> ## Documentation Index > Fetch the complete documentation index at: https://docs.galtea.ai/llms.txt > Use this file to discover all available pages before exploring further. # Propose Classifier (Jev) metrics for an LLM judge metric > Splits an LLM judge (PARTIAL_PROMPT) metric's judge prompt into one classifier question per condition, plus one question listing them all when every condition always applies. Persists nothing, consumes no credits, and leaves the source metric unchanged. Create the proposals with `POST /metrics/bulk`. Answers 400 where the deployment does not enable Classifier (Jev) metrics. ## OpenAPI ````yaml https://api.galtea.ai/openapi.json post /metrics/{id}/classifier-conversion openapi: 3.0.0 info: version: 1.0.0 title: Product Management Service API description: API documentation for Product Management Service contact: name: Galtea AI servers: - url: https://api.galtea.ai security: - bearerAuth: [] tags: [] externalDocs: description: Galtea Platform Documentation url: https://docs.galtea.ai paths: /metrics/{id}/classifier-conversion: post: tags: - metrics summary: Propose Classifier (Jev) metrics for an LLM judge metric description: >- Splits an LLM judge (PARTIAL_PROMPT) metric's judge prompt into one classifier question per condition, plus one question listing them all when every condition always applies. Persists nothing, consumes no credits, and leaves the source metric unchanged. Create the proposals with `POST /metrics/bulk`. Answers 400 where the deployment does not enable Classifier (Jev) metrics. operationId: proposeClassifierConversion parameters: - schema: type: string description: The LLM judge (PARTIAL_PROMPT) metric to convert example: metric_123 required: true description: The LLM judge (PARTIAL_PROMPT) metric to convert name: id in: path responses: '200': description: The proposed classifier metrics content: application/json: schema: $ref: '#/components/schemas/ClassifierConversion' '400': description: Bad request content: application/json: schema: $ref: '#/components/schemas/Error' '401': description: Unauthorized content: application/json: schema: $ref: '#/components/schemas/Error' '403': description: Forbidden content: application/json: schema: $ref: '#/components/schemas/Error' '404': description: Not found content: application/json: schema: $ref: '#/components/schemas/Error' '429': description: Too many requests content: application/json: schema: $ref: '#/components/schemas/Error' '502': description: The metrics generator could not split the judge prompt content: application/json: schema: $ref: '#/components/schemas/Error' security: - bearerAuth: [] components: schemas: ClassifierConversion: type: object properties: proposals: type: array items: $ref: '#/components/schemas/ClassifierConversionProposal' description: One classifier metric per condition of the judge prompt. merged: allOf: - $ref: '#/components/schemas/ClassifierConversionMerged' - nullable: true description: >- One classifier metric whose question lists every condition. Null when there are fewer than two conditions or one of them does not always apply. refused: type: array items: $ref: '#/components/schemas/ClassifierConversionRefused' description: The parts no classifier question can check. specifications: type: array items: $ref: '#/components/schemas/ClassifierConversionSpecification' description: >- The source metric's specifications. Send their ids with each metric to link it to them. required: - proposals - merged - refused - specifications Error: type: object properties: error: type: string example: Error type message: type: string example: Error message description ClassifierConversionProposal: type: object properties: name: type: string description: The name to create the metric with, built from the source name. classifierQuestion: $ref: '#/components/schemas/ClassifierQuestion' evaluationParams: type: array items: type: string description: Derived from the question's placeholders. label: type: string description: A few words naming the condition. text: type: string description: The condition, copied word for word from the judge prompt. required: - name - classifierQuestion - evaluationParams - label - text ClassifierConversionMerged: type: object properties: name: type: string description: The name to create the metric with, built from the source name. classifierQuestion: $ref: '#/components/schemas/ClassifierQuestion' evaluationParams: type: array items: type: string description: Derived from the question's placeholders. required: - name - classifierQuestion - evaluationParams ClassifierConversionRefused: type: object properties: text: type: string description: The part of the judge prompt the classifier cannot check. reason: type: string suggestion: type: string nullable: true required: - text - reason - suggestion ClassifierConversionSpecification: type: object properties: id: type: string name: type: string description: type: string productId: type: string required: - id - name - description - productId ClassifierQuestion: type: object properties: type: type: string enum: - yes_no - scale instructions: type: string goodAnswer: type: string enum: - 'yes' - 'no' criteria: type: object nullable: true properties: 'yes': type: string nullable: true 'no': type: string nullable: true required: - 'yes' - 'no' levels: type: array items: type: object properties: description: type: string score: type: number required: - description - score doesNotApply: type: string nullable: true required: - type - instructions securitySchemes: bearerAuth: type: http scheme: bearer description: >- API key authorization. Pass your API key in the Authorization header as a Bearer token. Both new (`gsk_*`) and legacy (`gsk-`) API keys are accepted, e.g. `Authorization: Bearer gsk_...` or `Authorization: Bearer gsk-...`. ```` This documentation is built and hosted on [Mintlify](https://mintlify.com), a developer documentation platform.