Skip to content

Instantly share code, notes, and snippets.

@chrisobriensp
Last active February 26, 2023 12:37
Show Gist options
  • Save chrisobriensp/47a5a19fc02d831f3afb5561ac1155da to your computer and use it in GitHub Desktop.
Save chrisobriensp/47a5a19fc02d831f3afb5561ac1155da to your computer and use it in GitHub Desktop.
Azure OpenAI - Power Platform custom connector
swagger: '2.0'
info:
title: Default title
description: Azure OpenAI - Completions API
version: '1.0'
host: [YOUR ENDPOINT PREFIX HERE].openai.azure.com
basePath: /openai
schemes:
- https
consumes: []
produces: []
paths:
/deployments/{deployment-id}/completions:
post:
responses:
default:
description: default
schema:
type: object
properties:
id:
type: string
description: id
object:
type: string
description: object
created:
type: integer
format: int32
description: created
model:
type: string
description: model
choices:
type: array
items:
type: object
properties:
text:
type: string
description: text
index:
type: integer
format: int32
description: index
logprobs:
type: string
description: logprobs
finish_reason:
type: string
description: finish_reason
description: choices
usage:
type: object
properties:
prompt_tokens:
type: integer
format: int32
description: prompt_tokens
completion_tokens:
type: integer
format: int32
description: completion_tokens
total_tokens:
type: integer
format: int32
description: total_tokens
description: usage
parameters:
- name: deployment-id
in: path
required: true
type: string
default: [YOUR DEPLOYMENT ID HERE]
x-ms-visibility: important
- name: api-version
in: query
required: true
type: string
default: '2022-12-01'
x-ms-visibility: important
- name: Content-Type
in: header
required: true
default: application/json
type: string
- name: body
in: body
required: false
schema:
type: object
properties:
prompt:
type: string
description: >-
The prompt(s) to generate completions for, encoded as a string
or array of strings.\nNote that <|endoftext|> is the document
separator that the model sees during training, so if a prompt
is not specified the model will generate as if from the
beginning of a new document. Maximum allowed size of string
list is 2048.
max_tokens:
type: integer
description: >-
The token count of your prompt plus max_tokens cannot exceed
the model's context length. Most models have a context length
of 2048 tokens (except for the newest models, which support
4096). Has minimum of 0.
temperature:
type: number
description: >-
What sampling temperature to use. Higher values means the
model will take more risks. Try 0.9 for more creative
applications, and 0 (argmax sampling) for ones with a
well-defined answer.\nWe generally recommend altering this or
top_p but not both.
operationId: Completions
summary: Completions
description: Completions API
x-ms-visibility: important
definitions: {}
parameters: {}
responses: {}
securityDefinitions:
API Key:
type: apiKey
in: header
name: api-key
security:
- API Key: []
tags: []
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment