Get all LLM configurations

GET

/api/v1/config/llms

const url = 'http://localhost:11044/api/v1/config/llms';
const options = {method: 'GET', headers: {'X-Embabel-Api-Key': '<X-Embabel-Api-Key>'}};

try {
  const response = await fetch(url, options);
  const data = await response.json();
  console.log(data);
} catch (error) {
  console.error(error);
}

curl --request GET \
  --url http://localhost:11044/api/v1/config/llms \
  --header 'X-Embabel-Api-Key: <X-Embabel-Api-Key>'

Returns model, temperature, and reasoning effort for chat, actionCompilerLlm, memoryLlm, apiExplorerLlm, codingLlm, fallbackCodingLlm, rankerLlm, plannerLlm, and lensLlm.

Authorizations

apiKeyAuth
basicAuth

Responses

200

LLM configurations

*/*

The model settings of every purpose a world configures, one entry per purpose

object

actionCompilerLlm

required

The model that compiles actions

object

model

The pinned model, or null when the purpose inherits one

string

reasoningEffort

The reasoning effort every call for this purpose runs at, or null for the model’s default

string

temperature

The sampling temperature, or null for the model’s default

number format: double

apiExplorerLlm

required

The model that explores APIs

object

model

The pinned model, or null when the purpose inherits one

string

reasoningEffort

The reasoning effort every call for this purpose runs at, or null for the model’s default

string

temperature

The sampling temperature, or null for the model’s default

number format: double

chat

required

The model a person talks to

object

model

The pinned model, or null when the purpose inherits one

string

reasoningEffort

The reasoning effort every call for this purpose runs at, or null for the model’s default

string

temperature

The sampling temperature, or null for the model’s default

number format: double

codingLlm

required

The model code is written with

object

model

The pinned model, or null when the purpose inherits one

string

reasoningEffort

The reasoning effort every call for this purpose runs at, or null for the model’s default

string

temperature

The sampling temperature, or null for the model’s default

number format: double

fallbackCodingLlm

required

The model code is written with when the coding model fails

object

model

The pinned model, or null when the purpose inherits one

string

reasoningEffort

The reasoning effort every call for this purpose runs at, or null for the model’s default

string

temperature

The sampling temperature, or null for the model’s default

number format: double

lensLlm

required

The model lenses run on

object

model

The pinned model, or null when the purpose inherits one

string

reasoningEffort

The reasoning effort every call for this purpose runs at, or null for the model’s default

string

temperature

The sampling temperature, or null for the model’s default

number format: double

memoryLlm

required

The model memory work runs on

object

model

The pinned model, or null when the purpose inherits one

string

reasoningEffort

The reasoning effort every call for this purpose runs at, or null for the model’s default

string

temperature

The sampling temperature, or null for the model’s default

number format: double

plannerLlm

required

The model that plans

object

model

The pinned model, or null when the purpose inherits one

string

reasoningEffort

The reasoning effort every call for this purpose runs at, or null for the model’s default

string

temperature

The sampling temperature, or null for the model’s default

number format: double

rankerLlm

required

The model that ranks results

object

model

The pinned model, or null when the purpose inherits one

string

reasoningEffort

The reasoning effort every call for this purpose runs at, or null for the model’s default

string

temperature

The sampling temperature, or null for the model’s default

number format: double