> ## Documentation Index > Fetch the complete documentation index at: https://domoinc-bradley-turek-pfilter-operators-reference.mintlify.site/llms.txt > Use this file to discover all available pages before exploring further. # Classification - Beta > Classify text into one or more predefined categories using LLM structured outputs. ## OpenAPI ````yaml /openapi/product/AI-Services.yaml post /api/ai/v1/classification openapi: 3.1.0 info: title: AI Services description: >- Domo AI Services provide a consistent API to leverage Foundation Models to solve common problems such as natural language SQL generation (text-to-SQL), Summarization, Classification, Tool Calling and others. version: 2.3.3639_master servers: - url: https://{subdomain}.domo.com variables: subdomain: description: The Domo instance subdomain. default: subdomain security: [] tags: - name: AI Services - Classification description: Domo AI Service Classification APIs - name: AI Services - Data Extraction description: Domo AI Service Data Extraction APIs - name: AI Services - Embedding description: Domo AI Service Embedding APIs - name: AI Services - Image description: Domo AI Service Image APIs - name: AI Services - Messages description: Domo AI Service Messages APIs - name: AI Services - Sentiment Analysis description: Domo AI Service Sentiment Analysis APIs - name: AI Services - Text description: Domo AI Service Text APIs paths: /api/ai/v1/classification: post: tags: - AI Services - Classification summary: Classification - Beta description: >- Classify text into one or more predefined categories using LLM structured outputs. operationId: messagesClassification requestBody: content: application/json: schema: $ref: '#/components/schemas/ClassificationRequest' examples: Support Ticket Priority (Single-Label): description: >- Classify support ticket by priority level using single-label classification. value: input: - type: text text: >- URGENT: Our production dashboard is down and we can't access any of our KPI data. This is affecting our entire sales team and we need this resolved immediately! labels: - label: critical description: >- System outage or data loss affecting multiple users or business operations - label: high description: >- Significant functionality issue affecting user productivity - label: medium description: >- Feature not working as expected but workarounds available - label: low description: Minor issue, cosmetic bug, or feature request classificationType: SINGLE_LABEL Product Feedback (Multi-Label): description: Classify product feedback into multiple categories. value: input: - type: text text: >- The new filtering feature is great, but it would be even better if we could save filter presets and share them with our team. Also, the export functionality could use some performance improvements when dealing with large datasets. labels: - label: feature_request description: Request for new functionality or capabilities - label: enhancement description: Suggestion to improve existing functionality - label: bug_report description: Report of incorrect behavior or errors - label: performance description: Feedback about speed, responsiveness, or resource usage - label: usability description: Feedback about user experience or ease of use classificationType: MULTI_LABEL With Specific Model: description: Classification request with a specific model specified. value: input: - type: text text: >- URGENT: Our production dashboard is down and we can't access any of our KPI data. This is affecting our entire sales team and we need this resolved immediately! labels: - label: critical description: >- System outage or data loss affecting multiple users or business operations - label: high description: >- Significant functionality issue affecting user productivity - label: medium description: >- Feature not working as expected but workarounds available - label: low description: Minor issue, cosmetic bug, or feature request classificationType: SINGLE_LABEL model: domo.domo_ai.domogpt-medium-v1.2:anthropic required: true responses: '200': description: Successful classification response. content: application/json: schema: $ref: '#/components/schemas/ClassificationResponse' examples: Classification Response: description: Classification Response value: output: - critical classificationType: SINGLE_LABEL model: domo.domo_ai.domogpt-medium-v1.2:anthropic isCustomerModel: false sessionId: a1b2c3d4-e5f6-7890-abcd-ef1234567890 requestId: f9e8d7c6-b5a4-3210-fedc-ba9876543210 '403': description: Forbidden content: '*/*': schema: type: string '409': description: Conflict security: - domo-developer-token: [] components: schemas: ClassificationRequest: type: object description: >- Request for classifying content into predefined categories using the Messages API.

The Classification service uses LLM structured outputs to reliably classify content into one or more predefined categories. The service dynamically generates JSON schemas based on the provided labels to ensure type-safe responses.

properties: input: type: array description: >- The input message content to classify (text, images, documents, etc.) items: oneOf: - $ref: '#/components/schemas/TextMessageContent' - $ref: '#/components/schemas/ImageMessageContent' - $ref: '#/components/schemas/DocumentMessageContent' labels: type: array description: >- The list of possible classification labels with optional descriptions (2-50 labels required) items: $ref: '#/components/schemas/ClassificationLabel' classificationType: type: string description: 'The type of classification: SINGLE_LABEL or MULTI_LABEL' enum: - SINGLE_LABEL - MULTI_LABEL instructions: type: string description: Optional instructions for classification behavior model: type: string description: The ID of the model to use (optional, uses default if not specified) modelConfiguration: type: object additionalProperties: {} description: Additional model parameters (temperature, max_tokens, etc.) sessionId: type: string format: uuid description: AI session ID for associating with existing session reasoningConfig: $ref: '#/components/schemas/ReasoningConfig' description: Configuration for reasoning behavior required: - classificationType - input - labels ClassificationResponse: type: object description: |- Response for text classification. Supports both single-label and multi-label classifications uniformly. All classification responses return a list of labels via the output() method. properties: output: type: array description: The classification output - a list of selected labels. items: type: string classificationType: type: string description: The type of classification (SINGLE_LABEL or MULTI_LABEL). enum: - SINGLE_LABEL - MULTI_LABEL model: type: string description: The ID of the model used for classification. isCustomerModel: type: boolean description: Whether the model is a customer model (vs Domo provided). sessionId: type: string format: uuid description: The AI session ID associated with this response. requestId: type: string format: uuid description: The request ID associated with this response. modelProviderUsage: $ref: '#/components/schemas/ModelProviderUsage' description: The token usage from the model provider. TextMessageContent: allOf: - $ref: '#/components/schemas/MessageContent' - type: object properties: text: type: string description: the text content of the message description: Text-based message content. ImageMessageContent: allOf: - $ref: '#/components/schemas/MessageContent' - type: object properties: image: $ref: '#/components/schemas/Image' description: the image data and metadata description: Image-based message content. DocumentMessageContent: allOf: - $ref: '#/components/schemas/MessageContent' - type: object properties: document: $ref: '#/components/schemas/Document' description: the document data and metadata description: Document-based message content. ClassificationLabel: type: object description: >- Represents a classification label with an optional description to guide the LLM. properties: label: type: string description: The classification label value (required, 1-100 characters). minLength: 1 description: type: string description: >- Optional description to help the LLM understand when to use this label (max 500 characters). required: - label ReasoningConfig: type: object properties: reasoningEffort: type: string enum: - NONE - LOW - MEDIUM - HIGH ModelProviderUsage: type: object properties: inputTokens: type: integer format: int64 outputTokens: type: integer format: int64 totalTokens: type: integer format: int64 reasoningTokens: type: integer format: int64 MessageContent: description: Base interface for multi-modal message content discriminator: propertyName: type properties: type: type: string required: - type Image: type: object description: Image data and metadata. properties: data: type: string description: the base64 encoded image data type: type: string description: the image type e.g. "base64" mediaType: type: string description: the media type of the image e.g. "image/png" Document: type: object description: Document data and metadata. properties: data: type: string description: the base64-encoded document data type: type: string description: the document type e.g. "base64" mediaType: type: string description: the media type of the document e.g. "application/pdf" name: type: string description: the name of the document securitySchemes: domo-developer-token: type: apiKey name: X-DOMO-Developer-Token in: header ````