NVIDIA NIM · OpenAPI Overlay 1.0.0

API Evangelist conversational phrasing for NVIDIA NIM Biology (BioNeMo) ASR Reranking API

2 actions 2 updates phrasing extends openapi/nvidia-nim-reranking-api-openapi.yml

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

View Overlay File View on GitHub Overlay Specification

What the actions change

x-apievangelist-phrasing

Targets 2

$.info

$.paths['/v1/ranking'].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 NVIDIA NIM Biology (BioNeMo) ASR Reranking API
  version: 1.0.0
extends: openapi/nvidia-nim-reranking-api-openapi.yml
actions:
- target: $.info
  update:
    x-apievangelist-phrasing:
      method: generated
      generated: '2026-10-01'
      generator: build-phrasing.py
      label: Generated by API Evangelist
      operations: 1
- target: $.paths['/v1/ranking'].post
  update:
    x-apievangelist-phrasing:
      intent: Rerank passages by relevance to a query
      effect: read
      questions:
      - Can I reorder a set of retrieved passages by how relevant they are to a search query?
      - What happens when a candidate passage is too long for the reranking model?
      instructions:
      - text: Rerank the passages {passages} against the query {query} with {model}.
        slots:
          passages: requestBody.passages
          query: requestBody.query
          model: requestBody.model
      - text: 'Score {passages} for relevance to {query} using {model}, truncating long passages: {truncate}.'
        slots:
          passages: requestBody.passages
          query: requestBody.query
          model: requestBody.model
          truncate: requestBody.truncate
      method: generated
      generated: '2026-10-01'