NVIDIA NIM · OpenAPI Overlay 1.0.0

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

2 actions 2 updates phrasing extends openapi/nvidia-nim-embeddings-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/embeddings'].post

OpenAPI Overlay

Raw ↑ 
# 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 Embeddings API
  version: 1.0.0
extends: openapi/nvidia-nim-embeddings-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/embeddings'].post
  update:
    x-apievangelist-phrasing:
      intent: Create embedding vectors for text
      effect: write
      questions:
      - Can I turn a batch of text strings into embedding vectors for semantic search?
      - Should a query and a document be embedded with a different input type for retrieval models like NV-EmbedQA?
      - Can I shrink the size of the returned embedding vectors on Matryoshka-style models?
      instructions:
      - text: Embed the text {input} with the {model} embedding model.
        slots:
          input: requestBody.input
          model: requestBody.model
      - text: Create {input_type} embeddings for {input} using {model}.
        slots:
          input_type: requestBody.input_type
          input: requestBody.input
          model: requestBody.model
      - text: Generate {dimensions}-dimension embedding vectors for {input} with {model}.
        slots:
          dimensions: requestBody.dimensions
          input: requestBody.input
          model: requestBody.model
      method: generated
      generated: '2026-10-01'