Sapling.ai (Independent Publisher) (Preview)
Sapling is building the AI assistant for business communication, one that helps teams communicate more efficiently and effectively with their clients, across diverse use cases.
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 | Fördős András |
| [email protected] |
| Connector Metadata | |
|---|---|
| Publisher | Fördős András |
| Website | https://sapling.ai/docs/ |
| Privacy policy | https://sapling.ai/privacy |
| Categories | AI;Productivity |
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 Key | securestring | The API Key for this api | True |
Throttling Limits
| Name | Calls | Renewal Period |
|---|---|---|
| API calls per connection | 100 | 60 seconds |
Actions
| Autocomplete |
predictions of the next few characters or words given the current context in a particular editable. |
| Detect AI |
The endpoint computes the likelihood a piece of text was AI generated. |
| Medical spellcheck |
Use spellcheck only for medical terms. |
| Spellcheck |
Perform only requires spellcheck on your text instead of a full grammar edit. |
| Statistics |
Computes simple statistics for a given text document, like word and sentence counts and Flesch-Kincaid score. |
Autocomplete
predictions of the next few characters or words given the current context in a particular editable.
Parameters
| Name | Key | Required | Type | Description |
|---|---|---|---|---|
|
Query
|
query | True | string |
Text that should be autocompleted. |
|
Session ID
|
session_id | True | string |
Unique name or UUID of document or portion of text that is being checked. |
Returns
| Name | Path | Type | Description |
|---|---|---|---|
|
Hash
|
hash | string |
Opaque ID of completion for use with accept event. |
|
Output
|
output | string |
Predicted completion. For example, for the query 'Hi, how are', the predicted completion should be 'you' (with a leading space). |
|
Query
|
query | string |
Actual query used to generate completion (may be a truncated version of request query). |
Detect AI
The endpoint computes the likelihood a piece of text was AI generated.
Parameters
| Name | Key | Required | Type | Description |
|---|---|---|---|---|
|
Text
|
text | True | string |
Text to run detection on. The limit is currently 8000 characters. |
|
Sent scores
|
sent_scores | boolean |
Whether to return sentence scores. If speed is of the essence, you can disable this setting. |
Returns
| Name | Path | Type | Description |
|---|---|---|---|
|
Hash
|
hash | string |
Opaque ID of completion for use with accept event. |
|
Score
|
score | float |
Between 0 and 1, with 0 indicating the maximum confidence that the text is human-written. |
|
Sentence scores
|
sentence_scores | array of object |
The per-sentence scores may not correlate with the overall score, as they're computed using different method. |
|
Score
|
sentence_scores.score | float |
Calculated score for sentence. |
|
Sentence
|
sentence_scores.sentence | string |
Sentence for which score is calculated. |
|
Text
|
text | string |
The full text, that is under analysis. |
|
Truncated
|
truncated | boolean |
Indication, whether response is truncated. |
Medical spellcheck
Use spellcheck only for medical terms.
Parameters
| Name | Key | Required | Type | Description |
|---|---|---|---|---|
|
Text
|
text | True | string |
Text to process for edits. |
|
Minimum length
|
min_length | True | integer |
Minimum character length of words to suggest corrections for. Setting this too low will result in much higher false positives. |
|
Session ID
|
session_id | True | string |
Unique name or UUID of document or portion of text that is being checked. |
|
Multiple edits
|
multiple_edits | boolean |
If true, will return candidates field containing list of other potential corrections for each error. |
|
|
Neural spellcheck
|
neural_spellcheck | boolean |
If true, endpoint backend will use more powerful neural (GPT-style) model to make spelling suggestions. |
|
|
Language
|
lang | string |
Language code of the text, for example 'en'. |
Returns
| Name | Path | Type | Description |
|---|---|---|---|
|
edits
|
edits | array of EditDef |
Spellcheck
Perform only requires spellcheck on your text instead of a full grammar edit.
Parameters
| Name | Key | Required | Type | Description |
|---|---|---|---|---|
|
Text
|
text | True | string |
Text to process for edits. |
|
Minimum length
|
min_length | True | integer |
Minimum character length of words to suggest corrections for. Setting this too low will result in much higher false positives. |
|
Session ID
|
session_id | True | string |
Unique name or UUID of document or portion of text that is being checked. |
|
Multiple edits
|
multiple_edits | boolean |
If true, will return candidates field containing list of other potential corrections for each error. |
|
|
Neural spellcheck
|
neural_spellcheck | boolean |
If true, endpoint backend will use more powerful neural (GPT-style) model to make spelling suggestions. |
|
|
Language
|
lang | string |
Language code of the text, for example 'en'. |
Returns
| Name | Path | Type | Description |
|---|---|---|---|
|
edits
|
edits | array of EditDef |
Statistics
Computes simple statistics for a given text document, like word and sentence counts and Flesch-Kincaid score.
Parameters
| Name | Key | Required | Type | Description |
|---|---|---|---|---|
|
Text
|
text | True | string |
Text to compute statistics for. |
|
Session ID
|
session_id | True | string |
Unique name or UUID of document or portion of text that is being processed. |
Returns
| Name | Path | Type | Description |
|---|---|---|---|
|
Characters
|
chars | integer |
Number of characters. |
|
Readability
|
readability | float |
Flesch-Kincaid readability grade |
|
Reading time (min)
|
reading_time_min | integer |
Readin time - minutes. |
|
Reading time (sec)
|
reading_time_sec | float |
Reading time - seconds |
|
Sentences
|
sentences | integer |
Number of sentences. |
|
Words
|
words | integer |
Number of words. |
Definitions
EditDef
Grammar, spelling, or stylistic edits for text, based on action chosen.
| Name | Path | Type | Description |
|---|---|---|---|
|
End
|
end | integer |
Offset of edit end relative to sentence. |
|
ID
|
id | string |
Opaque edit id, used to give feedback. |
|
Replacement
|
replacement | string |
Suggested replacement. |
|
Sentence
|
sentence | string |
Unedited sentence. |
|
Sentence start
|
sentence_start | integer |
Offset of sentence from start of text. |
|
Start
|
start | integer |
Offset of edit start relative to sentence. |
|
Error type
|
error_type | string |
Error type, see 'Error Categories'. |
|
General error type
|
general_error_type | string |
See 'Error Categories' on the website. |