riva/proto/riva_nlp.proto
riva/proto/riva_nlp.proto#
-
service RivaLanguageUnderstanding
- rpc TextClassResponse ClassifyText(TextClassRequest)
ClassifyText takes as input an input/query string and parameters related to the requested model to use to evaluate the text. The service evaluates the text with the requested model, and returns one or more classifications.
- rpc TokenClassResponse ClassifyTokens(TokenClassRequest)
ClassifyTokens takes as input either a string or list of tokens and parameters related to which model to use. The service evaluates the text with the requested model, performing additional tokenization if necessary, and returns one or more class labels per token.
- rpc TextTransformResponse TransformText(TextTransformRequest)
TransformText takes an input/query string and parameters related to the requested model and returns another string. The behavior of the function is defined entirely by the underlying model and may be used for tasks like translation, adding punctuation, augment the input directly, etc.
- rpc TokenClassResponse AnalyzeEntities(AnalyzeEntitiesRequest)
AnalyzeEntities accepts an input string and returns all named entities within the text, as well as a category and likelihood.
- rpc AnalyzeIntentResponse AnalyzeIntent(AnalyzeIntentRequest)
AnalyzeIntent accepts an input string and returns the most likely intent as well as slots relevant to that intent.
The model requires that a valid “domain” be passed in, and optionally supports including a previous intent classification result to provide context for the model.
- rpc TextTransformResponse PunctuateText(TextTransformRequest)
PunctuateText takes text with no- or limited- punctuation and returns the same text with corrected punctuation and capitalization.
- rpc NaturalQueryResponse NaturalQuery(NaturalQueryRequest)
NaturalQuery is a search function that enables querying one or more documents or contexts with a query that is written in natural language.
- rpc RivaNLPConfigResponse GetRivaNLPConfig(RivaNLPConfigRequest)
Enables clients to request the configuration of the current ASR service, or a specific model within the service.
-
message AnalyzeEntitiesOptions
AnalyzeEntitiesOptions is an optional configuration message to be sent as part of an AnalyzeEntitiesRequest with query metadata
-
string lang
-
string lang
Deprecated. Optional language field. Assumed to be “en-US” if not specified.
-
message AnalyzeEntitiesRequest
AnalyzeEntitiesRequest is the input message for the AnalyzeEntities service
-
string query
-
string query
Deprecated. The string to analyze for intent and slots
- AnalyzeEntitiesOptions options
Deprecated. Optional configuration for the request, including providing context from previous turns and hardcoding a domain/language
- nvidia.riva.RequestId id
Deprecated. The ID to be associated with the request. If provided, this will be returned in the corresponding response.
-
message AnalyzeIntentContext
AnalyzeIntentContext is reserved for future use when we may send context back in a a variety of different formats (including raw neural network hidden states)
Reserved for future use
-
message AnalyzeIntentOptions
AnalyzeIntentOptions is an optional configuration message to be sent as part of an AnalyzeIntentRequest with query metadata
-
string previous_intent
-
string previous_intent
Deprecated.
- AnalyzeIntentContext vectors
Deprecated.
- string domain
Deprecated. Optional domain field. Domain must be supported otherwise an error will be returned. If left blank, a domain detector will be run first and then the query routed to the appropriate intent classifier (if it exists)
- string lang
Deprecated. Optional language field. Assumed to be “en-US” if not specified.
-
message AnalyzeIntentRequest
AnalyzeIntentRequest is the input message for the AnalyzeIntent service
-
string query
-
string query
Deprecated. The string to analyze for intent and slots
- AnalyzeIntentOptions options
Deprecated. Optional configuration for the request, including providing context from previous turns and hardcoding a domain/language
- nvidia.riva.RequestId id
Deprecated. The ID to be associated with the request. If provided, this will be returned in the corresponding response.
-
message AnalyzeIntentResponse
AnalyzeIntentResponse is returned by the AnalyzeIntent service, and includes information related to the query’s intent, (optionally) slot data, and its domain.
-
Classification intent
-
Classification intent
Deprecated. Intent classification result, including the label and score
- TokenClassValue slots(repeated)
Deprecated. List of tokens explicitly marked as filling a slot relevant to the intent, where the tokens may not exactly match the input (based on the recombined values after tokenization)
- string domain_str
Deprecated. Returns the inferred domain for the query if not hardcoded in the request. In the case where the domain was hardcoded in AnalyzeIntentRequest, the returned domain is an exact match to the request. In the case where no domain matches the query, intent and slots will be unset.
DEPRECATED, use Classification domain field.
- Classification domain
Deprecated. Returns the inferred domain for the query if not hardcoded in the request. In the case where the domain was hardcoded in AnalyzeIntentRequest, the returned domain is an exact match to the request. In the case where no domain matches the query, intent and slots will be unset.
- nvidia.riva.RequestId id
Deprecated. The ID associated with the request
-
message Classification
Classification messages return a class name and corresponding score
-
string class_name
-
string class_name
Deprecated.
- float score
Deprecated.
-
message ClassificationResult
ClassificationResults contain zero or more Classification messages If the number of Classifications is > 1, top_n > 1 must have been specified.
-
Classification labels(repeated)
-
Classification labels(repeated)
Deprecated.
-
message NLPModelParams
NLPModelParams is a metadata message that is included in every request message used by the Core NLP Service and is used to specify model characteristics/requirements
-
string model_name
Requested model to use. If specified, this takes preference over language_code.
-
string language_code
Specify language of the supplied text as a [BCP-47](https://www.rfc-editor.org/rfc/bcp/bcp47.txt) language tag. Defaults to “en-US” if not set.
-
string model_name
-
message NaturalQueryRequest
-
string query
-
string query
Deprecated. The natural language query
- uint32 top_n
Deprecated. Maximum number of answers to return for the query. Defaults to 1 if not set.
- string context
Deprecated. Context to search with the above query
- nvidia.riva.RequestId id
Deprecated. The ID to be associated with the request. If provided, this will be returned in the corresponding response.
-
message NaturalQueryResponse
-
NaturalQueryResult results(repeated)
-
NaturalQueryResult results(repeated)
Deprecated.
- nvidia.riva.RequestId id
Deprecated. The ID associated with the request
-
message NaturalQueryResult
-
string answer
-
string answer
Deprecated. text which answers the query
- float score
Deprecated. Score representing confidence in result
-
message RivaNLPConfigRequest
-
string model_name
If model is specified only return config for model, otherwise return all configs.
-
string model_name
-
message RivaNLPConfigResponse
- RivaNLPConfigResponse.Config model_config (repeated)
- message RivaNLPConfigResponse.Config
-
string model_name
- RivaNLPConfigResponse.Config.ParametersEntry parameters (repeated)
-
string model_name
- message RivaNLPConfigResponse.Config.ParametersEntry
-
string key
-
string value
-
string key
-
message Span
Span of a particular result
-
uint32 start
-
uint32 start
Deprecated.
- uint32 end
Deprecated.
-
message TextClassRequest
TextClassRequest is the input message to the ClassifyText service.
-
string text(repeated)
-
string text(repeated)
Deprecated. Each repeated text element is handled independently for handling multiple input strings with a single request
- uint32 top_n
Deprecated. Return the top N classification results for each input. 0 or 1 will return top class, otherwise N. Note: Current disabled.
- NLPModelParams model
Deprecated.
- nvidia.riva.RequestId id
Deprecated. The ID to be associated with the request. If provided, this will be returned in the corresponding response.
-
message TextClassResponse
TextClassResponse is the return message from the ClassifyText service.
-
ClassificationResult results(repeated)
-
ClassificationResult results(repeated)
Deprecated.
- nvidia.riva.RequestId id
Deprecated. The ID associated with the request
-
message TextTransformRequest
TextTransformRequest is a request type intended for services like TransformText which take an arbitrary text input
-
string text(repeated)
Each repeated text element is handled independently for handling multiple input strings with a single request
-
uint32 top_n
-
NLPModelParams model
- nvidia.riva.RequestId id
The ID to be associated with the request. If provided, this will be returned in the corresponding response.
-
string text(repeated)
-
message TextTransformResponse
TextTransformResponse is returned by the TransformText method. Responses are returned in the same order as they were requested.
-
string text(repeated)
- nvidia.riva.RequestId id
The ID associated with the request
-
string text(repeated)
-
message TokenClassRequest
TokenClassRequest is the input message to the ClassifyText service.
-
string text(repeated)
-
string text(repeated)
Deprecated. Each repeated text element is handled independently for handling multiple input strings with a single request
- uint32 top_n
Deprecated. Return the top N classification results for each input. 0 or 1 will return top class, otherwise N. Note: Current disabled.
- NLPModelParams model
Deprecated.
- nvidia.riva.RequestId id
Deprecated. The ID to be associated with the request. If provided, this will be returned in the corresponding response.
-
message TokenClassResponse
TokenClassResponse returns a single TokenClassSequence per input request
-
TokenClassSequence results(repeated)
-
TokenClassSequence results(repeated)
Deprecated.
- nvidia.riva.RequestId id
Deprecated. The ID associated with the request
-
message TokenClassSequence
TokenClassSequence is used for returning a sequence of TokenClassValue objects in the original order of input tokens
-
TokenClassValue results(repeated)
-
TokenClassValue results(repeated)
Deprecated.
-
message TokenClassValue
TokenClassValue is used to correlate an input token with its classification results
-
string token
-
string token
Deprecated.
- Classification label(repeated)
Deprecated.
- Span span(repeated)
Deprecated.