Infobip · OpenAPI Overlay 1.0.0

API Evangelist conversational phrasing for Infobip OpenAPI Specification AI Hub API

3 actions 3 updates phrasing extends openapi/infobip-ai-hub-api-openapi.yml

Generated by API Evangelist Written by API Evangelist tooling for Infobip's API. It is a proposal applied on top of the contract, not a document Infobip publishes.

View Overlay File View on GitHub Overlay Specification

What the actions change

x-apievangelist-phrasing

Targets 3

$.info

$.paths['/ai/1/aiassistants/{assistantId}/query'].post

$.paths['/ai/1/aiassistants/{assistantId}/retrieve-context'].post

OpenAPI Overlay

# Generated by API Evangelist (build-phrasing.py). Our phrasing, not observed demand.
overlay: 1.0.0
info:
  title: API Evangelist conversational phrasing for Infobip OpenAPI Specification AI Hub API
  version: 1.0.0
extends: openapi/infobip-ai-hub-api-openapi.yml
actions:
- target: $.info
  update:
    x-apievangelist-phrasing:
      method: generated
      generated: '2026-09-26'
      generator: build-phrasing.py
      label: Generated by API Evangelist
      operations: 2
- target: $.paths['/ai/1/aiassistants/{assistantId}/query'].post
  update:
    x-apievangelist-phrasing:
      intent: Ask an AI assistant a question and get its answer
      effect: read
      questions:
      - How do I send a user's message to my Infobip AI assistant and get a generated reply?
      - Can the assistant keep context across several questions in the same session?
      - Is it possible to see which document contexts the assistant used to write its answer?
      instructions:
      - text: 'Ask AI assistant {assistantId}: {message}'
        slots:
          assistantId: path.assistantId
          message: requestBody.message
      - text: Send {message} to assistant {assistantId} in session {sessionId} and return its answer.
        slots:
          assistantId: path.assistantId
          message: requestBody.message
          sessionId: requestBody.sessionId
      - text: Get assistant {assistantId}'s generated reply to {message} and include the source contexts it drew on.
        slots:
          assistantId: path.assistantId
          message: requestBody.message
      method: generated
      generated: '2026-09-26'
- target: $.paths['/ai/1/aiassistants/{assistantId}/retrieve-context'].post
  update:
    x-apievangelist-phrasing:
      intent: Retrieve relevant knowledge base chunks for a message
      effect: read
      questions:
      - How can I fetch the raw knowledge base passages an assistant would match to a message, without a generated answer?
      - Can I choose how many context chunks come back from the semantic search?
      - Does chunk retrieval support re-ranking for more precise results?
      instructions:
      - text: Retrieve the most relevant knowledge base chunks from assistant {assistantId} for {message}.
        slots:
          assistantId: path.assistantId
          message: requestBody.message
      - text: Return the top {k} context chunks from assistant {assistantId} matching {message}.
        slots:
          k: requestBody.k
          assistantId: path.assistantId
          message: requestBody.message
      - text: Pull re-ranked context chunks for {message} from assistant {assistantId}, re-ranking over {reRankK} candidates.
        slots:
          message: requestBody.message
          assistantId: path.assistantId
          reRankK: requestBody.reRankK
      method: generated
      generated: '2026-09-26'