Class: MistralTextEmbeddingModel

Hierarchy

• AbstractModel<MistralTextEmbeddingModelSettings>

  ↳ MistralTextEmbeddingModel

Implements

• EmbeddingModel<string, MistralTextEmbeddingModelSettings>

Accessors

modelInformation

• get modelInformation(): ModelInformation

Returns

ModelInformation

Implementation of

EmbeddingModel.modelInformation

Inherited from

AbstractModel.modelInformation

Defined in

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

---

modelName

• get modelName(): "mistral-embed"

Returns

"mistral-embed"

Overrides

AbstractModel.modelName

Defined in

packages/modelfusion/src/model-provider/mistral/MistralTextEmbeddingModel.ts:44

---

settingsForEvent

• get settingsForEvent(): Partial<MistralTextEmbeddingModelSettings>

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

Returns

Partial<MistralTextEmbeddingModelSettings>

Implementation of

EmbeddingModel.settingsForEvent

Overrides

AbstractModel.settingsForEvent

Defined in

packages/modelfusion/src/model-provider/mistral/MistralTextEmbeddingModel.ts:99

Constructors

constructor

• new MistralTextEmbeddingModel(settings): MistralTextEmbeddingModel

Parameters

Name	Type
settings	MistralTextEmbeddingModelSettings

Returns

MistralTextEmbeddingModel

Overrides

AbstractModel&lt;MistralTextEmbeddingModelSettings&gt;.constructor

Defined in

packages/modelfusion/src/model-provider/mistral/MistralTextEmbeddingModel.ts:39

Methods

callAPI

▸ callAPI(texts, callOptions): Promise<{ data: { embedding: number[] ; index: number ; object: string }[] ; id: string ; model: string ; object: string ; usage: { prompt_tokens: number ; total_tokens: number } }>

Parameters

Name	Type
texts	string[]
callOptions	FunctionCallOptions

Returns

Promise<{ data: { embedding: number[] ; index: number ; object: string }[] ; id: string ; model: string ; object: string ; usage: { prompt_tokens: number ; total_tokens: number } }>

Defined in

packages/modelfusion/src/model-provider/mistral/MistralTextEmbeddingModel.ts:58

---

doEmbedValues

▸ doEmbedValues(texts, options): Promise<{ embeddings: number[][] ; rawResponse: { data: { embedding: number[] ; index: number ; object: string }[] ; id: string ; model: string ; object: string ; usage: { prompt_tokens: number ; total_tokens: number } } }>

Parameters

Name	Type
texts	string[]
options	FunctionCallOptions

Returns

Promise<{ embeddings: number[][] ; rawResponse: { data: { embedding: number[] ; index: number ; object: string }[] ; id: string ; model: string ; object: string ; usage: { prompt_tokens: number ; total_tokens: number } } }>

Implementation of

EmbeddingModel.doEmbedValues

Defined in

packages/modelfusion/src/model-provider/mistral/MistralTextEmbeddingModel.ts:105

---

withSettings

▸ withSettings(additionalSettings): MistralTextEmbeddingModel

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<MistralTextEmbeddingModelSettings>

Returns

MistralTextEmbeddingModel

Example

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

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

Implementation of

EmbeddingModel.withSettings

Overrides

AbstractModel.withSettings

Defined in

packages/modelfusion/src/model-provider/mistral/MistralTextEmbeddingModel.ts:114

Properties

dimensions

• Readonly dimensions: 1024

The size of the embedding vector.

Implementation of

EmbeddingModel.dimensions

Defined in

packages/modelfusion/src/model-provider/mistral/MistralTextEmbeddingModel.ts:56

---

isParallelizable

• Readonly isParallelizable: false

Parallel calls are technically possible, but I have been hitting rate limits and disabled them for now.

Implementation of

EmbeddingModel.isParallelizable

Defined in

packages/modelfusion/src/model-provider/mistral/MistralTextEmbeddingModel.ts:54

---

maxValuesPerCall

• Readonly maxValuesPerCall: 32

Limit of how many values can be sent in a single API call.

Implementation of

EmbeddingModel.maxValuesPerCall

Defined in

packages/modelfusion/src/model-provider/mistral/MistralTextEmbeddingModel.ts:48

---

provider

• Readonly provider: "mistral"

Overrides

AbstractModel.provider

Defined in

packages/modelfusion/src/model-provider/mistral/MistralTextEmbeddingModel.ts:43

---

settings

• Readonly settings: MistralTextEmbeddingModelSettings

Implementation of

EmbeddingModel.settings

Inherited from

AbstractModel.settings

Defined in

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