Vectara Query API

Semantic, keyword, and hybrid queries with optional grounded generation.

Documentation

Specifications

Schemas & Data

Other Resources

Work with this as data

Every API here is available over the APIs.io API and to AI agents over MCP.

MCP server

One button, every client — Claude, Cursor, VS Code and the rest.

https://apis.io/mcp

Tools for apis

7 MCP tools reach this
  • find_apisBrowse and filter every API in the catalog.
  • get_api_artifactsOne API's artifacts, grouped by type.
  • get_openapiThe primary OpenAPI for this API.
  • find_similar_apisAPIs that look like this one.
  • apis_io_searchSTART HERE — APIs, providers and tags for one query, each with its total.
  • resolveTurn a domain, URL or GitHub org into the provider it belongs to.
  • find_cohortsEvery scored population of providers in the catalog.
All 92 tools

Call it yourself

curl for this page
This API
curl "https://apis.io/api/v1/apis/vectara-query-api"
All apis
curl "https://apis.io/api/v1/apis?limit=25"

Discovery needs no key. Ratings and market analysis are Pro.

Get an API key

Free tier, no email required.

A second provider on the same verified email joins the account you already have.

OpenAPI Specification

vectara-query-api-openapi.yml Raw ↑
openapi: 3.1.0
info:
  title: Vectara REST Agents Query API
  description: 'Vectara REST API v2 is the unified interface for the Vectara Retrieval Augmented

    Generation (RAG) platform. It exposes endpoints for managing corpora, uploading

    and indexing documents, running semantic and hybrid queries with grounded

    generation, managing agents, tools, pipelines, generation presets, and reading

    metadata.


    This OpenAPI 3.1 description is hand-curated from the public Vectara REST API

    documentation at https://docs.vectara.com/docs/rest-api/ and the published

    OpenAPI document at https://docs.vectara.com/vectara-oas-v2.yaml. It covers a

    representative subset of endpoints across corpora, documents, query, agents,

    tools, pipelines, and OAuth.

    '
  version: '2.0'
  contact:
    name: Vectara Support
    url: https://docs.vectara.com/docs/support
  license:
    name: Proprietary
servers:
- url: https://api.vectara.io
  description: Vectara REST API production base URL
- url: https://auth.vectara.io
  description: Vectara OAuth 2.0 token endpoint
security:
- ApiKeyAuth: []
- OAuth2: []
tags:
- name: Query
  description: Semantic, keyword, and hybrid queries with optional grounded generation.
paths:
  /v2/corpora/{corpus_key}/query:
    parameters:
    - $ref: '#/components/parameters/CorpusKey'
    post:
      tags:
      - Query
      summary: Query A Single Corpus
      operationId: queryCorpus
      requestBody:
        required: true
        content:
          application/json:
            schema:
              $ref: '#/components/schemas/QueryRequest'
      responses:
        '200':
          description: Query results with optional grounded generation.
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/QueryResponse'
  /v2/corpora/{corpus_key}/search:
    parameters:
    - $ref: '#/components/parameters/CorpusKey'
    post:
      tags:
      - Query
      summary: Search A Single Corpus
      operationId: searchCorpus
      requestBody:
        required: true
        content:
          application/json:
            schema:
              $ref: '#/components/schemas/QueryRequest'
      responses:
        '200':
          description: Search results.
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/QueryResponse'
  /v2/corpora/{corpus_key}/queries:
    parameters:
    - $ref: '#/components/parameters/CorpusKey'
    post:
      tags:
      - Query
      summary: Run A Multi-Stage Query
      operationId: queriesCorpus
      requestBody:
        required: true
        content:
          application/json:
            schema:
              $ref: '#/components/schemas/QueryRequest'
      responses:
        '200':
          description: Query results.
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/QueryResponse'
components:
  schemas:
    QueryResponse:
      type: object
      properties:
        summary:
          type: string
        factual_consistency_score:
          type: number
        search_results:
          type: array
          items:
            type: object
            properties:
              text:
                type: string
              score:
                type: number
              document_id:
                type: string
              part_metadata:
                type: object
                additionalProperties: true
              document_metadata:
                type: object
                additionalProperties: true
    QueryRequest:
      type: object
      required:
      - query
      properties:
        query:
          type: string
          description: The natural-language query string.
        search:
          type: object
          properties:
            limit:
              type: integer
              default: 10
            offset:
              type: integer
              default: 0
            metadata_filter:
              type: string
            lexical_interpolation:
              type: number
            reranker:
              type: object
              properties:
                type:
                  type: string
        generation:
          type: object
          properties:
            generation_preset_name:
              type: string
            max_used_search_results:
              type: integer
            response_language:
              type: string
            enable_factual_consistency_score:
              type: boolean
        stream_response:
          type: boolean
  parameters:
    CorpusKey:
      in: path
      name: corpus_key
      required: true
      schema:
        type: string
      description: The unique key identifying a corpus.
  securitySchemes:
    ApiKeyAuth:
      type: apiKey
      in: header
      name: x-api-key
      description: Vectara API key passed in the `x-api-key` header.
    OAuth2:
      type: oauth2
      description: OAuth 2.0 client credentials flow.
      flows:
        clientCredentials:
          tokenUrl: https://auth.vectara.io/oauth2/token
          scopes: {}