다음을 통해 공유


Hugging Face (Independent Publisher)

We're on a journey to advance and democratize artificial intelligence through open source and open science. Hugging Face is most notable for its Transformers library built for natural language processing applications and its platform that allows users to share machine learning models and datasets.

This connector is available in the following products and regions:

Service Class Regions
Logic Apps Standard All Logic Apps regions except the following:
     -   Azure Government regions
     -   Azure China regions
     -   US Department of Defense (DoD)
Power Automate Premium All Power Automate regions except the following:
     -   US Government (GCC)
     -   US Government (GCC High)
     -   China Cloud operated by 21Vianet
     -   US Department of Defense (DoD)
Power Apps Premium All Power Apps regions except the following:
     -   US Government (GCC)
     -   US Government (GCC High)
     -   China Cloud operated by 21Vianet
     -   US Department of Defense (DoD)
Contact
Name Troy Taylor
URL https://www.hitachisolutions.com
Email ttaylor@hitachisolutions.com
Connector Metadata
Publisher Troy Taylor
Website https://huggingface.co/
Privacy policy https://huggingface.co/privacy
Categories AI

Creating a connection

The connector supports the following authentication types:

Default Parameters for creating connection. All regions Not shareable

Default

Applicable: All regions

Parameters for creating connection.

This is not shareable connection. If the power app is shared with another user, another user will be prompted to create new connection explicitly.

Name Type Description Required
API Token (in the form 'Bearer yourToken') securestring The API Token (in the form 'Bearer yourToken') for this api True

Throttling Limits

Name Calls Renewal Period
API calls per connection 100 60 seconds

Actions

Run a conversational task

Retrieve a generated response to a conversation.

Run a fill mask task

Retrieve a list of possible missing words.

Run a model by ID

Retrieve the response for your requested input.

Run a question answering task

Retrieve an answer to your question.

Run a sentence similarity task

Calculate the semantic similarity between one text and a list of other sentences by comparing their embeddings.

Run a summarization task

Retrieve a shorter text summary.

Run a text classification task

Retrieves the likelihood of classes of an input for sentiment-analysis.

Run a text generation task

Retrieve a continuation of text from a prompt.

Run a token classification task

Retrieve sentence parsing keywords contained within the text.

Run a zero-shot classification task

Retrieve the results from a passed sentence/paragraph and the possible labels for that sentence.

Run an English to German translation task

Retrieves translated text into German.

Run a conversational task

Retrieve a generated response to a conversation.

Parameters

Name Key Required Type Description
Past User Inputs
past_user_inputs array of string

The past user inputs.

Generated Responses
generated_responses array of string

The generated responses.

Text
text True string

The text.

Min Length
min_length integer

The minimum length.

Max Length
max_length integer

The max length.

Top Tokens
top_k integer

The top tokens considered.

Top Probably
top_p integer

The top probably tokens.

Temperature
temperature float

The temperature.

Repetition Penalty
repetition_penalty float

The repetition penalty.

Max Time
max_time float

The max time.

Use Cache
use_cache boolean

Whether to use cache.

Wait For Model
wait_for_model boolean

Whether to wait for model.

Returns

Name Path Type Description
Generated Text
generated_text string

The generated text.

Past User Inputs
conversation.past_user_inputs array of string

The past user inputs.

Generated Responses
conversation.generated_responses array of string

The generated responses.

Run a fill mask task

Retrieve a list of possible missing words.

Parameters

Name Key Required Type Description
Inputs
inputs True string

The inputs.

Use Cache
use_cache boolean

Whether to use cache.

Wait For Model
wait_for_model boolean

Whether to wait for model.

Returns

Name Path Type Description
array of object
Score
score float

The score.

Token
token integer

The token.

Token String
token_str string

The token string.

Sequence
sequence string

The sequence.

Run a model by ID

Retrieve the response for your requested input.

Parameters

Name Key Required Type Description
Model ID
model_id True string

The model identifier.

Inputs
inputs True string

The inputs.

Query
query string

The query.

Use Cache
use_cache boolean

Whether to use cache.

Wait For Model
wait_for_model boolean

Whether to wait for model.

Returns

The response object.

Response
object

Run a question answering task

Retrieve an answer to your question.

Parameters

Name Key Required Type Description
Question
question True string

The question.

Context
context True string

The context.

Returns

Name Path Type Description
Score
score float

The score.

Start
start integer

The start.

End
end integer

The end.

Answer
answer string

The answer.

Run a sentence similarity task

Calculate the semantic similarity between one text and a list of other sentences by comparing their embeddings.

Parameters

Name Key Required Type Description
Source Sentence
source_sentence True string

The source sentence.

Sentences
sentences True array of string

The sentences.

Use Cache
use_cache boolean

Whether to use cache.

Wait For Model
wait_for_model boolean

Whether to wait for model.

Returns

Name Path Type Description
array of float

Run a summarization task

Retrieve a shorter text summary.

Parameters

Name Key Required Type Description
Inputs
inputs string

The inputs.

Do Sample
do_sample boolean

Whether to do sample.

Min Length
min_length integer

The minimum length.

Max Length
max_length integer

The max length.

Top Tokens
top_k integer

The top tokens considered.

Top Probably
top_p integer

The top probably tokens.

Temperature
temperature float

The temperature.

Repetition Penalty
repetition_penalty float

The repetition penalty.

Max Time
max_time float

The max time.

Use Cache
use_cache boolean

Whether to use cache.

Wait For Model
wait_for_model boolean

Whether to wait for model.

Returns

Name Path Type Description
array of object
Summary Text
summary_text string

The summary text.

Run a text classification task

Retrieves the likelihood of classes of an input for sentiment-analysis.

Parameters

Name Key Required Type Description
Inputs
inputs True string

The inputs.

Use Cache
use_cache boolean

Whether to use cache.

Wait For Model
wait_for_model boolean

Whether to wait for model.

Returns

Name Path Type Description
array of array
items
array of object
Label
label string

The label.

Score
score float

The score.

Run a text generation task

Retrieve a continuation of text from a prompt.

Parameters

Name Key Required Type Description
Inputs
inputs string

The inputs.

Do Sample
do_sample boolean

Whether to do sample.

Min Length
min_length integer

The minimum length.

Max Length
max_length integer

The max length.

Top Tokens
top_k integer

The top tokens considered.

Top Probably
top_p integer

The top probably tokens.

Temperature
temperature float

The temperature.

Repetition Penalty
repetition_penalty float

The repetition penalty.

Max Time
max_time float

The max time.

Use Cache
use_cache boolean

Whether to use cache.

Wait For Model
wait_for_model boolean

Whether to wait for model.

Returns

Name Path Type Description
array of object
Generated Text
generated_text string

The generated text.

Run a token classification task

Retrieve sentence parsing keywords contained within the text.

Parameters

Name Key Required Type Description
Inputs
inputs True string

The inputs.

Aggregation Strategy
aggregation_strategy string

The aggregation strategy.

Use Cache
use_cache boolean

Whether to use cache.

Wait For Model
wait_for_model boolean

Whether to wait for model.

Returns

Name Path Type Description
array of object
Entity Group
entity_group string

The entity group.

Score
score float

The score.

Word
word string

The word.

Start
start integer

The start.

End
end integer

The end.

Run a zero-shot classification task

Retrieve the results from a passed sentence/paragraph and the possible labels for that sentence.

Parameters

Name Key Required Type Description
Inputs
inputs string

The inputs.

Candidate Labels
candidate_labels array of string

The candidate labels.

Multi Label
multi_label boolean

Whether multi label.

Use Cache
use_cache boolean

Whether to use cache.

Wait For Model
wait_for_model boolean

Whether to wait for model.

Returns

Name Path Type Description
Sequence
sequence string

The sequence.

Labels
labels array of string

The labels

Scores
scores array of float

The scores.

Run an English to German translation task

Retrieves translated text into German.

Parameters

Name Key Required Type Description
Inputs
inputs True string

The inputs.

Use Cache
use_cache boolean

Whether to use cache.

Wait For Model
wait_for_model boolean

Whether to wait for model.

Returns

Name Path Type Description
array of object
Translation Text
translation_text string

The translation text.

Definitions

object

This is the type 'object'.