: list of label/score pairs.'
      items:
        type: object
        properties:
          label:
            type: string
            description: Predicted label name.
          score:
            type: number
            description: Confidence score (probability-like) for the label.

````