Recognize Text

lexv2_runtime.recognize_text
ActionAmazon Web Servicesconnection required

Calls the AWS lexv2_runtime API (SigV4).

Sends user input to Amazon Lex V2.

Connection

Required
Yes — the node will not save without one
Auth type
API key
Providers
Amazon Lex Runtime V2
Secret shape
{"access_key_id", "secret_access_key"}
Config it needs
region
Resolved by
config.connection_id, else node.connection_id

Configuration

6 fields, 5 required. A dotted path is a nested object and name[] an array of objects — the editor renders the same tree.

FieldTypeRequiredDefaultConstraintsExample
region
AWS region (overrides the connection).
stringNo———
bot_id
The identifier of the bot that processes the request.
stringYes———
bot_alias_id
The alias identifier in use for the bot that processes the request.
stringYes———
locale_id
The locale where the session is in use.
stringYes———
session_id
The identifier of the user session that is having the conversation.
stringYes———
request
Request body as JSON — this operation takes a structured request.
objectYes———

Output

One shape.

result

FieldTypeExample
messages
array—
sessionState
object—
interpretations
array—
requestAttributes
object—
{
  "interpretations": [],
  "messages": [],
  "requestAttributes": {},
  "sessionState": {}
}

Related Amazon Lex Runtime V2 nodes

See Recognize Text run in a workflow.

In a technical demo we add the Amazon Lex Runtime V2 connection, drop the node on the canvas and let Workflow Health pre-flight it before the first real run.