Class: CohereTextGenerationModel

Create a text generation model that calls the Cohere Co.Generate API.

See

https://docs.cohere.com/reference/generate

Example

const model = new CohereTextGenerationModel({
  model: "command",
  temperature: 0.7,
  maxGenerationTokens: 500,
});

const text = await generateText(
   model,
  "Write a short story about a robot learning to love:\n\n"
);

Hierarchy

• AbstractModel<CohereTextGenerationModelSettings>

  ↳ CohereTextGenerationModel

Implements

• TextStreamingBaseModel<string, CohereTextGenerationModelSettings>

Accessors

modelInformation

• get modelInformation(): ModelInformation

Returns

ModelInformation

Implementation of

TextStreamingBaseModel.modelInformation

Inherited from

AbstractModel.modelInformation

Defined in

packages/modelfusion/src/model-function/AbstractModel.ts:17

---

modelName

• get modelName(): "command" | "command-light"

Returns

"command" | "command-light"

Overrides

AbstractModel.modelName

Defined in

packages/modelfusion/src/model-provider/cohere/CohereTextGenerationModel.ts:96

---

settingsForEvent

• get settingsForEvent(): Partial<CohereTextGenerationModelSettings>

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

Returns

Partial<CohereTextGenerationModelSettings>

Implementation of

TextStreamingBaseModel.settingsForEvent

Overrides

AbstractModel.settingsForEvent

Defined in

packages/modelfusion/src/model-provider/cohere/CohereTextGenerationModel.ts:154

Constructors

constructor

• new CohereTextGenerationModel(settings): CohereTextGenerationModel

Parameters

Name	Type
settings	CohereTextGenerationModelSettings

Returns

CohereTextGenerationModel

Overrides

AbstractModel&lt;CohereTextGenerationModelSettings&gt;.constructor

Defined in

packages/modelfusion/src/model-provider/cohere/CohereTextGenerationModel.ts:83

Methods

callAPI

▸ callAPI<RESPONSE>(prompt, callOptions, options): Promise<RESPONSE>

Type parameters

Name
RESPONSE

Parameters

Name	Type
prompt	string
callOptions	FunctionCallOptions
options	Object
options.responseFormat	CohereTextGenerationResponseFormatType<RESPONSE>

Returns

Promise<RESPONSE>

Defined in

packages/modelfusion/src/model-provider/cohere/CohereTextGenerationModel.ts:107

---

countPromptTokens

▸ countPromptTokens(input): Promise<number>

Parameters

Name	Type
input	string

Returns

Promise<number>

Implementation of

TextStreamingBaseModel.countPromptTokens

Defined in

packages/modelfusion/src/model-provider/cohere/CohereTextGenerationModel.ts:103

---

doGenerateTexts

▸ doGenerateTexts(prompt, options): Promise<{ rawResponse: { generations: { finish_reason?: string ; id: string ; text: string }[] ; id: string ; meta?: { api_version: { version: string } } ; prompt: string } ; textGenerationResults: { finishReason: TextGenerationFinishReason ; text: string = generation.text }[] }>

Parameters

Name	Type
prompt	string
options	FunctionCallOptions

Returns

Promise<{ rawResponse: { generations: { finish_reason?: string ; id: string ; text: string }[] ; id: string ; meta?: { api_version: { version: string } } ; prompt: string } ; textGenerationResults: { finishReason: TextGenerationFinishReason ; text: string = generation.text }[] }>

Implementation of

TextStreamingBaseModel.doGenerateTexts

Defined in

packages/modelfusion/src/model-provider/cohere/CohereTextGenerationModel.ts:176

---

doStreamText

▸ doStreamText(prompt, options): Promise<AsyncIterable<Delta<{ is_finished: false ; text: string } | { finish_reason: string ; is_finished: true ; response: { generations: { finish_reason?: string ; id: string ; text: string }[] ; id: string ; meta?: { api_version: { version: string } } ; prompt: string } = cohereTextGenerationResponseSchema }>>>

Parameters

Name	Type
prompt	string
options	FunctionCallOptions

Returns

Promise<AsyncIterable<Delta<{ is_finished: false ; text: string } | { finish_reason: string ; is_finished: true ; response: { generations: { finish_reason?: string ; id: string ; text: string }[] ; id: string ; meta?: { api_version: { version: string } } ; prompt: string } = cohereTextGenerationResponseSchema }>>>

Implementation of

TextStreamingBaseModel.doStreamText

Defined in

packages/modelfusion/src/model-provider/cohere/CohereTextGenerationModel.ts:220

---

extractTextDelta

▸ extractTextDelta(delta): string

Parameters

Name	Type
delta	unknown

Returns

string

Implementation of

TextStreamingBaseModel.extractTextDelta

Defined in

packages/modelfusion/src/model-provider/cohere/CohereTextGenerationModel.ts:226

---

processTextGenerationResponse

▸ processTextGenerationResponse(rawResponse): Object

Parameters

Name	Type
rawResponse	Object
rawResponse.generations	{ finish_reason?: string ; id: string ; text: string }[]
rawResponse.id	string
rawResponse.meta?	Object
rawResponse.meta.api_version	Object
rawResponse.meta.api_version.version	string
rawResponse.prompt	string

Returns

Object

Name	Type
rawResponse	{ generations: { finish_reason?: string ; id: string ; text: string }[] ; id: string ; meta?: { api_version: { version: string } } ; prompt: string }
rawResponse.generations	{ finish_reason?: string ; id: string ; text: string }[]
rawResponse.id	string
rawResponse.meta?	{ api_version: { version: string } }
rawResponse.meta.api_version	{ version: string }
rawResponse.meta.api_version.version	string
rawResponse.prompt	string
textGenerationResults	{ finishReason: TextGenerationFinishReason ; text: string = generation.text }[]

Defined in

packages/modelfusion/src/model-provider/cohere/CohereTextGenerationModel.ts:193

---

restoreGeneratedTexts

▸ restoreGeneratedTexts(rawResponse): Object

Parameters

Name	Type
rawResponse	unknown

Returns

Object

Name	Type
rawResponse	{ generations: { finish_reason?: string ; id: string ; text: string }[] ; id: string ; meta?: { api_version: { version: string } } ; prompt: string }
rawResponse.generations	{ finish_reason?: string ; id: string ; text: string }[]
rawResponse.id	string
rawResponse.meta?	{ api_version: { version: string } }
rawResponse.meta.api_version	{ version: string }
rawResponse.meta.api_version.version	string
rawResponse.prompt	string
textGenerationResults	{ finishReason: TextGenerationFinishReason ; text: string = generation.text }[]

Implementation of

TextStreamingBaseModel.restoreGeneratedTexts

Defined in

packages/modelfusion/src/model-provider/cohere/CohereTextGenerationModel.ts:184

---

withChatPrompt

▸ withChatPrompt(options?): PromptTemplateTextStreamingModel<ChatPrompt, string, CohereTextGenerationModelSettings, CohereTextGenerationModel>

Returns this model with a chat prompt template.

Parameters

Name	Type
options?	Object
options.assistant?	string
options.user?	string

Returns

PromptTemplateTextStreamingModel<ChatPrompt, string, CohereTextGenerationModelSettings, CohereTextGenerationModel>

Implementation of

TextStreamingBaseModel.withChatPrompt

Defined in

packages/modelfusion/src/model-provider/cohere/CohereTextGenerationModel.ts:243

---

withInstructionPrompt

▸ withInstructionPrompt(): PromptTemplateTextStreamingModel<InstructionPrompt, string, CohereTextGenerationModelSettings, CohereTextGenerationModel>

Returns this model with an instruction prompt template.

Returns

PromptTemplateTextStreamingModel<InstructionPrompt, string, CohereTextGenerationModelSettings, CohereTextGenerationModel>

Implementation of

TextStreamingBaseModel.withInstructionPrompt

Defined in

packages/modelfusion/src/model-provider/cohere/CohereTextGenerationModel.ts:239

---

withJsonOutput

▸ withJsonOutput(): this

When possible, limit the output generation to the specified JSON schema, or super sets of it (e.g. JSON in general).

Returns

this

Implementation of

TextStreamingBaseModel.withJsonOutput

Defined in

packages/modelfusion/src/model-provider/cohere/CohereTextGenerationModel.ts:231

---

withPromptTemplate

▸ withPromptTemplate<INPUT_PROMPT>(promptTemplate): PromptTemplateTextStreamingModel<INPUT_PROMPT, string, CohereTextGenerationModelSettings, CohereTextGenerationModel>

Type parameters

Name
INPUT_PROMPT

Parameters

Name	Type
promptTemplate	TextGenerationPromptTemplate<INPUT_PROMPT, string>

Returns

PromptTemplateTextStreamingModel<INPUT_PROMPT, string, CohereTextGenerationModelSettings, CohereTextGenerationModel>

Implementation of

TextStreamingBaseModel.withPromptTemplate

Defined in

packages/modelfusion/src/model-provider/cohere/CohereTextGenerationModel.ts:247

---

withSettings

▸ withSettings(additionalSettings): CohereTextGenerationModel

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<CohereTextGenerationModelSettings>

Returns

CohereTextGenerationModel

Example

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

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

Implementation of

TextStreamingBaseModel.withSettings

Overrides

AbstractModel.withSettings

Defined in

packages/modelfusion/src/model-provider/cohere/CohereTextGenerationModel.ts:266

---

withTextPrompt

▸ withTextPrompt(): PromptTemplateTextStreamingModel<string, string, CohereTextGenerationModelSettings, CohereTextGenerationModel>

Returns this model with a text prompt template.

Returns

PromptTemplateTextStreamingModel<string, string, CohereTextGenerationModelSettings, CohereTextGenerationModel>

Implementation of

TextStreamingBaseModel.withTextPrompt

Defined in

packages/modelfusion/src/model-provider/cohere/CohereTextGenerationModel.ts:235

Properties

contextWindowSize

• Readonly contextWindowSize: number

Implementation of

TextStreamingBaseModel.contextWindowSize

Defined in

packages/modelfusion/src/model-provider/cohere/CohereTextGenerationModel.ts:100

---

provider

• Readonly provider: "cohere"

Overrides

AbstractModel.provider

Defined in

packages/modelfusion/src/model-provider/cohere/CohereTextGenerationModel.ts:95

---

settings

• Readonly settings: CohereTextGenerationModelSettings

Implementation of

TextStreamingBaseModel.settings

Inherited from

AbstractModel.settings

Defined in

packages/modelfusion/src/model-function/AbstractModel.ts:7

---

tokenizer

• Readonly tokenizer: CohereTokenizer

Implementation of

TextStreamingBaseModel.tokenizer

Defined in

packages/modelfusion/src/model-provider/cohere/CohereTextGenerationModel.ts:101