Generate a note asynchronously
POST/digest_async
Digests a list of transcript items and produces a structured clinical note.
Request
- application/json
Body
required
- Array [
- ]
- Array [
- ]
Possible values: [note
]
Specifies which items you want us to send you back. In other words, which feature(s) you want to use, for now only note generation is available.
Possible values: [fr
, en
, en-US
, en-GB
, fr-FR
, es-ES
, es-MX
]
Language of the given transcript and the desired note ('fr' and 'en' are deprecated, and correspond to 'fr-FR' and 'en-US' respectively. Generating a note in 'es-ES' and 'es-MX' is not supported and will be soon removed).
transcript_items object[]required
The transcript from which to generate the note.
You don't need to specify each item's start or end time, but make sure they are sorted. In fact, due to its asynchronous nature, our real-time transcription API does not guarantee the order. Thus, before calling this note-generation API please filter-out non-final items and sort them by start_offset_ms
.
The transcribed text.
Possible values: [doctor
, patient
, unspecified
]
Who said the text in this transcript item.
Possible values: [highest_quality
, fastest
]
Choose a generation mode:
• highest_quality
: generates very high quality notes, might take up to one minute;
• fastest
: quicker note generation (few seconds), but might not give the best possible output.
Default is highest_quality
.
Possible values: [auto
, paragraphs
, bullet_points
]
Choose a desired style for note sections:
• paragraphs
: Prioritizes generating paragraphs;
• bullet_points
: Prioritizes structuring content using bullet points.
• auto
: Automatically picks the most natural formatting option.
Default is auto
.
Default value: false
Flag to structure the content of the note sections according to distinct clinical problems or topics addressed during the consultation.
When this flag is enabled, the text within some sections of the clinical note is organized into subsections, each corresponding to a specific problem or topic. This format aims to enhance the clarity and organization of the clinical note, making it easier to read and understand the different issues discussed during the consultation.
Important: Currently, the application of this flag is limited to the HISTORY_OF_PRESENT_ILLNESS
and SOAP_SUBJECTIVE
sections and is only effective when the language is set to English (US or GB).
Possible values: [GENERAL_MEDICINE
, GENERAL_MEDICINE_AP_MERGED
, CARDIOLOGY
, PSYCHIATRY
, DIET
, PSYCHOLOGY
, SOAP
, GENERAL_MEDICINE_WCC
, SOAP_WCC
, GENERAL_MEDICINE_EMERGENCY
, SOAP_EMERGENCY
]
The desired template of the generated note.
Some templates are only available in specific languages. Check Note template for details.
note object
Optional initial Note to be enhanced using the new transcript_items
.
This is useful if you generate notes gradually to avoid accumulating a very long transcript items list.
Typically, this will be the last note Nabla generated for you along with the new transcript_items
that did not serve for its generation.
Important: This is expected to be a recent (up to few-hours old) Nabla-generated note. If the note is too old or altered, you will get an error.
sections object[]required
Sections of the note.
A key identifying a section of a note. The set of possible keys depend on the template that is used. Check Note template for possible values.
The section title.
Content of the note section (required).
Possible values: <= 700 characters
Some contextual information that will be used to generate the note (for example name, gender, age, pronouns, medical history) [BETA].
Once we are done processing the input and generating the note, we will call you back with a 'POST' on this URL and a Json body respecting exactly the same schema as the response of the synchronous equivalent endpoint (i.e. /copilot/digest
).
Possible values: <= 128 characters
An optional unique client-made id for this request. When specified, this id is included in the Json payload that will be sent asynchronously. This can help clients both guarantee idempotency and correlate asynchronous responses with their requests. Note: this id must be different for every request. It is recommended to use a randomly generated UUID.
Responses
- 200
- 299
Request received and processing started.
- application/json
- Schema
- Example (from schema)
Schema
The id of the request you just created.
The provided client_request_id
.
{
"request_id": "98FCE1EF-DBCA-41EF-8BC7-4D1621AC07C6",
"client_request_id": "string"
}
Here's the schema of the Json payload that will be sent asynchronously to the URL you provided. (299 is not a possible response code — only a way here to document the asynchronous payload schema).
- application/json
- Schema
Schema
- success
- error
- Array [
- ]
- Array [
- ]
The id of the async request.
The client_request_id
provided in the request.
note objectrequired
The generated note.
sections object[]required
Content of the note structured in multiple sections.
A key identifying a section of a note. The set of possible keys depend on the template that is used. Check Note template for possible values.
The section title.
Content of the note section.
suggested_dot_phrases object[]
A collection of Dot Phrases that were successfully matched to the encounter's transcript, given the Dot Phrases defined on the calling user. Will be null in the context of a Server API call (i.e. no calling user). This functionality enriches the generated note by expanding concise key sentences (triggers) into a more detailed format following the given Dot Phrase definition. Thus, enhancing the depth and utility of the note and facilitating a comprehensive review of patient assessments in a structured and conventional manner.
ID of the original Dot Phrase that resulted in the current suggestion. Can be null or not present if the related Dot Phrase is not a resource stored on the calling user.
note_section object
The key and the title of the section in the note where this Dot Phrase is suggested to go. There are three possible scenarios:
• No suggested section: Given the Dot Phrase's content, we found no appropriate section to suggest. You should decide for a default (for instance: any kind of "free text" area you might have).
• Suggested section already present in the note: We recommend you append the Dot Phrase's suggested text_to_insert
to the section's content.
• Suggested section is not present in the note: Add a new section to the note with the provided key and title and use the Dot Phrase's suggested text_to_insert
as the section's content.
Section key.
Section title.
The actual suggested content, to be inserted in the corresponding note section.
The id of the async request.
The client_request_id
provided in the request.