ExOpenAI.Edits (ex_openai.ex v1.0.4) View Source
Modules for interacting with the edits
group of OpenAI APIs
API Reference: https://platform.openai.com/docs/api-reference/edits
Link to this section Summary
Functions
Creates a new edit for the provided input, instruction, and parameters.
Link to this section Functions
Specs
create_edit(String.t(), String.t(), top_p: float(), temperature: float(), n: integer(), input: String.t() ) :: {:ok, ExOpenAI.Components.CreateEditResponse.t()} | {:error, any()}
Creates a new edit for the provided input, instruction, and parameters.
Endpoint: https://api.openai.com/v1/edits
Method: POST
Docs: https://platform.openai.com/docs/api-reference/edits
Required Arguments:
instruction
: The instruction that tells the model how to edit the prompt.
Example: Fix the spelling mistakes.
model
: ID of the model to use. You can use thetext-davinci-edit-001
orcode-davinci-edit-001
model with this endpoint.
Optional Arguments:
input
: The input text to use as a starting point for the edit.
Example: "What day of the wek is it?"
n
: How many edits to generate for the input and instruction.
Example: 1
temperature
: What sampling temperature to use, between 0 and 2. Higher values like 0.8 will make the output more random, while lower values like 0.2 will make it more focused and deterministic.
We generally recommend altering this or top_p
but not both.
Example: 1
top_p
: An alternative to sampling with temperature, called nucleus sampling, where the model considers the results of the tokens with top_p probability mass. So 0.1 means only the tokens comprising the top 10% probability mass are considered.
We generally recommend altering this or temperature
but not both.
Example: 1