List generation presets

GET 
/v2/generation_presets

List generation presets used for query or chat requests. Generation presets are the build of properties used to configure generation for a request. This includes the template that renders the prompt, and various generation settings like temperature.

Request

Query Parameters

llm_name string

Filter presets by the LLM name.

limit int32

Possible values: >= 1 and <= 100

Default value: 10

The maximum number of results to return in the list.

page_key string

Used to retrieve the next page of generation presets after the limit has been reached. This parameter is not needed for the first page of results.

Header Parameters

Request-Timeout integer

Possible values: >= 1

The API will make a best effort to complete the request in the specified seconds or time out.

Request-Timeout-Millis integer

Possible values: >= 1

The API will make a best effort to complete the request in the specified milliseconds or time out.

Responses

200

List of Generation Presets.

application/json

Schema

Schema

generation_presets object[]
List of generation presets.
Array [
name string
Name of the generation preset to be used with configuring generation.
description string
Description of the generation preset.
llm_name string
Name of the model that these presets are used with.
prompt_template string
Preset template used to render the prompt sent to generation.
max_used_search_results int32
Possible values: >= 1
Preset maximum number of search results that will be available to the prompt.
max_tokens int32
Possible values: >= 1
Preset maximum number of tokens to be returned by the generation.
temperature float
The sampling temperature to use. Higher values make the output more random, while lower values make it more focused and deterministic.
frequency_penalty float
Higher values penalize new tokens based on their existing frequency in the generation so far, decreasing the model's likelihood to repeat the same line verbatim.
presence_penalty float
Higher values penalize new tokens based on whether they appear in the generation so far, increasing the model's likelihood to talk about new topics.
enabled boolean
Indicates whether the prompt is enabled.
default boolean
Indicates if this prompt is the default prompt used with the LLM.
]
metadata object

The standard metadata in the response of a list operation.

page_key string

When requesting the next page of this list, this is needed as a query parameter.

Example (from schema)

{
  "generation_presets": [
    {
      "name": "string",
      "description": "string",
      "llm_name": "string",
      "prompt_template": "string",
      "max_used_search_results": 0,
      "max_tokens": 0,
      "temperature": 0,
      "frequency_penalty": 0,
      "presence_penalty": 0,
      "enabled": true,
      "default": true
    }
  ],
  "metadata": {
    "page_key": "string"
  }
}

403

Permissions do not allow listing generation presets.

application/json

Schema

Schema

messages message[]

The messages describing why the error occurred.

request_id string

The ID of the request that can be used to help Vectara support debug what went wrong.

Example (from schema)

{
  "messages": [
    "Internal server error."
  ],
  "request_id": "string"
}

Loading...