Oracle Partitioning Vector Database/Inference Operations API

openapi: 3.2.0
info:
  description: '<p>Provides the Oracle REST Data Services (ORDS) users the ability to perform Oracle Database management and monitoring operations through a user-friendly REST API. Depending on the database version and configuration, ORDS database APIs provide services such as manage pluggable databases, export data, and review database performance.</p><p>To install and configure Oracle REST Data Services refer to the <a href=https://docs.oracle.com/pls/topic/lookup?ctx=ords-latest&id=ORDIG> Oracle&reg REST Data Services Installation and Configuration Guide</a>.</p>

    <p>An OpenAPI V3 document that describes the available ORDS database API services can be retrieved from a running ORDS instance. The API document can be imported into compatible development tools and invoked from there. The URL to retrieve the API document depends on the your configuration. <p><p>The pattern for the API document URL is: </p>

    <code>https://&lt;server&gt;/&lt;context root&gt;/&lt;my database&gt;/&lt;my schema&gt;/_/db-api/stable/&lt;service path&gt;  </code>

    <p>Where, the <code>&lt;my database&gt;</code> and  <code>&lt;my schema&gt;</code> variables can be optional, depending on the ORDS configuration and the service invoked.'
  version: 2026.03.26
  title: Oracle REST Data Services Vector Database/Inference Operations API
  contact:
    name: Oracle REST Data Services
    url: https://www.oracle.com/database/technologies/appdev/rest.html
  x-summary: Provides the Oracle REST Data Services (ORDS) users the ability to perform Oracle Database management and monitoring operations through a user-friendly REST API.
tags:
- name: Vector Database/Inference Operations
  description: The operations from the Vector Database/Inference Operations category.
paths:
  /vecdb/embed:
    post:
      tags:
      - Vector Database/Inference Operations
      operationId: generate_embedding
      summary: Generate text embeddings
      description: Generate vector embeddings for one or more input texts using an ONNX model hosted in the database.
      security:
      - BasicAuth: []
      - BearerAuth: []
      - OAuth2: []
      requestBody:
        required: true
        content:
          application/json:
            schema:
              $ref: '#/components/schemas/VectorEmbedRequest'
            example:
              modelName: TEXT_MODEL
              inputs:
              - text: Apple is a popular fruit known for its sweetness and crisp texture.
              - text: The tech company Apple is known for its innovative products like the iPhone.
              - text: Many people enjoy eating apples as a healthy snack.
              - text: Apple Inc. has revolutionized the tech industry with its sleek designs and user-friendly interfaces.
              - text: An apple a day keeps the doctor away, as the saying goes.
              - text: Apple Computer Company was founded on April 1, 1976, by Steve Jobs, Steve Wozniak, and Ronald Wayne as a partnership.
      responses:
        '200':
          description: Embeddings generated successfully.
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/VectorEmbedResponse'
              example:
                data:
                - text: Apple is a popular fruit known for its sweetness and crisp texture.
                  embedding:
                  - -0.0013012911
                  - 0.008567206
                  - 0.010289432
                  - -0.031064631
                  - -0.082377188
                  - 0.047858458
        '400':
          description: The request body included invalid parameters.
          content:
            application/problem+json:
              schema:
                $ref: '#/components/schemas/ORDSErrorResponse'
      x-internal-id: vecdb-embed-post
      x-filename-id: vecdb-embed-post
  /vecdb/rerank:
    post:
      tags:
      - Vector Database/Inference Operations
      operationId: rerank
      summary: Rerank documents by query relevance
      description: Score and order documents by relevance to a query using an ONNX reranker hosted in the database.
      security:
      - BasicAuth: []
      - BearerAuth: []
      - OAuth2: []
      requestBody:
        required: true
        content:
          application/json:
            schema:
              $ref: '#/components/schemas/VectorRerankRequest'
            example:
              query: What is the capital of the United States?
              documents:
              - Carson City is the capital city of the American state of Nevada.
              - The Commonwealth of the Northern Mariana Islands is a group of islands in the Pacific Ocean. Its capital is Saipan.
              - Washington, D.C. (also known as simply Washington or D.C., and officially as the District of Columbia) is the capital of the United States. It is a federal district.
              - Capitalization or capitalisation in English grammar is the use of a capital letter at the start of a word. English usage varies from capitalization in other languages.
              - Capital punishment (the death penalty) has existed in the United States since beforethe United States was a country. As of 2017, capital punishment is legal in 30 of the 50 states.
              modelName: reranker
              modelParams:
                provider: database
      responses:
        '200':
          description: Rerank scores for each input document in descending relevance.
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/VectorRerankResponse'
              example:
              - index: 2
                score: 8.034194946289062
              - index: 0
                score: 4.549003601074219
              - index: 1
                score: 1.1962472200393677
              - index: 3
                score: -5.338606834411621
              - index: 4
                score: -6.584031105041504
        '400':
          description: The request body included invalid parameters.
          content:
            application/problem+json:
              schema:
                $ref: '#/components/schemas/ORDSErrorResponse'
      x-internal-id: vecdb-rerank-post
      x-filename-id: vecdb-rerank-post
components:
  schemas:
    VectorRerankResponse:
      type: array
      description: List of rerank results sorted by descending relevance.
      items:
        $ref: '#/components/schemas/VectorRerankItem'
    ORDSErrorResponse:
      type: object
      required:
      - code
      - message
      - type
      - instance
      properties:
        code:
          type: string
        message:
          type: string
        type:
          type: string
        instance:
          type: string
        diagnosticTrace:
          type: string
        stackTrace:
          type: string
    VectorRerankItem:
      type: object
      required:
      - index
      - score
      properties:
        index:
          type: integer
          format: int32
          description: Zero-based index of the input document in the request payload.
        score:
          type: number
          format: double
          description: Relevance score for the document (higher is more relevant).
    VectorEmbedItem:
      type: object
      required:
      - text
      - embedding
      properties:
        text:
          type: string
          description: Echo of the input text.
        embedding:
          type: array
          description: Embedding vector for the input text.
          items:
            type: number
            format: double
    VectorEmbedInputItem:
      type: object
      required:
      - text
      properties:
        text:
          type: string
          description: Input text to embed.
    VectorEmbedResponse:
      type: object
      required:
      - data
      properties:
        data:
          type: array
          description: List of generated embeddings.
          items:
            $ref: '#/components/schemas/VectorEmbedItem'
    VectorEmbedRequest:
      type: object
      required:
      - modelName
      - inputs
      properties:
        modelName:
          type: string
          description: The name of the text embedding model hosted in the database.
        inputs:
          type: array
          description: Array of input items to embed.
          minItems: 1
          items:
            $ref: '#/components/schemas/VectorEmbedInputItem'
        debugFlags:
          $ref: '#/components/schemas/VectorDebugFlags'
    VectorRerankRequest:
      type: object
      required:
      - query
      - documents
      - modelName
      properties:
        query:
          type: string
          description: Natural language query to use for reranking.
        documents:
          type: array
          description: Array of raw document strings to score.
          minItems: 1
          items:
            type: string
        modelName:
          type: string
          description: The name of the ONNX reranking model hosted in the database.
        modelParams:
          type: object
          description: Model-specific parameters.
          additionalProperties: true
          properties:
            provider:
              type: string
              description: Optional model provider (e.g., 'database').
        debugFlags:
          $ref: '#/components/schemas/VectorDebugFlags'
    VectorDebugFlags:
      type: object
      description: Debug flags to be used to trace vector modules
      properties:
        VECTOR_INDEX:
          type: string
          enum:
          - low
          - medium
          - high
        VECTOR_INDEX_NEIGHBOR_GRAPH:
          type: string
          enum:
          - low
          - medium
          - high
        VECTOR_INDEX_NEIGHBOR_GRAPH_BUILD:
          type: string
          enum:
          - low
          - medium
          - high
        VECTOR_INDEX_NEIGHBOR_GRAPH_MEM:
          type: string
          enum:
          - low
          - medium
          - high
        VECTOR_INDEX_NEIGHBOR_GRAPH_SEARCH:
          type: string
          enum:
          - low
          - medium
          - high
        VECTOR_INDEX_NEIGHBOR_GRAPH_APPCHNG:
          type: string
          enum:
          - low
          - medium
          - high
        VECTOR_INDEX_NEIGHBOR_GRAPH_STATS:
          type: string
          enum:
          - low
          - medium
          - high
        VECTOR_INDEX_NEIGHBOR_PARTITIONS:
          type: string
          enum:
          - low
          - medium
          - high
        VECTOR_INDEX_FIXED_VIEW:
          type: string
          enum:
          - low
          - medium
          - high
        VECIDX_TRANS:
          type: string
          enum:
          - low
          - medium
          - high
        VECIDX_TRANS_COM:
          type: string
          enum:
          - low
          - medium
          - high
        VECIDX_TRANS_PJ:
          type: string
          enum:
          - low
          - medium
          - high
        VECIDX_TRANS_PJ_DWNGRD:
          type: string
          enum:
          - low
          - medium
          - high
        VECIDX_TRANS_PJ_GROW:
          type: string
          enum:
          - low
          - medium
          - high
        VECIDX_TRANS_SJ:
          type: string
          enum:
          - low
          - medium
          - high
        VECIDX_TRANS_SJ_BG:
          type: string
          enum:
          - low
          - medium
          - high
        VEC_INDEX_CALIBRATION:
          type: string
          enum:
          - low
          - medium
          - high
        VECTOR_TRACE:
          type: string
          enum:
          - low
          - medium
          - high
  securitySchemes:
    BasicAuth:
      type: http
      scheme: basic
    BearerAuth:
      type: http
      scheme: bearer
    OAuth2:
      type: oauth2
      flows:
        implicit:
          authorizationUrl: /oauth/auth
          scopes: {}
        authorizationCode:
          authorizationUrl: /oauth/auth
          tokenUrl: /oauth/token
          scopes: {}
        clientCredentials:
          tokenUrl: /oauth/token
          scopes: {}
externalDocs:
  description: Oracle REST Data Services product documentation.
  url: https://docs.oracle.com/en/database/oracle/oracle-rest-data-services/