hfapigo

package module
v1.2.2 Latest Latest
Warning

This package is not in the latest version of its module.

 Go to latest Published: May 14, 2023 License: MIT Imports: 10 Imported by: 20

README

hfapigo

Unit Tests CodeQL Go Report Card Go Reference

(Golang) Go bindings for the Hugging Face Inference API. Directly call any model available in the Model Hub.

An API key is required for authorized access. To get one, create a Hugging Face profile.

Usage

See the examples directory.

Resources

Documentation

Index

Constants

View Source 
const (
	AuthHeaderKey    = "Authorization"
	AuthHeaderPrefix = "Bearer "
)
View Source 
const (
	MaxCandidateLabels       = 10
	RecommendedZeroShotModel = "facebook/bart-large-mnli"
)
View Source 
const APIBaseURL = "https://api-inference.huggingface.co/models/"
View Source 
const RecommendedAudioClassificationModel = "superb/hubert-large-superb-er"
View Source 
const RecommendedConversationalModel = "microsoft/DialoGPT-large"
View Source 
const RecommendedFillMaskModel = "bert-base-uncased"
View Source 
const RecommendedImageClassificationModel = "google/vit-base-patch16-224"
View Source 
const RecommendedImageSegmentationModel = "facebook/detr-resnet-50-panoptic"
View Source 
const RecommendedObjectDetectionModel = "facebook/detr-resnet-50"
View Source 
const RecommendedQuestionAnsweringModel = "bert-large-uncased-whole-word-masking-finetuned-squad"
View Source 
const (
	RecommendedRussianToEnglishModel = "Helsinki-NLP/opus-mt-ru-en"
)
View Source 
const (
	RecommendedSentenceSimilarityModel = "sentence-transformers/all-MiniLM-L6-v2"
)
View Source 
const RecommendedSpeechRecongnitionModelEnglish = "facebook/wav2vec2-large-960h-lv60-self"
View Source 
const RecommendedTableQuestionAnsweringModel = "google/tapas-base-finetuned-wtq"
View Source 
const (
	RecommendedTextClassificationModel = "distilbert-base-uncased-finetuned-sst-2-english"
)
View Source 
const RecommendedTextGenerationModel = "gpt2"
View Source 
const RecommendedTextToImageModel = "runwayml/stable-diffusion-v1-5"
View Source 
const RecommendedTokenClassificationModel = "dbmdz/bert-large-cased-finetuned-conll03-english"
View Source 
const RecommmendedSummarizationModel = "facebook/bart-large-cnn"

Variables

View Source 
var APIKey = func() string { return "" }

Functions

func MakeHFAPIRequest 

func MakeHFAPIRequest(jsonBody []byte, model string) ([]byte, error)

MakeHFAPIRequest builds and sends an HTTP POST request to the given model using the provided JSON body. If the request is successful, returns the response JSON and a nil error. If the request fails, returns an empty slice and an error describing the failure.

func MakeHFAPIRequestWithMedia 

func MakeHFAPIRequestWithMedia(model, mediaFile string) ([]byte, error)

func SendTextToImageRequest added in v1.2.0 

func SendTextToImageRequest(model string, request *TextToImageRequest) (image.Image, string, error)

Send a TextToImageRequest. If successful, returns the generated image object, format name, and nil. If unsuccessful, returns nil, "", and an error.

func SetAPIKey 

func SetAPIKey(key string)

Types

type AggregationStrategy 

type AggregationStrategy string
const (
	// Every token gets classified without further aggregation.
	AggregationStrategyNone AggregationStrategy = "none"

	// Entities are grouped according to the default schema (B-, I- tags get merged when the tag is similar).
	AggregationStrategySimple AggregationStrategy = "simple"

	// Same as the simple strategy except entities cannot end up with different tags. Entities will use the tag of the first token when there is ambiguity.
	AggregationStrategyFirst AggregationStrategy = "first"

	// Same as the simple strategy except entities cannot end up with different tags. Scores are averaged across tokens and then the maximum label is applied.
	AggregationStrategyAverage AggregationStrategy = "average"

	// Same as the simple strategy except entities cannot end up with different tags. Entity will be the token with the maximum score.
	AggregationStrategyMax AggregationStrategy = "max"
)

type AudioClassificationResponse 

type AudioClassificationResponse struct {
	Score float64 `json:"score,omitempty"`
	Label string  `json:"label,omitempty"`
}

Response structure for audio classification endpoint

func SendAudioClassificationRequest 

func SendAudioClassificationRequest(model, audioFile string) ([]*AudioClassificationResponse, error)

type Conversation 

type Conversation struct {
	// The last outputs from the model in the conversation, after the model has run.
	GeneratedResponses []string `json:"generated_responses,omitempty"`

	// The last inputs from the user in the conversation, after the model has run.
	PastUserInputs []string `json:"past_user_inputs,omitempty"`
}

Used with ConversationalResponse

type ConversationalParameters 

type ConversationalParameters struct {
	// (Default: None). Integer to define the minimum length in tokens of the output summary.
	MinLength *int `json:"min_length,omitempty"`

	// (Default: None). Integer to define the maximum length in tokens of the output summary.
	MaxLength *int `json:"max_length,omitempty"`

	// (Default: None). Integer to define the top tokens considered within the sample operation to create
	// new text.
	TopK *int `json:"top_k,omitempty"`

	// (Default: None). Float to define the tokens that are within the sample` operation of text generation.
	// Add tokens in the sample for more probable to least probable until the sum of the probabilities is
	// greater than top_p.
	TopP *float64 `json:"top_p,omitempty"`

	// (Default: 1.0). Float (0.0-100.0). The temperature of the sampling operation. 1 means regular sampling,
	// 0 mens top_k=1, 100.0 is getting closer to uniform probability.
	Temperature *float64 `json:"temperature,omitempty"`

	// (Default: None). Float (0.0-100.0). The more a token is used within generation the more it is penalized
	// to not be picked in successive generation passes.
	RepetitionPenalty *float64 `json:"repetitionpenalty,omitempty"`

	// (Default: None). Float (0-120.0). The amount of time in seconds that the query should take maximum.
	// Network can cause some overhead so it will be a soft limit.
	MaxTime *float64 `json:"maxtime,omitempty"`
}

Used with ConversationalRequest

func NewConversationalParameters 

func NewConversationalParameters() *ConversationalParameters

func (*ConversationalParameters) SetMaxLength added in v0.0.1 

func (c *ConversationalParameters) SetMaxLength(maxLength int) *ConversationalParameters

func (*ConversationalParameters) SetMaxTime added in v0.0.1 

func (c *ConversationalParameters) SetMaxTime(maxTime float64) *ConversationalParameters

func (*ConversationalParameters) SetMinLength added in v0.0.1 

func (c *ConversationalParameters) SetMinLength(minLength int) *ConversationalParameters

func (*ConversationalParameters) SetRepetitionPenalty added in v0.0.1 

func (c *ConversationalParameters) SetRepetitionPenalty(penalty float64) *ConversationalParameters

func (*ConversationalParameters) SetTempurature 

func (c *ConversationalParameters) SetTempurature(temperature float64) *ConversationalParameters

func (*ConversationalParameters) SetTopK added in v0.0.1 

func (c *ConversationalParameters) SetTopK(topK int) *ConversationalParameters

func (*ConversationalParameters) SetTopP added in v0.0.1 

func (c *ConversationalParameters) SetTopP(topP float64) *ConversationalParameters

type ConversationalRequest 

type ConversationalRequest struct {
	// (Required)
	Inputs ConverstationalInputs `json:"inputs,omitempty"`

	Parameters ConversationalParameters `json:"parameters,omitempty"`
	Options    Options                  `json:"options,omitempty"`
}

Request structure for the conversational endpoint

type ConversationalResponse 

type ConversationalResponse struct {
	// The answer of the model
	GeneratedText string `json:"generated_text,omitempty"`

	// A facility dictionary to send back for the next input (with the new user input addition).
	Conversation Conversation `json:"conversation,omitempty"`
}

Response structure for the conversational endpoint

func SendConversationalRequest 

func SendConversationalRequest(model string, request *ConversationalRequest) (*ConversationalResponse, error)

type ConverstationalInputs 

type ConverstationalInputs struct {
	// (Required) The last input from the user in the conversation.
	Text string `json:"text,omitempty"`

	// A list of strings corresponding to the earlier replies from the model.
	GeneratedResponses []string `json:"generated_responses,omitempty"`

	// A list of strings corresponding to the earlier replies from the user.
	// Should be of the same length of GeneratedResponses.
	PastUserInputs []string `json:"past_user_inputs,omitempty"`
}

Used with ConversationalRequest

type FillMaskRequest 

type FillMaskRequest struct {
	// (Required) a string to be filled from, must contain the [MASK] token (check model card for exact name of the mask)
	Inputs  []string `json:"inputs,omitempty"`
	Options Options  `json:"options,omitempty"`
}

Request structure for the Fill Mask endpoint

type FillMaskResponse 

type FillMaskResponse struct {
	Masks []*FillMaskResponseEntry
}

Response structure for the Fill Mask endpoint

func SendFillMaskRequest 

func SendFillMaskRequest(model string, request *FillMaskRequest) ([]*FillMaskResponse, error)

type FillMaskResponseEntry 

type FillMaskResponseEntry struct {
	// The actual sequence of tokens that ran against the model (may contain special tokens)
	Sequence string `json:"sequence,omitempty"`

	// The probability for this token.
	Score float64 `json:"score,omitempty"`

	// The id of the token
	TokenID int `json:"token,omitempty"`

	// The string representation of the token
	TokenStr string `json:"token_str,omitempty"`
}

Used in the FillMaskResponse struct

type ImageClassificationResponse added in v1.1.0 

type ImageClassificationResponse struct {
	// The label for the class (model specific)
	Label string `json:"label,omitempty"`

	// A float that represents how likely it is that the image file belongs to this class.
	Score float64 `json:"score,omitempty"`
}

func SendImageClassificationRequest added in v1.1.0 

func SendImageClassificationRequest(model, imageFile string) ([]*ImageClassificationResponse, error)

type ImageSegmentationResponse added in v1.1.0 

type ImageSegmentationResponse struct {
	// The label for the class (model specific) of a segment.
	Label string `json:"label,omitempty"`

	// A float that represents how likely it is that the segment belongs to the given class.
	Score float64 `json:"score,omitempty"`

	// A str (base64 str of a single channel black-and-white img) representing the mask of a segment.
	Mask string `json:"mask,omitempty"`
}

func SendImageSegmentationRequest added in v1.1.0 

func SendImageSegmentationRequest(model, imageFile string) ([]*ImageSegmentationResponse, error)

type ObjectBox 

type ObjectBox struct {
	XMin int `json:"xmin,omitempty"`
	YMin int `json:"ymin,omitempty"`
	XMax int `json:"xmax,omitempty"`
	YMax int `json:"ymax,omitempty"`
}

type ObjectDetectionResponse 

type ObjectDetectionResponse struct {
	// The label for the class (model specific) of a detected object.
	Label string `json:"label,omitempty"`

	// A float that represents how likely it is that the detected object belongs to the given class.
	Score float64 `json:"score,omitempty"`

	// Bounding box of the detected object
	Box ObjectBox
}

func SendObjectDetectionRequest 

func SendObjectDetectionRequest(model, imageFile string) ([]*ObjectDetectionResponse, error)

type Options 

type Options struct {

	// (Default: false). Boolean to use GPU instead of CPU for inference.
	// Requires Startup plan at least.
	UseGPU *bool `json:"use_gpu,omitempty"`

	// (Default: true). There is a cache layer on the inference API to speedup
	// requests we have already seen. Most models can use those results as is
	// as models are deterministic (meaning the results will be the same anyway).
	// However if you use a non deterministic model, you can set this parameter
	// to prevent the caching mechanism from being used resulting in a real new query.
	UseCache *bool `json:"use_cache,omitempty"`

	// (Default: false) If the model is not ready, wait for it instead of receiving 503.
	// It limits the number of requests required to get your inference done. It is advised
	// to only set this flag to true after receiving a 503 error as it will limit hanging
	// in your application to known places.
	WaitForModel *bool `json:"wait_for_model,omitempty"`
}

func NewOptions 

func NewOptions() *Options

func (*Options) SetUseCache 

func (opts *Options) SetUseCache(useCache bool) *Options

func (*Options) SetUseGPU 

func (opts *Options) SetUseGPU(useGPU bool) *Options

func (*Options) SetWaitForModel 

func (opts *Options) SetWaitForModel(waitForModel bool) *Options

type QuestionAnsweringInputs 

type QuestionAnsweringInputs struct {
	// (Required) The question as a string that has an answer within Context.
	Question string `json:"question,omitempty"`

	// (Required) A string that contains the answer to the question
	Context string `json:"context,omitempty"`
}

type QuestionAnsweringRequest 

type QuestionAnsweringRequest struct {
	// (Required)
	Inputs  QuestionAnsweringInputs `json:"inputs,omitempty"`
	Options Options                 `json:"options,omitempty"`
}

Request structure for question answering model

type QuestionAnsweringResponse 

type QuestionAnsweringResponse struct {
	// A string that’s the answer within the Context text.
	Answer string `json:"answer,omitempty"`

	// A float that represents how likely that the answer is correct.
	Score float64 `json:"score,omitempty"`

	// The string index of the start of the answer within Context.
	Start int `json:"start,omitempty"`

	// The string index of the stop of the answer within Context.
	End int `json:"end,omitempty"`
}

Response structure for question answering model

func SendQuestionAnsweringRequest 

func SendQuestionAnsweringRequest(model string, request *QuestionAnsweringRequest) (*QuestionAnsweringResponse, error)

type SentenceSimilarityInputs added in v1.0.0 

type SentenceSimilarityInputs struct {
	// (Required) The string that you wish to compare the other strings with.
	// This can be a phrase, sentence, or longer passage, depending on the
	// model being used.
	SourceSentence string `json:"source_sentence,omitempty"`

	// A list of strings which will be compared against the source_sentence.
	Sentences []string `json:"sentences,omitempty"`
}

type SentenceSimilarityRequest added in v1.0.0 

type SentenceSimilarityRequest struct {
	// (Required) Inputs for the request.
	Inputs  SentenceSimilarityInputs `json:"inputs,omitempty"`
	Options Options                  `json:"options,omitempty"`
}

Request structure for the Sentence Similarity endpoint.

type SentenceSimilarityResponse added in v1.0.0 

type SentenceSimilarityResponse []float64

Response structure from the Sentence Similarity endpoint. The return value is a list of similarity scores, given as floats. Each list entry corresponds to the Inputs.Sentences list entry of the same index.

func SendSentenceSimilarityRequest added in v1.0.0 

func SendSentenceSimilarityRequest(model string, request *SentenceSimilarityRequest) (*SentenceSimilarityResponse, error)

type SpeechRecognitionResponse 

type SpeechRecognitionResponse struct {
	// The string that was recognized within the audio file.
	Text string `json:"text,omitempty"`
}

func SendSpeechRecognitionRequest 

func SendSpeechRecognitionRequest(model, audioFile string) (*SpeechRecognitionResponse, error)

SendSpeechRecognitionRequest takes a model string and a path to an audio file. It reads the file and sends a request to the speech recognition endpoint.

type SummarizationParameters 

type SummarizationParameters struct {
	// (Default: None). Integer to define the minimum length in tokens of the output summary.
	MinLength *int `json:"min_length,omitempty"`

	// (Default: None). Integer to define the maximum length in tokens of the output summary.
	MaxLength *int `json:"max_length,omitempty"`

	// (Default: None). Integer to define the top tokens considered within the sample operation to create
	// new text.
	TopK *int `json:"top_k,omitempty"`

	// (Default: None). Float to define the tokens that are within the sample` operation of text generation.
	// Add tokens in the sample for more probable to least probable until the sum of the probabilities is
	// greater than top_p.
	TopP *float64 `json:"top_p,omitempty"`

	// (Default: 1.0). Float (0.0-100.0). The temperature of the sampling operation. 1 means regular sampling,
	// 0 mens top_k=1, 100.0 is getting closer to uniform probability.
	Temperature *float64 `json:"temperature,omitempty"`

	// (Default: None). Float (0.0-100.0). The more a token is used within generation the more it is penalized
	// to not be picked in successive generation passes.
	RepetitionPenalty *float64 `json:"repetitionpenalty,omitempty"`

	// (Default: None). Float (0-120.0). The amount of time in seconds that the query should take maximum.
	// Network can cause some overhead so it will be a soft limit.
	MaxTime *float64 `json:"maxtime,omitempty"`
}

Used with SummarizationRequest

func NewSummarizationParameters 

func NewSummarizationParameters() *SummarizationParameters

func (*SummarizationParameters) SetMaxLength added in v0.0.1 

func (sp *SummarizationParameters) SetMaxLength(maxLength int) *SummarizationParameters

func (*SummarizationParameters) SetMaxTime added in v0.0.1 

func (sp *SummarizationParameters) SetMaxTime(maxTime float64) *SummarizationParameters

func (*SummarizationParameters) SetMinLength added in v0.0.1 

func (sp *SummarizationParameters) SetMinLength(minLength int) *SummarizationParameters

func (*SummarizationParameters) SetRepetitionPenalty added in v0.0.1 

func (sp *SummarizationParameters) SetRepetitionPenalty(penalty float64) *SummarizationParameters

func (*SummarizationParameters) SetTempurature 

func (sp *SummarizationParameters) SetTempurature(temperature float64) *SummarizationParameters

func (*SummarizationParameters) SetTopK added in v0.0.1 

func (sp *SummarizationParameters) SetTopK(topK int) *SummarizationParameters

func (*SummarizationParameters) SetTopP added in v0.0.1 

func (sp *SummarizationParameters) SetTopP(topP float64) *SummarizationParameters

type SummarizationRequest 

type SummarizationRequest struct {
	// Strings to be summarized
	Inputs     []string                `json:"inputs,omitempty"`
	Parameters SummarizationParameters `json:"parameters,omitempty"`
	Options    Options                 `json:"options,omitempty"`
}

Request structure for the summarization endpoint

type SummarizationResponse 

type SummarizationResponse struct {
	// The summarized input string
	SummaryText string `json:"summary_text,omitempty"`
}

Response structure for the summarization endpoint

func SendSummarizationRequest 

func SendSummarizationRequest(model string, request *SummarizationRequest) ([]*SummarizationResponse, error)

type TableQuestionAnsweringInputs 

type TableQuestionAnsweringInputs struct {
	// (Required) The query in plain text that you want to ask the table
	Query string `json:"query,omitempty"`

	// (Required) A table of data represented as a dict of list where entries
	// are headers and the lists are all the values, all lists must
	// have the same size.
	Table map[string][]string `json:"table,omitempty"`
}

type TableQuestionAnsweringRequest 

type TableQuestionAnsweringRequest struct {
	Inputs  TableQuestionAnsweringInputs `json:"inputs,omitempty"`
	Options Options                      `json:"options,omitempty"`
}

Request structure for table question answering model

type TableQuestionAnsweringResponse 

type TableQuestionAnsweringResponse struct {
	// The plaintext answer
	Answer string `json:"answer,omitempty"`

	// A list of coordinates of the cells references in the answer
	Coordinates [][]int `json:"coordinates,omitempty"`

	// A list of coordinates of the cells contents
	Cells []string `json:"cells,omitempty"`

	// The aggregator used to get the answer
	Aggregator string `json:"aggregator,omitempty"`
}

Response structure for table question answering model

func SendTableQuestionAnsweringRequest 

func SendTableQuestionAnsweringRequest(model string, request *TableQuestionAnsweringRequest) (*TableQuestionAnsweringResponse, error)

type TextClassificationRequest 

type TextClassificationRequest struct {
	// (Required) strings to be classified
	Inputs  []string `json:"inputs,omitempty"`
	Options Options  `json:"options,omitempty"`
}

Request structure for the Text classification endpoint

type TextClassificationResponse 

type TextClassificationResponse struct {
	// HFAPI returns a list of labels and their associated scores for
	// each input.
	Labels []*TextClassificationResponseLabel
}

Response structure for the Text classification endpoint

func SendTextClassificationRequest 

func SendTextClassificationRequest(model string, request *TextClassificationRequest) ([]*TextClassificationResponse, error)

type TextClassificationResponseLabel 

type TextClassificationResponseLabel struct {
	// The label for the class (model specific)
	Name string `json:"label,omitempty"`

	// A float that represents how likely is that the text belongs in this class.
	Score float64 `json:"score,omitempty"`
}

Used in TextClassificationResponse

type TextGenerationParameters 

type TextGenerationParameters struct {
	// (Default: None). Integer to define the top tokens considered within the sample operation to create new text.
	TopK *int `json:"top_k,omitempty"`

	// (Default: None). Float to define the tokens that are within the sample` operation of text generation. Add
	// tokens in the sample for more probable to least probable until the sum of the probabilities is greater
	// than top_p.
	TopP *float64 `json:"top_p,omitempty"`

	// (Default: 1.0). Float (0.0-100.0). The temperature of the sampling operation. 1 means regular sampling,
	// 0 means top_k=1, 100.0 is getting closer to uniform probability.
	Temperature *float64 `json:"temperature,omitempty"`

	// (Default: None). Float (0.0-100.0). The more a token is used within generation the more it is penalized
	// to not be picked in successive generation passes.
	RepetitionPenalty *float64 `json:"repetition_penalty,omitempty"`

	// (Default: None). Int (0-250). The amount of new tokens to be generated, this does not include the input
	// length it is a estimate of the size of generated text you want. Each new tokens slows down the request,
	// so look for balance between response times and length of text generated.
	MaxNewTokens *int `json:"max_new_tokens,omitempty"`

	// (Default: None). Float (0-120.0). The amount of time in seconds that the query should take maximum.
	// Network can cause some overhead so it will be a soft limit. Use that in combination with max_new_tokens
	// for best results.
	MaxTime *float64 `json:"max_time,omitempty"`

	// (Default: True). Bool. If set to False, the return results will not contain the original query making it
	// easier for prompting.
	ReturnFullText *bool `json:"return_full_text,omitempty"`

	// (Default: 1). Integer. The number of proposition you want to be returned.
	NumReturnSequences *int `json:"num_return_sequences,omitempty"`
}

func NewTextGenerationParameters 

func NewTextGenerationParameters() *TextGenerationParameters

func (*TextGenerationParameters) SetMaxNewTokens 

func (params *TextGenerationParameters) SetMaxNewTokens(maxNewTokens int) *TextGenerationParameters

func (*TextGenerationParameters) SetMaxTime 

func (params *TextGenerationParameters) SetMaxTime(maxTime float64) *TextGenerationParameters

func (*TextGenerationParameters) SetNumReturnSequences 

func (params *TextGenerationParameters) SetNumReturnSequences(numReturnSequences int) *TextGenerationParameters

func (*TextGenerationParameters) SetRepetitionPenaly 

func (params *TextGenerationParameters) SetRepetitionPenaly(penalty float64) *TextGenerationParameters

func (*TextGenerationParameters) SetReturnFullText 

func (params *TextGenerationParameters) SetReturnFullText(returnFullText bool) *TextGenerationParameters

func (*TextGenerationParameters) SetTempurature 

func (params *TextGenerationParameters) SetTempurature(temp float64) *TextGenerationParameters

func (*TextGenerationParameters) SetTopK 

func (params *TextGenerationParameters) SetTopK(topK int) *TextGenerationParameters

func (*TextGenerationParameters) SetTopP 

func (params *TextGenerationParameters) SetTopP(topP float64) *TextGenerationParameters

type TextGenerationRequest 

type TextGenerationRequest struct {
	// (Required) a string to be generated from
	Inputs     []string                 `json:"inputs,omitempty"`
	Parameters TextGenerationParameters `json:"parameters,omitempty"`
	Options    Options                  `json:"options,omitempty"`
}

type TextGenerationResponse 

type TextGenerationResponse struct {
	// A list of generated texts. The length of this list is the value of
	// NumReturnSequences in the request.
	GeneratedTexts []string
}

func SendTextGenerationRequest 

func SendTextGenerationRequest(model string, request *TextGenerationRequest) ([]*TextGenerationResponse, error)

type TextToImageRequest added in v1.2.0 

type TextToImageRequest struct {
	// The prompt or prompts to guide the image generation.
	Inputs     string                       `json:"inputs,omitempty"`
	Options    Options                      `json:"options,omitempty"`
	Parameters TextToImageRequestParameters `json:"parameters,omitempty"`
}

Request structure for text-to-image model

type TextToImageRequestParameters added in v1.2.2 

type TextToImageRequestParameters struct {
	// The prompt or prompts not to guide the image generation.
	// Ignored when not using guidance (i.e., ignored if guidance_scale is less than 1).
	NegativePrompt string `json:"negative_prompt,omitempty"`
	// The height in pixels of the generated image.
	Height int64 `json:"height,omitempty"`
	// The width in pixels of the generated image.
	Width int64 `json:"width,omitempty"`
	// The number of denoising steps. More denoising steps usually lead to a higher quality
	// image at the expense of slower inference. Defaults to 50.
	NumInferenceSteps int64 `json:"num_inference_steps,omitempty"`
	// Higher guidance scale encourages to generate images that are closely linked to the text
	// input, usually at the expense of lower image quality. Defaults to 7.5.
	GuidanceScale float64 `json:"guidance_scale,omitempty"`
}

type TokenClassificationParameters 

type TokenClassificationParameters struct {
	// (Default: simple)
	AggregationStrategy *AggregationStrategy `json:"aggregation_strategy,omitempty"`
}

func NewTokenClassificationParameters 

func NewTokenClassificationParameters() *TokenClassificationParameters

func (*TokenClassificationParameters) SetAggregationStrategy 

func (params *TokenClassificationParameters) SetAggregationStrategy(aggregationStrategy AggregationStrategy) *TokenClassificationParameters

type TokenClassificationRequest 

type TokenClassificationRequest struct {
	// (Required) strings to be classified
	Inputs     []string                      `json:"inputs,omitempty"`
	Parameters TokenClassificationParameters `json:"parameters,omitempty"`
	Options    Options                       `json:"options,omitempty"`
}

Request structure for the token classification endpoint

type TokenClassificationResponse 

type TokenClassificationResponse struct {
	Entities []*TokenClassificationResponseEntity
}

Response structure for the token classification endpoint

func SendTokenClassificationRequest 

func SendTokenClassificationRequest(model string, request *TokenClassificationRequest) ([]*TokenClassificationResponse, error)

type TokenClassificationResponseEntity 

type TokenClassificationResponseEntity struct {
	// The type for the entity being recognized (model specific).
	Label string `json:"entity_group,omitempty"`

	// How likely the entity was recognized.
	Score float64 `json:"score,omitempty"`

	// The string that was captured
	Entity string `json:"word,omitempty"`

	// The offset stringwise where the answer is located. Useful to disambiguate if Entity occurs multiple times.
	Start int `json:"start,omitempty"`

	// The offset stringwise where the answer is located. Useful to disambiguate if Entity occurs multiple times.
	End int `json:"end,omitempty"`
}

type TranslationRequest 

type TranslationRequest struct {
	// (Required) a string to be translated in the original languages
	Inputs []string `json:"inputs,omitempty"`

	Options Options `json:"options,omitempty"`
}

Request structure for the Translation endpoint

type TranslationResponse 

type TranslationResponse struct {
	// The translated Input string
	TranslationText string `json:"translation_text,omitempty"`
}

Response structure from the Translation endpoint

func SendTranslationRequest 

func SendTranslationRequest(model string, request *TranslationRequest) ([]*TranslationResponse, error)

type ZeroShotParameters 

type ZeroShotParameters struct {
	// (Required) A list of strings that are potential classes for inputs. Max 10 candidate_labels,
	// for more, simply run multiple requests, results are going to be misleading if using
	// too many candidate_labels anyway. If you want to keep the exact same, you can
	// simply run multi_label=True and do the scaling on your end.
	CandidateLabels []string `json:"candidate_labels,omitempty"`

	// (Default: false) Boolean that is set to True if classes can overlap
	MultiLabel *bool `json:"multi_label,omitempty"`
}

Used with ZeroShotRequest

func (*ZeroShotParameters) SetMultiLabel 

func (zsp *ZeroShotParameters) SetMultiLabel(multiLabel bool) *ZeroShotParameters

type ZeroShotRequest 

type ZeroShotRequest struct {
	// (Required) Input or Inputs are required request fields
	Inputs []string `json:"inputs,omitempty"`

	// (Required)
	Parameters ZeroShotParameters `json:"parameters,omitempty"`

	Options Options `json:"options,omitempty"`
}

Request structure for the Zero-shot classification endpoint.

One of the following fields is required: 

Input
Inputs

type ZeroShotResponse 

type ZeroShotResponse struct {
	// The string sent as an input
	Sequence string `json:"sequence,omitempty"`

	// The list of labels sent in the request, sorted in descending order
	// by probability that the input corresponds to the to the label.
	Labels []string `json:"labels,omitempty"`

	// a list of floats that correspond the the probability of label, in the same order as labels.
	Scores []float64 `json:"scores,omitempty"`
}

Response structure from the Zero-shot classification endpoint.

func SendZeroShotRequest 

func SendZeroShotRequest(model string, request *ZeroShotRequest) ([]*ZeroShotResponse, error)

Source Files

View all Source files

Directories

Path Synopsis
examples
audio_classification
conversational
fill_mask
image_classification
image_segmentation
object_detection
question_answering
sentence_similarity
speech_recognition
summarization
table_question_answering
text_classification
text_generation
text_to_image
token_classification
translation
zeroshot

Jump to

Keyboard shortcuts

? : This menu
/ : Search site
f or F : Jump to
y or Y : Canonical URL
go.dev uses cookies from Google to deliver and enhance the quality of its services and to analyze traffic. Learn more.