Class: TextGenerationToolCallModel<SOURCE_PROMPT, TARGET_PROMPT, MODEL>

Type parameters

Name	Type
SOURCE_PROMPT	SOURCE_PROMPT
TARGET_PROMPT	TARGET_PROMPT
MODEL	extends TextGenerationModel<TARGET_PROMPT, TextGenerationModelSettings>

Implements

• ToolCallGenerationModel<SOURCE_PROMPT, MODEL["settings"]>

Accessors

modelInformation

• get modelInformation(): ModelInformation

Returns

ModelInformation

Implementation of

ToolCallGenerationModel.modelInformation

Defined in

packages/modelfusion/src/tool/generate-tool-call/TextGenerationToolCallModel.ts:37

---

settings

• get settings(): TextGenerationModelSettings

Returns

TextGenerationModelSettings

Implementation of

ToolCallGenerationModel.settings

Defined in

packages/modelfusion/src/tool/generate-tool-call/TextGenerationToolCallModel.ts:41

---

settingsForEvent

• get settingsForEvent(): Partial<MODEL["settings"]>

Returns settings that should be recorded in observability events. Security-related settings (e.g. API keys) should not be included here.

Returns

Partial<MODEL["settings"]>

Implementation of

ToolCallGenerationModel.settingsForEvent

Defined in

packages/modelfusion/src/tool/generate-tool-call/TextGenerationToolCallModel.ts:45

Constructors

constructor

• new TextGenerationToolCallModel<SOURCE_PROMPT, TARGET_PROMPT, MODEL>(«destructured»): TextGenerationToolCallModel<SOURCE_PROMPT, TARGET_PROMPT, MODEL>

Type parameters

Name	Type
SOURCE_PROMPT	SOURCE_PROMPT
TARGET_PROMPT	TARGET_PROMPT
MODEL	extends TextGenerationModel<TARGET_PROMPT, TextGenerationModelSettings>

Parameters

Name	Type
«destructured»	Object
› model	MODEL
› template	ToolCallPromptTemplate<SOURCE_PROMPT, TARGET_PROMPT>

Returns

TextGenerationToolCallModel<SOURCE_PROMPT, TARGET_PROMPT, MODEL>

Defined in

packages/modelfusion/src/tool/generate-tool-call/TextGenerationToolCallModel.ts:26

Methods

doGenerateToolCall

▸ doGenerateToolCall(tool, prompt, options?): Promise<{ rawResponse: unknown ; toolCall: null | { args: unknown ; id: string } ; usage: undefined | { completionTokens: number ; promptTokens: number ; totalTokens: number } }>

Parameters

Name	Type
tool	ToolDefinition<string, unknown>
prompt	SOURCE_PROMPT
options?	FunctionOptions

Returns

Promise<{ rawResponse: unknown ; toolCall: null | { args: unknown ; id: string } ; usage: undefined | { completionTokens: number ; promptTokens: number ; totalTokens: number } }>

Implementation of

ToolCallGenerationModel.doGenerateToolCall

Defined in

packages/modelfusion/src/tool/generate-tool-call/TextGenerationToolCallModel.ts:60

---

getModelWithJsonOutput

▸ getModelWithJsonOutput(schema): MODEL

Parameters

Name	Type
schema	Schema<unknown> & JsonSchemaProducer

Returns

MODEL

Defined in

packages/modelfusion/src/tool/generate-tool-call/TextGenerationToolCallModel.ts:49

---

withSettings

▸ withSettings(additionalSettings): this

The withSettings method creates a new model with the same configuration as the original model, but with the specified settings changed.

Parameters

Name	Type
additionalSettings	Partial<MODEL["settings"]>

Returns

this

Example

const model = new OpenAICompletionModel({
  model: "gpt-3.5-turbo-instruct",
  maxGenerationTokens: 500,
});

const modelWithMoreTokens = model.withSettings({
  maxGenerationTokens: 1000,
});

Implementation of

ToolCallGenerationModel.withSettings

Defined in

packages/modelfusion/src/tool/generate-tool-call/TextGenerationToolCallModel.ts:93