- Provider rules are based on the Provider entity.
- Model rules are based on the AIModelEntity entity.
All entities mentioned below are based onPydantic BaseModeland can be found in theentitiesmodule.
Provider
provider(string) Provider identifier, e.g.,openailabel(object) Provider display name, i18n, withen_USEnglish andzh_HansChinese language settingszh_Hans(string) [optional] Chinese label name, ifzh_Hansis not set,en_USwill be used by default.en_US(string) English label name
description(object) Provider description, i18nzh_Hans(string) [optional] Chinese descriptionen_US(string) English description
icon_small(string) [optional] Small provider ICON, stored in the_assetsdirectory under the corresponding provider implementation directory, with the same language strategy aslabelzh_Hans(string) Chinese ICONen_US(string) English ICON
icon_large(string) [optional] Large provider ICON, stored in the_assetsdirectory under the corresponding provider implementation directory, with the same language strategy aslabelzh_Hans(string) Chinese ICONen_US(string) English ICON
background(string) [optional] Background color value, e.g., #FFFFFF, if empty, the default frontend color value will be displayed.help(object) [optional] help informationtitle(object) help title, i18nzh_Hans(string) [optional] Chinese titleen_US(string) English title
url(object) help link, i18nzh_Hans(string) [optional] Chinese linken_US(string) English link
supported_model_types(array[ModelType]) Supported model typesconfigurate_methods(array[ConfigurateMethod]) Configuration methodsprovider_credential_schema(ProviderCredentialSchema) Provider credential specificationmodel_credential_schema(ModelCredentialSchema) Model credential specification
AIModelEntity
model(string) Model identifier, e.g.,gpt-3.5-turbolabel(object) [optional] Model display name, i18n, withen_USEnglish andzh_HansChinese language settingszh_Hans(string) [optional] Chinese label nameen_US(string) English label name
model_type(ModelType) Model typefeatures(array[ModelFeature]) [optional] Supported feature listmodel_properties(object) Model propertiesmode(LLMMode) Mode (available for model typellm)context_size(int) Context size (available for model typesllm,text-embedding)max_chunks(int) Maximum number of chunks (available for model typestext-embedding,moderation)file_upload_limit(int) Maximum file upload limit, in MB (available for model typespeech2text)supported_file_extensions(string) Supported file extension formats, e.g., mp3, mp4 (available for model typespeech2text)default_voice(string) default voice, e.g.:alloy,echo,fable,onyx,nova,shimmer(available for model typetts)voices(list) List of available voice.(available for model typetts)mode(string) voice model.(available for model typetts)name(string) voice model display name.(available for model typetts)language(string) the voice model supports languages.(available for model typetts)
word_limit(int) Single conversion word limit, paragraphwise by default(available for model typetts)audio_type(string) Support audio file extension format, e.g.:mp3,wav(available for model typetts)max_workers(int) Number of concurrent workers supporting text and audio conversion(available for model typetts)max_characters_per_chunk(int) Maximum characters per chunk (available for model typemoderation)
parameter_rules(array[ParameterRule]) [optional] Model invocation parameter rulespricing(PriceConfig) [optional] Pricing informationdeprecated(bool) Whether deprecated. If deprecated, the model will no longer be displayed in the list, but those already configured can continue to be used. Default False.
ModelType
llmText generation modeltext-embeddingText Embedding modelrerankRerank modelspeech2textSpeech to textttsText to speechmoderationModeration
ConfigurateMethod
-
predefined-modelPredefined model Indicates that users can use the predefined models under the provider by configuring the unified provider credentials. -
customizable-modelCustomizable model Users need to add credential configuration for each model. -
fetch-from-remoteFetch from remote Consistent with thepredefined-modelconfiguration method, only unified provider credentials need to be configured, and models are obtained from the provider through credential information.
ModelFeature
agent-thoughtAgent reasoning, generally over 70B with thought chain capability.visionVision, i.e., image understanding.tool-callmulti-tool-callstream-tool-call
FetchFrom
predefined-modelPredefined modelfetch-from-remoteRemote model
LLMMode
completionText completionchatDialogue
ParameterRule
-
name(string) Actual model invocation parameter name -
use_template(string) [optional] Using template By default, 5 variable content configuration templates are preset:temperaturetop_pfrequency_penaltypresence_penaltymax_tokens
nameanduse_template. If additional configuration parameters are set, they will override the default configuration. Refer toopenai/llm/gpt-3.5-turbo.yaml. -
label(object) [optional] Label, i18nzh_Hans(string) [optional] Chinese label nameen_US(string) English label name
-
type(string) [optional] Parameter typeintIntegerfloatFloatstringStringbooleanBoolean
-
help(string) [optional] Help informationzh_Hans(string) [optional] Chinese help informationen_US(string) English help information
-
required(bool) Required, default False. -
default(int/float/string/bool) [optional] Default value -
min(int/float) [optional] Minimum value, applicable only to numeric types -
max(int/float) [optional] Maximum value, applicable only to numeric types -
precision(int) [optional] Precision, number of decimal places to keep, applicable only to numeric types -
options(array[string]) [optional] Dropdown option values, applicable only whentypeisstring, if not set or null, option values are not restricted
PriceConfig
input(float) Input price, i.e., Prompt priceoutput(float) Output price, i.e., returned content priceunit(float) Pricing unit, e.g., if the price is meausred in 1M tokens, the corresponding token amount for the unit price is0.000001.currency(string) Currency unit
ProviderCredentialSchema
credential_form_schemas(array[CredentialFormSchema]) Credential form standard
ModelCredentialSchema
model(object) Model identifier, variable name defaults tomodellabel(object) Model form item display nameen_US(string) Englishzh_Hans(string) [optional] Chinese
placeholder(object) Model prompt contenten_US(string) Englishzh_Hans(string) [optional] Chinese
credential_form_schemas(array[CredentialFormSchema]) Credential form standard
CredentialFormSchema
variable(string) Form item variable namelabel(object) Form item label nameen_US(string) Englishzh_Hans(string) [optional] Chinese
type(FormType) Form item typerequired(bool) Whether requireddefault(string) Default valueoptions(array[FormOption]) Specific property of form items of typeselectorradio, defining dropdown contentplaceholder(object) Specific property of form items of typetext-input, placeholder contenten_US(string) Englishzh_Hans(string) [optional] Chinese
max_length(int) Specific property of form items of typetext-input, defining maximum input length, 0 for no limit.show_on(array[FormShowOnObject]) Displayed when other form item values meet certain conditions, displayed always if empty.
FormType
text-inputText input componentsecret-inputPassword input componentselectSingle-choice dropdownradioRadio componentswitchSwitch component, only supportstrueandfalsevalues
FormOption
label(object) Labelen_US(string) Englishzh_Hans(string) [optional] Chinese
value(string) Dropdown option valueshow_on(array[FormShowOnObject]) Displayed when other form item values meet certain conditions, displayed always if empty.
FormShowOnObject
variable(string) Variable name of other form itemsvalue(string) Variable value of other form items
Edit this page | Report an issue