Snowflake · OpenAPI Overlay 1.0.0

API Evangelist conversational phrasing for Cortex Inference API

3 actions 3 updates phrasing extends openapi/snowflake-cortex-inference-api-openapi.yml

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

View Overlay File View on GitHub Overlay Specification

What the actions change

x-apievangelist-phrasing

Targets 3

$.info

$.paths['/api/v2/cortex/models'].get

$.paths['/api/v2/cortex/inference:complete'].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 Cortex Inference API
  version: 1.0.0
extends: openapi/snowflake-cortex-inference-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: 2
- target: $.paths['/api/v2/cortex/models'].get
  update:
    x-apievangelist-phrasing:
      intent: List the LLMs available to this session
      effect: read
      questions:
      - Which large language models can I call from Cortex in my current session?
      - Can I check which model names are valid before I send a completion request?
      instructions:
      - text: List the LLMs available for my current session.
      - text: Show which Cortex models I'm allowed to use right now.
      method: generated
      generated: '2026-10-01'
- target: $.paths['/api/v2/cortex/inference:complete'].post
  update:
    x-apievangelist-phrasing:
      intent: Generate an LLM text completion
      effect: write
      questions:
      - How do I send a chat prompt to an LLM through Cortex and get a completion back?
      - Can I cap the output length and adjust temperature on a completion?
      - Does the completion endpoint support streaming responses and tool calls?
      instructions:
      - text: Ask model {model} to respond to {messages}.
        slots:
          model: requestBody.model
          messages: requestBody.messages
      - text: Complete {messages} with {model}, limited to {max_tokens} tokens at temperature {temperature}.
        slots:
          messages: requestBody.messages
          model: requestBody.model
          max_tokens: requestBody.max_tokens
          temperature: requestBody.temperature
      - text: Run a completion on {model} for {messages} using tools {tools}.
        slots:
          model: requestBody.model
          messages: requestBody.messages
          tools: requestBody.tools
      method: generated
      generated: '2026-10-01'