Huggingface.js 文档

@huggingface/inference

Huggingface.js

加入 Hugging Face 社区

并获得增强的文档体验

在模型、数据集和 Spaces 上进行协作

通过加速推理获得更快的示例

切换文档主题

开始使用

@huggingface/inference

命名空间

片段

类

接口

类型别名

AudioClassificationArgs

Ƭ AudioClassificationArgs: BaseArgs & AudioClassificationInput | LegacyAudioInput

定义于

inference/src/tasks/audio/audioClassification.ts:9

AudioToAudioArgs

Ƭ AudioToAudioArgs: BaseArgs & { inputs: Blob } | LegacyAudioInput

定义于

inference/src/tasks/audio/audioToAudio.ts:8

AuthMethod

Ƭ AuthMethod: "none" | "hf-token" | "credentials-include" | "provider-key"

定义于

inference/src/types.ts:131

AutomaticSpeechRecognitionArgs

Ƭ AutomaticSpeechRecognitionArgs: BaseArgs & AutomaticSpeechRecognitionInput | LegacyAudioInput

定义于

inference/src/tasks/audio/automaticSpeechRecognition.ts:9

DocumentQuestionAnsweringArgs

Ƭ DocumentQuestionAnsweringArgs: BaseArgs & DocumentQuestionAnsweringInput & { inputs: DocumentQuestionAnsweringInputData & { image: Blob } }

定义于

inference/src/tasks/multimodal/documentQuestionAnswering.ts:13

FeatureExtractionArgs

Ƭ FeatureExtractionArgs: BaseArgs & FeatureExtractionInput & FeatureExtractionOAICompatInput

定义于

inference/src/tasks/nlp/featureExtraction.ts:12

FeatureExtractionOutput

Ƭ FeatureExtractionOutput: (number | number[] | number[][])[]

返回值为浮点型多维数组（维度取决于您发送的是字符串还是字符串列表，以及是否对您应用了自动降维，例如 mean_pooling。这应该在模型的 README 中解释）。

定义于

inference/src/tasks/nlp/featureExtraction.ts:17

FillMaskArgs

Ƭ FillMaskArgs: BaseArgs & FillMaskInput

定义于

inference/src/tasks/nlp/fillMask.ts:7

ImageClassificationArgs

Ƭ ImageClassificationArgs: BaseArgs & ImageClassificationInput | LegacyImageInput

定义于

inference/src/tasks/cv/imageClassification.ts:8

ImageSegmentationArgs

Ƭ ImageSegmentationArgs: BaseArgs & ImageSegmentationInput

定义于

inference/src/tasks/cv/imageSegmentation.ts:8

ImageToImageArgs

Ƭ ImageToImageArgs: BaseArgs & ImageToImageInput

定义于

inference/src/tasks/cv/imageToImage.ts:8

ImageToTextArgs

Ƭ ImageToTextArgs: BaseArgs & ImageToTextInput | LegacyImageInput

定义于

inference/src/tasks/cv/imageToText.ts:9

ImageToVideoArgs

Ƭ ImageToVideoArgs: BaseArgs & ImageToVideoInput

定义于

inference/src/tasks/cv/imageToVideo.ts:8

InferenceProvider

Ƭ InferenceProvider: typeof INFERENCE_PROVIDERS[number]

定义于

inference/src/types.ts:69

InferenceProviderOrPolicy

Ƭ InferenceProviderOrPolicy: typeof PROVIDERS_OR_POLICIES[number]

定义于

inference/src/types.ts:71

InferenceTask

Ƭ InferenceTask: Exclude\<PipelineType, "other"> | "conversational"

定义于

inference/src/types.ts:45

ModelId

Ƭ ModelId: string

HF 模型 ID，例如“meta-llama/Llama-3.3-70B-Instruct”

定义于

inference/src/types.ts:6

ObjectDetectionArgs

Ƭ ObjectDetectionArgs: BaseArgs & ObjectDetectionInput | LegacyImageInput

定义于

inference/src/tasks/cv/objectDetection.ts:8

QuestionAnsweringArgs

Ƭ QuestionAnsweringArgs: BaseArgs & QuestionAnsweringInput

定义于

inference/src/tasks/nlp/questionAnswering.ts:8

RequestArgs

Ƭ RequestArgs: BaseArgs & { data: Blob | ArrayBuffer } | { inputs: unknown } | { prompt: string } | { text: string } | { audio_url: string } | ChatCompletionInput & { parameters?: Record\<string, unknown> }

定义于

inference/src/types.ts:119

SentenceSimilarityArgs

Ƭ SentenceSimilarityArgs: BaseArgs & SentenceSimilarityInput

定义于

inference/src/tasks/nlp/sentenceSimilarity.ts:7

SummarizationArgs

Ƭ SummarizationArgs: BaseArgs & SummarizationInput

定义于

inference/src/tasks/nlp/summarization.ts:7

TableQuestionAnsweringArgs

Ƭ TableQuestionAnsweringArgs: BaseArgs & TableQuestionAnsweringInput

定义于

inference/src/tasks/nlp/tableQuestionAnswering.ts:7

TabularClassificationArgs

Ƭ TabularClassificationArgs: BaseArgs & { inputs: { data: Record\<string, string[]> } }

定义于

inference/src/tasks/tabular/tabularClassification.ts:6

TabularClassificationOutput

Ƭ TabularClassificationOutput: number[]

每行的预测标签列表

定义于

inference/src/tasks/tabular/tabularClassification.ts:18

TabularRegressionArgs

Ƭ TabularRegressionArgs: BaseArgs & { inputs: { data: Record\<string, string[]> } }

定义于

inference/src/tasks/tabular/tabularRegression.ts:6

TabularRegressionOutput

Ƭ TabularRegressionOutput: number[]

每行的预测值列表

定义于

inference/src/tasks/tabular/tabularRegression.ts:18

TextClassificationArgs

Ƭ TextClassificationArgs: BaseArgs & TextClassificationInput

定义于

inference/src/tasks/nlp/textClassification.ts:7

TextGenerationStreamFinishReason

Ƭ TextGenerationStreamFinishReason: "length" | "eos_token" | "stop_sequence"

定义于

inference/src/tasks/nlp/textGenerationStream.ts:48

TextToImageArgs

Ƭ TextToImageArgs: BaseArgs & TextToImageInput

定义于

inference/src/tasks/cv/textToImage.ts:8

TextToVideoArgs

Ƭ TextToVideoArgs: BaseArgs & TextToVideoInput

定义于

inference/src/tasks/cv/textToVideo.ts:11

TextToVideoOutput

Ƭ TextToVideoOutput: Blob

定义于

inference/src/tasks/cv/textToVideo.ts:13

TokenClassificationArgs

Ƭ TokenClassificationArgs: BaseArgs & TokenClassificationInput

定义于

inference/src/tasks/nlp/tokenClassification.ts:7

TranslationArgs

Ƭ TranslationArgs: BaseArgs & TranslationInput

定义于

inference/src/tasks/nlp/translation.ts:7

VisualQuestionAnsweringArgs

Ƭ VisualQuestionAnsweringArgs: BaseArgs & VisualQuestionAnsweringInput & { inputs: VisualQuestionAnsweringInputData & { image: Blob } }

定义于

inference/src/tasks/multimodal/visualQuestionAnswering.ts:13

ZeroShotClassificationArgs

Ƭ ZeroShotClassificationArgs: BaseArgs & ZeroShotClassificationInput

定义于

inference/src/tasks/nlp/zeroShotClassification.ts:7

ZeroShotImageClassificationArgs

Ƭ ZeroShotImageClassificationArgs: BaseArgs & ZeroShotImageClassificationInput | LegacyZeroShotImageClassificationInput

定义于

inference/src/tasks/cv/zeroShotImageClassification.ts:15

变量

INFERENCE _ PROVIDERS

• Const INFERENCE_PROVIDERS: 只读 ["black-forest-labs", "cerebras", "cohere", "fal-ai", "featherless-ai", "fireworks-ai", "groq", "hf-inference", "hyperbolic", "nebius", "novita", "nscale", "openai", "ovhcloud", "replicate", "sambanova", "together"]

定义于

inference/src/types.ts:47

PROVIDERS

• Const PROVIDERS: Record\<InferenceProvider, Partial\<Record\<InferenceTask, TaskProviderHelper>>>

定义于

inference/src/lib/getProviderHelper.ts:54

PROVIDERS _ OR _ POLICIES

• Const PROVIDERS_OR_POLICIES: 只读 ["black-forest-labs", "cerebras", "cohere", "fal-ai", "featherless-ai", "fireworks-ai", "groq", "hf-inference", "hyperbolic", "nebius", ""novita", "nscale", "openai", "ovhcloud", "replicate", "sambanova", "together", "auto"]

定义于

inference/src/types.ts:67

函数

audioClassification

▸ audioClassification(args, options?): Promise\<AudioClassificationOutput>

此任务读取音频输入并输出类别的可能性。推荐模型：superb/hubert-large-superb-er

参数

名称	类型
`args`	`AudioClassificationArgs`
`options?`	`Options`

返回值

Promise\<AudioClassificationOutput>

定义于

inference/src/tasks/audio/audioClassification.ts:15

audioToAudio

▸ audioToAudio(args, options?): Promise\<AudioToAudioOutput[]>

此任务读取音频输入并输出一个或多个音频文件。示例模型：speechbrain/sepformer-wham 进行音频源分离。

参数

名称	类型
`args`	`AudioToAudioArgs`
`options?`	`Options`

返回值

Promise\<AudioToAudioOutput[]>

定义于

inference/src/tasks/audio/audioToAudio.ts:39

automaticSpeechRecognition

▸ automaticSpeechRecognition(args, options?): Promise\<AutomaticSpeechRecognitionOutput>

此任务读取音频输入并输出音频文件中的口语单词。推荐模型（英语）：facebook/wav2vec2-large-960h-lv60-self

参数

名称	类型
`args`	`AutomaticSpeechRecognitionArgs`
`options?`	`Options`

返回值

Promise\<AutomaticSpeechRecognitionOutput>

定义于

inference/src/tasks/audio/automaticSpeechRecognition.ts:14

chatCompletion

▸ chatCompletion(args, options?): Promise\<ChatCompletionOutput>

使用聊天完成端点生成对提示的响应，使用 OpenAI 消息完成 API，无流

参数

名称	类型
`args`	`BaseArgs` & `ChatCompletionInput`
`options?`	`Options`

返回值

Promise\<ChatCompletionOutput>

定义于

inference/src/tasks/nlp/chatCompletion.ts:10

chatCompletionStream

▸ chatCompletionStream(args, options?): AsyncGenerator\<ChatCompletionStreamOutput>

用于从提示继续文本。与 textGeneration 相同，但返回一个可一次读取一个 token 的生成器

参数

名称	类型
`args`	`BaseArgs` & `ChatCompletionInput`
`options?`	`Options`

返回值

AsyncGenerator\<ChatCompletionStreamOutput>

定义于

inference/src/tasks/nlp/chatCompletionStream.ts:10

documentQuestionAnswering

▸ documentQuestionAnswering(args, options?): Promise\<DocumentQuestionAnsweringOutput[number]>

回答文档图像上的问题。推荐模型：impira/layoutlm-document-qa。

参数

名称	类型
`args`	`DocumentQuestionAnsweringArgs`
`options?`	`Options`

返回值

Promise\<DocumentQuestionAnsweringOutput[number]>

定义于

inference/src/tasks/multimodal/documentQuestionAnswering.ts:19

featureExtraction

▸ featureExtraction(args, options?): Promise\<FeatureExtractionOutput>

此任务读取一些文本并输出原始浮点值，这些值通常作为语义数据库/语义搜索的一部分被使用。

参数

名称	类型
`args`	`FeatureExtractionArgs`
`options?`	`Options`

返回值

Promise\<FeatureExtractionOutput>

定义于

inference/src/tasks/nlp/featureExtraction.ts:22

fillMask

▸ fillMask(args, options?): Promise\<FillMaskOutput>

尝试用缺失的单词（准确地说是标记）填充空白。这是 BERT 模型的基本任务。

参数

名称	类型
`args`	`FillMaskArgs`
`options?`	`Options`

Promise\<FillMaskOutput>

定义于

inference/src/tasks/nlp/fillMask.ts:12

getProviderHelper

▸ getProviderHelper(provider, task): TextToImageTaskHelper & TaskProviderHelper

通过名称和任务获取提供者辅助实例

参数

名称	类型
`提供者`	`"black-forest-labs"` \| `"cerebras"` \| `"cohere"` \| `"fal-ai"` \| `"featherless-ai"` \| `"fireworks-ai"` \| `"groq"` \| `"hf-inference"` \| `"hyperbolic"` \| `"nebius"` \| `"novita"` \| `"nscale"` \| `"openai"` \| `"ovhcloud"` \| `"replicate"` \| `"sambanova"` \| `"together"` \| `"auto"`
`任务`	`"text-to-image"`

TextToImageTaskHelper & TaskProviderHelper

定义于

inference/src/lib/getProviderHelper.ts:161

▸ getProviderHelper(provider, task): ConversationalTaskHelper & TaskProviderHelper

参数

名称	类型
`提供者`	`"black-forest-labs"` \| `"cerebras"` \| `"cohere"` \| `"fal-ai"` \| `"featherless-ai"` \| `"fireworks-ai"` \| `"groq"` \| `"hf-inference"` \| `"hyperbolic"` \| `"nebius"` \| `"novita"` \| `"nscale"` \| `"openai"` \| `"ovhcloud"` \| `"replicate"` \| `"sambanova"` \| `"together"` \| `"auto"`
`任务`	`"conversational"`

ConversationalTaskHelper & TaskProviderHelper

定义于

inference/src/lib/getProviderHelper.ts:165

▸ getProviderHelper(provider, task): TextGenerationTaskHelper & TaskProviderHelper

参数

名称	类型
`提供者`	`"black-forest-labs"` \| `"cerebras"` \| `"cohere"` \| `"fal-ai"` \| `"featherless-ai"` \| `"fireworks-ai"` \| `"groq"` \| `"hf-inference"` \| `"hyperbolic"` \| `"nebius"` \| `"novita"` \| `"nscale"` \| `"openai"` \| `"ovhcloud"` \| `"replicate"` \| `"sambanova"` \| `"together"` \| `"auto"`
`任务`	`"text-generation"`

TextGenerationTaskHelper & TaskProviderHelper

定义于

inference/src/lib/getProviderHelper.ts:169

▸ getProviderHelper(provider, task): TextToSpeechTaskHelper & TaskProviderHelper

参数

名称	类型
`提供者`	`"black-forest-labs"` \| `"cerebras"` \| `"cohere"` \| `"fal-ai"` \| `"featherless-ai"` \| `"fireworks-ai"` \| `"groq"` \| `"hf-inference"` \| `"hyperbolic"` \| `"nebius"` \| `"novita"` \| `"nscale"` \| `"openai"` \| `"ovhcloud"` \| `"replicate"` \| `"sambanova"` \| `"together"` \| `"auto"`
`任务`	`"text-to-speech"`

TextToSpeechTaskHelper & TaskProviderHelper

定义于

inference/src/lib/getProviderHelper.ts:173

▸ getProviderHelper(provider, task): TextToAudioTaskHelper & TaskProviderHelper

参数

名称	类型
`提供者`	`"black-forest-labs"` \| `"cerebras"` \| `"cohere"` \| `"fal-ai"` \| `"featherless-ai"` \| `"fireworks-ai"` \| `"groq"` \| `"hf-inference"` \| `"hyperbolic"` \| `"nebius"` \| `"novita"` \| `"nscale"` \| `"openai"` \| `"ovhcloud"` \| `"replicate"` \| `"sambanova"` \| `"together"` \| `"auto"`
`任务`	`"text-to-audio"`

TextToAudioTaskHelper & TaskProviderHelper

定义于

inference/src/lib/getProviderHelper.ts:177

▸ getProviderHelper(provider, task): AutomaticSpeechRecognitionTaskHelper & TaskProviderHelper

参数

名称	类型
`提供者`	`"black-forest-labs"` \| `"cerebras"` \| `"cohere"` \| `"fal-ai"` \| `"featherless-ai"` \| `"fireworks-ai"` \| `"groq"` \| `"hf-inference"` \| `"hyperbolic"` \| `"nebius"` \| `"novita"` \| `"nscale"` \| `"openai"` \| `"ovhcloud"` \| `"replicate"` \| `"sambanova"` \| `"together"` \| `"auto"`
`任务`	`"automatic-speech-recognition"`

AutomaticSpeechRecognitionTaskHelper & TaskProviderHelper

定义于

inference/src/lib/getProviderHelper.ts:181

▸ getProviderHelper(provider, task): TextToVideoTaskHelper & TaskProviderHelper

参数

名称	类型
`提供者`	`"black-forest-labs"` \| `"cerebras"` \| `"cohere"` \| `"fal-ai"` \| `"featherless-ai"` \| `"fireworks-ai"` \| `"groq"` \| `"hf-inference"` \| `"hyperbolic"` \| `"nebius"` \| `"novita"` \| `"nscale"` \| `"openai"` \| `"ovhcloud"` \| `"replicate"` \| `"sambanova"` \| `"together"` \| `"auto"`
`任务`	`"text-to-video"`

TextToVideoTaskHelper & TaskProviderHelper

定义于

inference/src/lib/getProviderHelper.ts:185

▸ getProviderHelper(provider, task): TextClassificationTaskHelper & TaskProviderHelper

参数

名称	类型
`提供者`	`"black-forest-labs"` \| `"cerebras"` \| `"cohere"` \| `"fal-ai"` \| `"featherless-ai"` \| `"fireworks-ai"` \| `"groq"` \| `"hf-inference"` \| `"hyperbolic"` \| `"nebius"` \| `"novita"` \| `"nscale"` \| `"openai"` \| `"ovhcloud"` \| `"replicate"` \| `"sambanova"` \| `"together"` \| `"auto"`
`任务`	`"text-classification"`

TextClassificationTaskHelper & TaskProviderHelper

定义于

inference/src/lib/getProviderHelper.ts:189

▸ getProviderHelper(provider, task): QuestionAnsweringTaskHelper & TaskProviderHelper

参数

名称	类型
`提供者`	`"black-forest-labs"` \| `"cerebras"` \| `"cohere"` \| `"fal-ai"` \| `"featherless-ai"` \| `"fireworks-ai"` \| `"groq"` \| `"hf-inference"` \| `"hyperbolic"` \| `"nebius"` \| `"novita"` \| `"nscale"` \| `"openai"` \| `"ovhcloud"` \| `"replicate"` \| `"sambanova"` \| `"together"` \| `"auto"`
`任务`	`"question-answering"`

QuestionAnsweringTaskHelper & TaskProviderHelper

定义于

inference/src/lib/getProviderHelper.ts:193

▸ getProviderHelper(provider, task): AudioClassificationTaskHelper & TaskProviderHelper

参数

名称	类型
`提供者`	`"black-forest-labs"` \| `"cerebras"` \| `"cohere"` \| `"fal-ai"` \| `"featherless-ai"` \| `"fireworks-ai"` \| `"groq"` \| `"hf-inference"` \| `"hyperbolic"` \| `"nebius"` \| `"novita"` \| `"nscale"` \| `"openai"` \| `"ovhcloud"` \| `"replicate"` \| `"sambanova"` \| `"together"` \| `"auto"`
`任务`	`"audio-classification"`

AudioClassificationTaskHelper & TaskProviderHelper

定义于

inference/src/lib/getProviderHelper.ts:197

▸ getProviderHelper(provider, task): AudioToAudioTaskHelper & TaskProviderHelper

参数

名称	类型
`提供者`	`"black-forest-labs"` \| `"cerebras"` \| `"cohere"` \| `"fal-ai"` \| `"featherless-ai"` \| `"fireworks-ai"` \| `"groq"` \| `"hf-inference"` \| `"hyperbolic"` \| `"nebius"` \| `"novita"` \| `"nscale"` \| `"openai"` \| `"ovhcloud"` \| `"replicate"` \| `"sambanova"` \| `"together"` \| `"auto"`
`任务`	`"audio-to-audio"`

AudioToAudioTaskHelper & TaskProviderHelper

定义于

inference/src/lib/getProviderHelper.ts:201

▸ getProviderHelper(provider, task): FillMaskTaskHelper & TaskProviderHelper

参数

名称	类型
`提供者`	`"black-forest-labs"` \| `"cerebras"` \| `"cohere"` \| `"fal-ai"` \| `"featherless-ai"` \| `"fireworks-ai"` \| `"groq"` \| `"hf-inference"` \| `"hyperbolic"` \| `"nebius"` \| `"novita"` \| `"nscale"` \| `"openai"` \| `"ovhcloud"` \| `"replicate"` \| `"sambanova"` \| `"together"` \| `"auto"`
`任务`	`"fill-mask"`

FillMaskTaskHelper & TaskProviderHelper

定义于

inference/src/lib/getProviderHelper.ts:205

▸ getProviderHelper(provider, task): FeatureExtractionTaskHelper & TaskProviderHelper

参数

名称	类型
`提供者`	`"black-forest-labs"` \| `"cerebras"` \| `"cohere"` \| `"fal-ai"` \| `"featherless-ai"` \| `"fireworks-ai"` \| `"groq"` \| `"hf-inference"` \| `"hyperbolic"` \| `"nebius"` \| `"novita"` \| `"nscale"` \| `"openai"` \| `"ovhcloud"` \| `"replicate"` \| `"sambanova"` \| `"together"` \| `"auto"`
`任务`	`"feature-extraction"`

FeatureExtractionTaskHelper & TaskProviderHelper

定义于

inference/src/lib/getProviderHelper.ts:209

▸ getProviderHelper(provider, task): ImageClassificationTaskHelper & TaskProviderHelper

参数

名称	类型
`提供者`	`"black-forest-labs"` \| `"cerebras"` \| `"cohere"` \| `"fal-ai"` \| `"featherless-ai"` \| `"fireworks-ai"` \| `"groq"` \| `"hf-inference"` \| `"hyperbolic"` \| `"nebius"` \| `"novita"` \| `"nscale"` \| `"openai"` \| `"ovhcloud"` \| `"replicate"` \| `"sambanova"` \| `"together"` \| `"auto"`
`任务`	`"image-classification"`

ImageClassificationTaskHelper & TaskProviderHelper

定义于

inference/src/lib/getProviderHelper.ts:213

▸ getProviderHelper(provider, task): ImageSegmentationTaskHelper & TaskProviderHelper

参数

名称	类型
`提供者`	`"black-forest-labs"` \| `"cerebras"` \| `"cohere"` \| `"fal-ai"` \| `"featherless-ai"` \| `"fireworks-ai"` \| `"groq"` \| `"hf-inference"` \| `"hyperbolic"` \| `"nebius"` \| `"novita"` \| `"nscale"` \| `"openai"` \| `"ovhcloud"` \| `"replicate"` \| `"sambanova"` \| `"together"` \| `"auto"`
`任务`	`"image-segmentation"`

ImageSegmentationTaskHelper & TaskProviderHelper

定义于

inference/src/lib/getProviderHelper.ts:217

▸ getProviderHelper(provider, task): DocumentQuestionAnsweringTaskHelper & TaskProviderHelper

参数

名称	类型
`提供者`	`"black-forest-labs"` \| `"cerebras"` \| `"cohere"` \| `"fal-ai"` \| `"featherless-ai"` \| `"fireworks-ai"` \| `"groq"` \| `"hf-inference"` \| `"hyperbolic"` \| `"nebius"` \| `"novita"` \| `"nscale"` \| `"openai"` \| `"ovhcloud"` \| `"replicate"` \| `"sambanova"` \| `"together"` \| `"auto"`
`任务`	`"document-question-answering"`

DocumentQuestionAnsweringTaskHelper & TaskProviderHelper

定义于

inference/src/lib/getProviderHelper.ts:221

▸ getProviderHelper(provider, task): ImageToTextTaskHelper & TaskProviderHelper

参数

名称	类型
`提供者`	`"black-forest-labs"` \| `"cerebras"` \| `"cohere"` \| `"fal-ai"` \| `"featherless-ai"` \| `"fireworks-ai"` \| `"groq"` \| `"hf-inference"` \| `"hyperbolic"` \| `"nebius"` \| `"novita"` \| `"nscale"` \| `"openai"` \| `"ovhcloud"` \| `"replicate"` \| `"sambanova"` \| `"together"` \| `"auto"`
`任务`	`"image-to-text"`

ImageToTextTaskHelper & TaskProviderHelper

定义于

inference/src/lib/getProviderHelper.ts:225

▸ getProviderHelper(provider, task): ObjectDetectionTaskHelper & TaskProviderHelper

参数

名称	类型
`提供者`	`"black-forest-labs"` \| `"cerebras"` \| `"cohere"` \| `"fal-ai"` \| `"featherless-ai"` \| `"fireworks-ai"` \| `"groq"` \| `"hf-inference"` \| `"hyperbolic"` \| `"nebius"` \| `"novita"` \| `"nscale"` \| `"openai"` \| `"ovhcloud"` \| `"replicate"` \| `"sambanova"` \| `"together"` \| `"auto"`
`任务`	`"object-detection"`

ObjectDetectionTaskHelper & TaskProviderHelper

定义于

inference/src/lib/getProviderHelper.ts:229

▸ getProviderHelper(provider, task): ZeroShotImageClassificationTaskHelper & TaskProviderHelper

参数

名称	类型
`提供者`	`"black-forest-labs"` \| `"cerebras"` \| `"cohere"` \| `"fal-ai"` \| `"featherless-ai"` \| `"fireworks-ai"` \| `"groq"` \| `"hf-inference"` \| `"hyperbolic"` \| `"nebius"` \| `"novita"` \| `"nscale"` \| `"openai"` \| `"ovhcloud"` \| `"replicate"` \| `"sambanova"` \| `"together"` \| `"auto"`
`任务`	`"zero-shot-image-classification"`

ZeroShotImageClassificationTaskHelper & TaskProviderHelper

定义于

inference/src/lib/getProviderHelper.ts:233

▸ getProviderHelper(provider, task): ZeroShotClassificationTaskHelper & TaskProviderHelper

参数

名称	类型
`提供者`	`"black-forest-labs"` \| `"cerebras"` \| `"cohere"` \| `"fal-ai"` \| `"featherless-ai"` \| `"fireworks-ai"` \| `"groq"` \| `"hf-inference"` \| `"hyperbolic"` \| `"nebius"` \| `"novita"` \| `"nscale"` \| `"openai"` \| `"ovhcloud"` \| `"replicate"` \| `"sambanova"` \| `"together"` \| `"auto"`
`任务`	`"zero-shot-classification"`

ZeroShotClassificationTaskHelper & TaskProviderHelper

定义于

inference/src/lib/getProviderHelper.ts:237

▸ getProviderHelper(provider, task): ImageToImageTaskHelper & TaskProviderHelper

参数

名称	类型
`提供者`	`"black-forest-labs"` \| `"cerebras"` \| `"cohere"` \| `"fal-ai"` \| `"featherless-ai"` \| `"fireworks-ai"` \| `"groq"` \| `"hf-inference"` \| `"hyperbolic"` \| `"nebius"` \| `"novita"` \| `"nscale"` \| `"openai"` \| `"ovhcloud"` \| `"replicate"` \| `"sambanova"` \| `"together"` \| `"auto"`
`任务`	`"image-to-image"`

ImageToImageTaskHelper & TaskProviderHelper

定义于

inference/src/lib/getProviderHelper.ts:241

▸ getProviderHelper(provider, task): ImageToVideoTaskHelper & TaskProviderHelper

参数

名称	类型
`提供者`	`"black-forest-labs"` \| `"cerebras"` \| `"cohere"` \| `"fal-ai"` \| `"featherless-ai"` \| `"fireworks-ai"` \| `"groq"` \| `"hf-inference"` \| `"hyperbolic"` \| `"nebius"` \| `"novita"` \| `"nscale"` \| `"openai"` \| `"ovhcloud"` \| `"replicate"` \| `"sambanova"` \| `"together"` \| `"auto"`
`任务`	`"image-to-video"`

ImageToVideoTaskHelper & TaskProviderHelper

定义于

inference/src/lib/getProviderHelper.ts:245

▸ getProviderHelper(provider, task): SentenceSimilarityTaskHelper & TaskProviderHelper

参数

名称	类型
`提供者`	`"black-forest-labs"` \| `"cerebras"` \| `"cohere"` \| `"fal-ai"` \| `"featherless-ai"` \| `"fireworks-ai"` \| `"groq"` \| `"hf-inference"` \| `"hyperbolic"` \| `"nebius"` \| `"novita"` \| `"nscale"` \| `"openai"` \| `"ovhcloud"` \| `"replicate"` \| `"sambanova"` \| `"together"` \| `"auto"`
`任务`	`"sentence-similarity"`

SentenceSimilarityTaskHelper & TaskProviderHelper

定义于

inference/src/lib/getProviderHelper.ts:249

▸ getProviderHelper(provider, task): TableQuestionAnsweringTaskHelper & TaskProviderHelper

参数

名称	类型
`提供者`	`"black-forest-labs"` \| `"cerebras"` \| `"cohere"` \| `"fal-ai"` \| `"featherless-ai"` \| `"fireworks-ai"` \| `"groq"` \| `"hf-inference"` \| `"hyperbolic"` \| `"nebius"` \| `"novita"` \| `"nscale"` \| `"openai"` \| `"ovhcloud"` \| `"replicate"` \| `"sambanova"` \| `"together"` \| `"auto"`
`任务`	`"table-question-answering"`

TableQuestionAnsweringTaskHelper & TaskProviderHelper

定义于

inference/src/lib/getProviderHelper.ts:253

▸ getProviderHelper(provider, task): TabularClassificationTaskHelper & TaskProviderHelper

参数

名称	类型
`提供者`	`"black-forest-labs"` \| `"cerebras"` \| `"cohere"` \| `"fal-ai"` \| `"featherless-ai"` \| `"fireworks-ai"` \| `"groq"` \| `"hf-inference"` \| `"hyperbolic"` \| `"nebius"` \| `"novita"` \| `"nscale"` \| `"openai"` \| `"ovhcloud"` \| `"replicate"` \| `"sambanova"` \| `"together"` \| `"auto"`
`任务`	`"tabular-classification"`

TabularClassificationTaskHelper & TaskProviderHelper

定义于

inference/src/lib/getProviderHelper.ts:257

▸ getProviderHelper(provider, task): TabularRegressionTaskHelper & TaskProviderHelper

参数

名称	类型
`提供者`	`"black-forest-labs"` \| `"cerebras"` \| `"cohere"` \| `"fal-ai"` \| `"featherless-ai"` \| `"fireworks-ai"` \| `"groq"` \| `"hf-inference"` \| `"hyperbolic"` \| `"nebius"` \| `"novita"` \| `"nscale"` \| `"openai"` \| `"ovhcloud"` \| `"replicate"` \| `"sambanova"` \| `"together"` \| `"auto"`
`任务`	`"tabular-regression"`

TabularRegressionTaskHelper & TaskProviderHelper

定义于

inference/src/lib/getProviderHelper.ts:261

▸ getProviderHelper(provider, task): TokenClassificationTaskHelper & TaskProviderHelper

参数

名称	类型
`提供者`	`"black-forest-labs"` \| `"cerebras"` \| `"cohere"` \| `"fal-ai"` \| `"featherless-ai"` \| `"fireworks-ai"` \| `"groq"` \| `"hf-inference"` \| `"hyperbolic"` \| `"nebius"` \| `"novita"` \| `"nscale"` \| `"openai"` \| `"ovhcloud"` \| `"replicate"` \| `"sambanova"` \| `"together"` \| `"auto"`
`任务`	`"token-classification"`

TokenClassificationTaskHelper & TaskProviderHelper

定义于

inference/src/lib/getProviderHelper.ts:265

▸ getProviderHelper(provider, task): TranslationTaskHelper & TaskProviderHelper

参数

名称	类型
`提供者`	`"black-forest-labs"` \| `"cerebras"` \| `"cohere"` \| `"fal-ai"` \| `"featherless-ai"` \| `"fireworks-ai"` \| `"groq"` \| `"hf-inference"` \| `"hyperbolic"` \| `"nebius"` \| `"novita"` \| `"nscale"` \| `"openai"` \| `"ovhcloud"` \| `"replicate"` \| `"sambanova"` \| `"together"` \| `"auto"`
`任务`	`"translation"`

TranslationTaskHelper & TaskProviderHelper

定义于

inference/src/lib/getProviderHelper.ts:269

▸ getProviderHelper(provider, task): SummarizationTaskHelper & TaskProviderHelper

参数

名称	类型
`提供者`	`"black-forest-labs"` \| `"cerebras"` \| `"cohere"` \| `"fal-ai"` \| `"featherless-ai"` \| `"fireworks-ai"` \| `"groq"` \| `"hf-inference"` \| `"hyperbolic"` \| `"nebius"` \| `"novita"` \| `"nscale"` \| `"openai"` \| `"ovhcloud"` \| `"replicate"` \| `"sambanova"` \| `"together"` \| `"auto"`
`任务`	`"summarization"`

SummarizationTaskHelper & TaskProviderHelper

定义于

inference/src/lib/getProviderHelper.ts:273

▸ getProviderHelper(provider, task): VisualQuestionAnsweringTaskHelper & TaskProviderHelper

参数

名称	类型
`提供者`	`"black-forest-labs"` \| `"cerebras"` \| `"cohere"` \| `"fal-ai"` \| `"featherless-ai"` \| `"fireworks-ai"` \| `"groq"` \| `"hf-inference"` \| `"hyperbolic"` \| `"nebius"` \| `"novita"` \| `"nscale"` \| `"openai"` \| `"ovhcloud"` \| `"replicate"` \| `"sambanova"` \| `"together"` \| `"auto"`
`任务`	`"visual-question-answering"`

VisualQuestionAnsweringTaskHelper & TaskProviderHelper

定义于

inference/src/lib/getProviderHelper.ts:277

▸ getProviderHelper(provider, task): TaskProviderHelper

参数

名称	类型
`提供者`	`"black-forest-labs"` \| `"cerebras"` \| `"cohere"` \| `"fal-ai"` \| `"featherless-ai"` \| `"fireworks-ai"` \| `"groq"` \| `"hf-inference"` \| `"hyperbolic"` \| `"nebius"` \| `"novita"` \| `"nscale"` \| `"openai"` \| `"ovhcloud"` \| `"replicate"` \| `"sambanova"` \| `"together"` \| `"auto"`
`任务`	`undefined` \| `InferenceTask`

TaskProviderHelper

定义于

inference/src/lib/getProviderHelper.ts:281

imageClassification

▸ imageClassification(args, options?): Promise\<ImageClassificationOutput>

此任务读取图像输入并输出类别的可能性。推荐模型：google/vit-base-patch16-224

参数

名称	类型
`args`	`ImageClassificationArgs`
`options?`	`Options`

Promise\<ImageClassificationOutput>

定义于

inference/src/tasks/cv/imageClassification.ts:14

imageSegmentation

▸ imageSegmentation(args, options?): Promise\<ImageSegmentationOutput>

此任务读取图像输入并输出检测到对象的类别可能性和边界框。推荐模型：facebook/detr-resnet-50-panoptic

参数

名称	类型
`args`	`ImageSegmentationArgs`
`options?`	`Options`

Promise\<ImageSegmentationOutput>

定义于

inference/src/tasks/cv/imageSegmentation.ts:14

imageToImage

▸ imageToImage(args, options?): Promise\<Blob>

此任务读取文本输入并输出图像。推荐模型：lllyasviel/sd-controlnet-depth

参数

名称	类型
`args`	`ImageToImageArgs`
`options?`	`Options`

Promise\<Blob>

定义于

inference/src/tasks/cv/imageToImage.ts:14

imageToText

▸ imageToText(args, options?): Promise\<ImageToTextOutput>

此任务读取图像输入并输出文本描述。

参数

名称	类型
`args`	`ImageToTextArgs`
`options?`	`Options`

Promise\<ImageToTextOutput>

定义于

inference/src/tasks/cv/imageToText.ts:13

imageToVideo

▸ imageToVideo(args, options?): Promise\<Blob>

此任务读取文本输入并输出图像。推荐模型：Wan-AI/Wan2.1-I2V-14B-720P

参数

名称	类型
`args`	`ImageToVideoArgs`
`options?`	`Options`

Promise\<Blob>

定义于

inference/src/tasks/cv/imageToVideo.ts:14

makeRequestOptions

▸ makeRequestOptions(args, providerHelper, options?): Promise\<{ info: RequestInit ; url: string }>

辅助函数，用于准备请求参数。此异步版本处理模型 ID 解析步骤。

参数

名称	类型
`args`	`RequestArgs` & { `data?`: `Blob` \| `ArrayBuffer` ; `stream?`: `boolean` }
`providerHelper`	`TaskProviderHelper`
`options?`	`Options` & { `task?`: `InferenceTask` }

Promise\<{ info: RequestInit ; url: string }>

定义于

inference/src/lib/makeRequestOptions.ts:19

makeRequestOptionsFromResolvedModel

▸ makeRequestOptionsFromResolvedModel(resolvedModel, providerHelper, args, mapping, options?): Object

辅助函数，用于准备请求参数。- 仅供内部使用。此同步版本跳过模型 ID 解析步骤。

参数

名称	类型
`resolvedModel`	`字符串`
`providerHelper`	`TaskProviderHelper`
`args`	`RequestArgs` & { `data?`: `Blob` \| `ArrayBuffer` ; `stream?`: `boolean` }
`mapping`	`undefined` \| `InferenceProviderMappingEntry`
`options?`	`Options` & { `task?`: `InferenceTask` }

Object

名称	类型
`info`	`RequestInit`
`url`	`字符串`

定义于

inference/src/lib/makeRequestOptions.ts:105

objectDetection

▸ objectDetection(args, options?): Promise\<ObjectDetectionOutput>

此任务读取图像输入并输出检测到对象的类别可能性和边界框。推荐模型：facebook/detr-resnet-50

参数

名称	类型
`args`	`ObjectDetectionArgs`
`options?`	`Options`

Promise\<ObjectDetectionOutput>

定义于

inference/src/tasks/cv/objectDetection.ts:14

questionAnswering

▸ questionAnswering(args, options?): Promise\<QuestionAnsweringOutput[number]>

想要一个无所不知的机器人，可以回答任何问题？推荐模型：deepset/roberta-base-squad2

参数

名称	类型
`args`	`QuestionAnsweringArgs`
`options?`	`Options`

Promise\<QuestionAnsweringOutput[number]>

定义于

inference/src/tasks/nlp/questionAnswering.ts:13

request

▸ request\<T>(args, options?): Promise\<T>

用于向推理提供者进行自定义调用的原语

类型参数

名称
`T`

参数

名称	类型
`args`	`RequestArgs`
`options?`	`Options` & { `task?`: `InferenceTask` }

Promise\<T>

已弃用

请改用特定的任务函数。此函数将在未来版本中移除。

定义于

inference/src/tasks/custom/request.ts:11

sentenceSimilarity

▸ sentenceSimilarity(args, options?): Promise\<SentenceSimilarityOutput>

通过比较嵌入来计算一段文本与另一组句子之间的语义相似度。

参数

名称	类型
`args`	`SentenceSimilarityArgs`
`options?`	`Options`

Promise\<SentenceSimilarityOutput>

定义于

inference/src/tasks/nlp/sentenceSimilarity.ts:12

setLogger

▸ setLogger(logger): void

参数

名称	类型
`logger`	`Logger`

空

定义于

inference/src/lib/logger.ts:5

streamingRequest

▸ streamingRequest\<T>(args, options?): AsyncGenerator\<T>

用于进行自定义推理调用的原语，该调用期望服务器发送事件，并通过生成器返回响应

类型参数

名称
`T`

参数

名称	类型
`args`	`RequestArgs`
`options?`	`Options` & { `task?`: `InferenceTask` }

AsyncGenerator\<T>

已弃用

请改用特定的任务函数。此函数将在未来版本中移除。

定义于

inference/src/tasks/custom/streamingRequest.ts:11

summarization

▸ summarization(args, options?): Promise\<SummarizationOutput>

此任务以将较长文本总结为较短文本而闻名。请注意，某些模型的输入长度有最大限制。这意味着摘要无法处理完整的书籍等。选择模型时请谨慎。

参数

名称	类型
`args`	`SummarizationArgs`
`options?`	`Options`

Promise\<SummarizationOutput>

定义于

inference/src/tasks/nlp/summarization.ts:12

tableQuestionAnswering

▸ tableQuestionAnswering(args, options?): Promise\<TableQuestionAnsweringOutput[number]\>

不懂SQL？不想深入研究大型电子表格？用普通英语提问！推荐模型：google/tapas-base-finetuned-wtq。

参数

名称	类型
`args`	`TableQuestionAnsweringArgs`
`options?`	`Options`

Promise\<TableQuestionAnsweringOutput[number]\>

定义于

inference/src/tasks/nlp/tableQuestionAnswering.ts:12

tabularClassification

▸ tabularClassification(args, options?): Promise\<TabularClassificationOutput\>

根据给定的表格形式特征集预测目标标签。通常，您会希望在训练数据上训练一个分类模型，并将其与相同格式的新数据一起使用。示例模型：vvmnnnkv/wine-quality

参数

名称	类型
`args`	`TabularClassificationArgs`
`options?`	`Options`

Promise\<TabularClassificationOutput\>

定义于

inference/src/tasks/tabular/tabularClassification.ts:25

tabularRegression

▸ tabularRegression(args, options?): Promise\<TabularRegressionOutput\>

为给定表格形式的特征集预测目标值。通常，您会希望在训练数据上训练回归模型，并将其与格式相同的新数据一起使用。示例模型：scikit-learn/Fish-Weight

参数

名称	类型
`args`	`TabularRegressionArgs`
`options?`	`Options`

Promise\<TabularRegressionOutput\>

定义于

inference/src/tasks/tabular/tabularRegression.ts:25

textClassification

▸ textClassification(args, options?): Promise\<TextClassificationOutput\>

通常用于情感分析，它将输出输入类的可能性。推荐模型：distilbert-base-uncased-finetuned-sst-2-english

参数

名称	类型
`args`	`TextClassificationArgs`
`options?`	`Options`

Promise\<TextClassificationOutput\>

定义于

inference/src/tasks/nlp/textClassification.ts:12

textGeneration

▸ textGeneration(args, options?): Promise\<TextGenerationOutput\>

用于从提示符继续文本。这是一个非常通用的任务。推荐模型：gpt2（一个简单的模型，但很有趣）。

参数

名称	类型
`args`	`BaseArgs` \& `TextGenerationInput`
`options?`	`Options`

Promise\<TextGenerationOutput\>

定义于

inference/src/tasks/nlp/textGeneration.ts:13

textGenerationStream

▸ textGenerationStream(args, options?): AsyncGenerator\<TextGenerationStreamOutput\>

用于从提示继续文本。与 textGeneration 相同，但返回一个可一次读取一个 token 的生成器

参数

名称	类型
`args`	`BaseArgs` \& `TextGenerationInput`
`options?`	`Options`

AsyncGenerator\<TextGenerationStreamOutput\>

定义于

inference/src/tasks/nlp/textGenerationStream.ts:90

textToImage

▸ textToImage(args, options?): Promise\<string\>

此任务读取一些文本输入并输出图像。推荐模型：stabilityai/stable-diffusion-2

参数

名称	类型
`args`	`TextToImageArgs`
`options?`	`TextToImageOptions` \& { `outputType`: `"url"` }

Promise\<string\>

定义于

inference/src/tasks/cv/textToImage.ts:18

▸ textToImage(args, options?): Promise\<Blob\>

参数

名称	类型
`args`	`TextToImageArgs`
`options?`	`TextToImageOptions` \& { `outputType?`: `"blob"` }

Promise\<Blob>

定义于

inference/src/tasks/cv/textToImage.ts:22

▸ textToImage(args, options?): Promise\<Record\<string, unknown\>\>

参数

名称	类型
`args`	`TextToImageArgs`
`options?`	`TextToImageOptions` \& { `outputType?`: `"json"` }

Promise\<Record\<string, unknown\>\>

定义于

inference/src/tasks/cv/textToImage.ts:26

textToSpeech

▸ textToSpeech(args, options?): Promise\<Blob\>

此任务合成语音音频，发出给定文本。推荐模型：espnet/kan-bayashi_ljspeech_vits

参数

名称	类型
`args`	`TextToSpeechArgs`
`options?`	`Options`

Promise\<Blob>

定义于

inference/src/tasks/audio/textToSpeech.ts:15

textToVideo

▸ textToVideo(args, options?): Promise\<TextToVideoOutput\>

参数

名称	类型
`args`	`TextToVideoArgs`
`options?`	`Options`

Promise\<TextToVideoOutput\>

定义于

inference/src/tasks/cv/textToVideo.ts:15

tokenClassification

▸ tokenClassification(args, options?): Promise\<TokenClassificationOutput\>

通常用于句子解析，可以是语法分析，也可以是命名实体识别（NER）以理解文本中包含的关键词。推荐模型：dbmdz/bert-large-cased-finetuned-conll03-english

参数

名称	类型
`args`	`TokenClassificationArgs`
`options?`	`Options`

Promise\<TokenClassificationOutput\>

定义于

inference/src/tasks/nlp/tokenClassification.ts:12

translation

▸ translation(args, options?): Promise\<TranslationOutput\>

此任务众所周知可将文本从一种语言翻译成另一种语言。推荐模型：Helsinki-NLP/opus-mt-ru-en。

参数

名称	类型
`args`	`TranslationArgs`
`options?`	`Options`

Promise\<TranslationOutput\>

定义于

inference/src/tasks/nlp/translation.ts:11

visualQuestionAnswering

▸ visualQuestionAnswering(args, options?): Promise\<VisualQuestionAnsweringOutput[number]\>

回答图像上的问题。推荐模型：dandelin/vilt-b32-finetuned-vqa。

参数

名称	类型
`args`	`VisualQuestionAnsweringArgs`
`options?`	`Options`

Promise\<VisualQuestionAnsweringOutput[number]\>

定义于

inference/src/tasks/multimodal/visualQuestionAnswering.ts:19

zeroShotClassification

▸ zeroShotClassification(args, options?): Promise\<ZeroShotClassificationOutput\>

此任务在零代码的情况下进行分类非常有用，您只需传递一个句子/段落和该句子的可能标签，即可获得结果。推荐模型：facebook/bart-large-mnli。

参数

名称	类型
`args`	`ZeroShotClassificationArgs`
`options?`	`Options`

Promise\<ZeroShotClassificationOutput\>

定义于

inference/src/tasks/nlp/zeroShotClassification.ts:12

zeroShotImageClassification

▸ zeroShotImageClassification(args, options?): Promise\<ZeroShotImageClassificationOutput\>

将图像分类到指定的类别中。推荐模型：openai/clip-vit-large-patch14-336

参数

名称	类型
`args`	`ZeroShotImageClassificationArgs`
`options?`	`Options`

Promise\<ZeroShotImageClassificationOutput\>

定义于

inference/src/tasks/cv/zeroShotImageClassification.ts:44

< > 在 GitHub 上更新

←使用推理客户端 HfInference→