Amazon Kendra · Arazzo Workflow

Amazon Kendra Query Suggestions then Search

Version 1.0.0

Generate type-ahead query suggestions for a partial query, then run a full search using the top suggestion.

1 workflow 2 source APIs 1 provider
View Spec View on GitHub Artificial IntelligenceEnterprise SearchKnowledge-ManagementMachine-LearningNatural-LanguageArazzoWorkflows

Provider

amazon-kendra

Workflows

query-suggestions-then-search
Fetch query suggestions for a partial query, then search with the top suggestion.
Calls GetQuerySuggestions for a partial query and runs a full Query using the top suggested phrase.
2 steps inputs: indexId, maxSuggestionsCount, partialQueryText outputs: queryId, resultItems, suggestions
1
getSuggestions
Fetch the query suggestions Kendra would offer for the partial query text based on prior query history.
2
searchTopSuggestion
Run a full search query using the top suggested phrase so the results reflect the completed query the user most likely intended.

Source API Descriptions

Arazzo Workflow Specification

Raw ↑
arazzo: 1.0.1
info:
  title: Amazon Kendra Query Suggestions then Search
  summary: Generate type-ahead query suggestions for a partial query, then run a full search using the top suggestion.
  description: >-
    Powers an autocomplete-then-search experience by calling GetQuerySuggestions
    with a partial query to fetch the suggestions Kendra would offer a user, then
    running a full Query using the top suggested phrase so the search reflects the
    completed query the user most likely intended. Each step inlines its request,
    including the AWS JSON protocol X-Amz-Target header, so the flow can be read
    and executed without opening the underlying OpenAPI description.
  version: 1.0.0
sourceDescriptions:
- name: queriesApi
  url: ../openapi/amazon-kendra-queries-api-openapi.yml
  type: openapi
- name: querySuggestionsApi
  url: ../openapi/amazon-kendra-query-suggestions-api-openapi.yml
  type: openapi
workflows:
- workflowId: query-suggestions-then-search
  summary: Fetch query suggestions for a partial query, then search with the top suggestion.
  description: >-
    Calls GetQuerySuggestions for a partial query and runs a full Query using the
    top suggested phrase.
  inputs:
    type: object
    required:
    - indexId
    - partialQueryText
    properties:
      indexId:
        type: string
        description: The identifier of the index to suggest and search against.
      partialQueryText:
        type: string
        description: The partial query text typed so far to generate suggestions for.
      maxSuggestionsCount:
        type: integer
        description: The maximum number of suggestions to return.
  steps:
  - stepId: getSuggestions
    description: >-
      Fetch the query suggestions Kendra would offer for the partial query text
      based on prior query history.
    operationId: GetQuerySuggestions
    parameters:
    - name: IndexId
      in: path
      value: $inputs.indexId
    - name: X-Amz-Target
      in: header
      value: AWSKendraFrontendService.GetQuerySuggestions
    requestBody:
      contentType: application/json
      payload:
        QueryText: $inputs.partialQueryText
        MaxSuggestionsCount: $inputs.maxSuggestionsCount
    successCriteria:
    - condition: $statusCode == 200
    outputs:
      suggestions: $response.body#/Suggestions
      topSuggestion: $response.body#/Suggestions/0/Value/Text/Text
  - stepId: searchTopSuggestion
    description: >-
      Run a full search query using the top suggested phrase so the results
      reflect the completed query the user most likely intended.
    operationId: Query
    parameters:
    - name: IndexId
      in: path
      value: $inputs.indexId
    - name: X-Amz-Target
      in: header
      value: AWSKendraFrontendService.Query
    requestBody:
      contentType: application/json
      payload:
        QueryText: $steps.getSuggestions.outputs.topSuggestion
    successCriteria:
    - condition: $statusCode == 200
    outputs:
      queryId: $response.body#/QueryId
      resultItems: $response.body#/ResultItems
      totalResults: $response.body#/TotalNumberOfResults
  outputs:
    suggestions: $steps.getSuggestions.outputs.suggestions
    queryId: $steps.searchTopSuggestion.outputs.queryId
    resultItems: $steps.searchTopSuggestion.outputs.resultItems

Work with this as data

Every workflow 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 arazzo workflows

4 MCP tools reach this
  • find_arazzoBrowse and filter every workflow in the catalog.
  • 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 workflow
curl "https://apis.io/api/v1/arazzo/amazon-kendra-query-suggestions-then-search-workflow"
All arazzo workflows
curl "https://apis.io/api/v1/arazzo?limit=25"

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

Get an API key

Free tier, no form to fill in. Signing in shares your email address with us — we store it to create your key and to recognise you if you sign in with another provider. See our Privacy Policy and Terms.

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