Seekr Inference API

openapi: 3.2.0
info:
  title: SeekrFlow Inference API
  description: SeekrFlow API Documentation
  termsOfService: http://www.seekr.com/support
  contact:
    name: Seekr API Support
    url: http://www.seekr.com/contact
    email: contact@seekr.com
  version: 0.1.0
servers:
- url: https://flow.seekr.com
  description: SeekrBuild server base URL
tags:
- name: Inference
paths:
  /v1/inference/chat/completions:
    post:
      summary: Route Chat Completion
      operationId: route_chat_completion_v1_inference_chat_completions_post
      responses:
        '200':
          description: Success
          content:
            application/json:
              schema: {}
      security:
      - APIKeyHeader: []
      tags:
      - Inference
  /v1/inference/internal/chat/completions:
    post:
      summary: Route Chat Completion
      operationId: route_chat_completion_v1_inference_internal_chat_completions_post
      responses:
        '200':
          description: Successful Response
          content:
            application/json:
              schema: {}
      x-excluded: true
      tags:
      - Inference
  /v1/inference/completions:
    post:
      summary: Route Completion
      operationId: route_completion_v1_inference_completions_post
      responses:
        '200':
          description: Success
          content:
            application/json:
              schema: {}
      security:
      - APIKeyHeader: []
      tags:
      - Inference
  /v1/inference/embeddings:
    post:
      summary: Route Embeddings
      operationId: route_embeddings_v1_inference_embeddings_post
      responses:
        '200':
          description: Success
          content:
            application/json:
              schema: {}
      security:
      - APIKeyHeader: []
      tags:
      - Inference
  /v1/inference/internal/embeddings:
    post:
      summary: Route Embeddings
      operationId: route_embeddings_v1_inference_internal_embeddings_post
      responses:
        '200':
          description: Successful Response
          content:
            application/json:
              schema: {}
      x-excluded: true
      tags:
      - Inference
  /inference/tokenize:
    post:
      summary: Route Tokenize
      operationId: route_tokenize_inference_tokenize_post
      responses:
        '200':
          description: Successful Response
          content:
            application/json:
              schema: {}
      security:
      - APIKeyHeader: []
      x-excluded: true
      tags:
      - Inference
  /inference/detokenize:
    post:
      summary: Route Detokenize
      operationId: route_detokenize_inference_detokenize_post
      responses:
        '200':
          description: Successful Response
          content:
            application/json:
              schema: {}
      security:
      - APIKeyHeader: []
      x-excluded: true
      tags:
      - Inference
  /v1/inference/rerank:
    post:
      summary: Route V1 Rerank
      operationId: route_v1_rerank_v1_inference_rerank_post
      responses:
        '200':
          description: Success
          content:
            application/json:
              schema: {}
      security:
      - APIKeyHeader: []
      tags:
      - Inference
  /v1/inference/score:
    post:
      summary: Route V1 Score
      operationId: route_v1_score_v1_inference_score_post
      responses:
        '200':
          description: Success
          content:
            application/json:
              schema: {}
      security:
      - APIKeyHeader: []
      tags:
      - Inference
  /v1/inference/internal/models:
    get:
      summary: Show Models
      description: "Returns a list of all models available in the stack.\n\nArgs:\n    token_data: User data specified by api-key\n\nReturns:\n    JSONResponse: A JSON response containing the list of models.\n\nRaises:\n    Exception: If there is an error in retrieving the endpoint information."
      operationId: show_models_v1_inference_internal_models_get
      responses:
        '200':
          description: Successful Response
          content:
            application/json:
              schema: {}
      security:
      - APIKeyHeader: []
      x-excluded: true
      tags:
      - Inference
  /v1/inference/health:
    get:
      summary: Health
      description: "Endpoint to check the health status of various components.\n\nThis function verifies the health of the service discovery module and\nthe engine stats scraper. If either component is down, it returns a\n503 response with the appropriate status message. If both components\nare healthy, it returns a 200 OK response.\n\nReturns:\n    Response: A JSONResponse with status code 503 if a component is\n    down, or a plain Response with status code 200 if all components\n    are healthy."
      operationId: health_v1_inference_health_get
      responses:
        '200':
          description: Success
          content:
            application/json:
              schema: {}
      tags:
      - Inference
  /v1/inference/audio/transcriptions:
    post:
      summary: Route V1 Audio Transcriptions
      description: Handles audio transcription requests.
      operationId: route_v1_audio_transcriptions_v1_inference_audio_transcriptions_post
      responses:
        '200':
          description: Success
          content:
            application/json:
              schema: {}
      tags:
      - Inference
components:
  securitySchemes:
    APIKeyHeader:
      type: apiKey
      description: Your Seekr API key, sent in the Authorization header with no 'Bearer' prefix.
      in: header
      name: Authorization