Skip to content
Changelog

Report a bug

Rosette Text Analytics integration: operations for AI agents

Rosette Text Analytics connects to Type.com as an integration. This page lists the 45 operations documented for Claude and Codex in Type.com: 25 read, 20 write.

About Rosette Text Analytics

Rosette Text Analytics is a platform that uses natural language processing, statistical modeling, and machine learning to analyze unstructured and semi-structured text across 364 language-encoding-script combinations, revealing valuable information and actionable data.

Categories: Analytics & Data

How to connect Rosette Text Analytics to Type.com

Access
Organization connection: one shared account for the workspace.

To add the connection, follow the steps in Space connections.

Documented operations

45 operations. Your connection's permissions determine which operations are available. API references describe the vendor surface; they do not expand your connection's credentials or access.

45 operations listed.

Address similarity

  • Read

    Supported languages

    Returns a list of supported languages for the /address-similarity endpoint

  • Write

    Match addresses from input

    Returns the confidence score of matching 2 addresses. You can specify the fields of the addresses to be matched or provide the address as a string.

Categories

  • Read

    Supported languages

    GET /categories/supported-languages

  • Write

    Identify contextual categories in the input.

    Returns a category or categories identified in the input. The possible categories are Tier 1 contextual categories defined in the QAG Taxonomy. The response is the contextual categories identified in the input.

Entities

  • Read

    Returns a list of entity types

    Returns list of supported entity types in the model. If you provide a profileId, it returns the list of entity types in the model used by the profileId. By default, the response lists all entity types by processor type.

  • Read

    Supported languages

    Returns a list of supported languages for the /entities endpoint

  • Read

    Indoc coref supported languages

    Returns a list of supported languages for the indoc coreference server on the /entities endpoint

  • Write

    Extracts entities from a document and links them to a knowledge base.

    Returns each entity extracted from the input. The response is a list of extracted entities.

  • Write

    Add gazetteer entries for entity extraction

    On-premise installations only. Allows you to dynamically add gazetteer entries to your instance. The entities object must be formatted as: {"entities": {"EntityTypeName": ["Value1", "Value2"] } } Example: {"entities": { "COMPANY": ["New Corp", "Best Business"] } }

Language

  • Read

    Supported languages

    Returns a list of supported languages for the /languages endpoint

  • Write

    Identifies the language(s) in a document

    Returns list of candidate languages in order of descending confidence. The response is an ordered list of identified languages, including language and identification confidence, sorted by descending confidence.

Events

  • Read

    Returns event schemas.

    An event schema defines the event types you are extracting. It includes key phrases, roles, role types, and extractors. You can return the list of all models installed in the system, along with the schemas used to create the model.

  • Read

    Supported languages

    Returns a list of supported languages for the /events endpoint

  • Write

    Extracts events from a document.

    Returns each event extracted from the input. The response is a list of event mentions. Each event includes a list of roles as well as any negation cues.

Morphology

  • Read

    Supported languages

    Returns a list of supported languages for the /morphology endpoint

  • Read

    Supported languages

    Returns a list of supported languages for the /morphology endpoint

  • Write

    Runs morphological analysis on input

    Returns morphological analysis of input. The response may include lemmas, part of speech tags, compound word components, and Han readings. Support for specific return types depends on language.

Name deduplication

  • Read

    Supported languages

    Returns a list of supported languages for the /name-deduplication endpoint

  • Write

    Deduplicates names from input

    Returns a list of cluster IDs to be used for deduplication, given a list of names and a score threshold. Position in the cluster ID list corresponds to the position of a name in the input list, and identical cluster IDs signify names that are considered to be duplicates.

Name similarity

  • Read

    Supported languages

    Returns a list of supported languages for the /name-similarity endpoint

  • Write

    Match names from input

    Returns the confidence score of matching 2 names. You must specify the names to be matched.

Name translation

  • Read

    Supported languages

    Returns a list of supported languages for the /name-translation endpoint

  • Write

    Translate names from input

    Returns the translation of a name. You must specify the name to translate and the target language for the translation. You can also include additional parameters. The endpoint returns a single translation; to return multiple candidates use the maximumResults parameter.

Record similarity

  • Read

    Supported languages

    Returns a list of supported languages for the /record-similarity endpoint

  • Write

    Match pairs of records

    Compares records and returns a similarity score for each pair. Set comparisonMethod to control pairing: onetoone (default), oneton (single record on one side compared to every record on the other side), or ntom (every left record compared to every right record).

Relationships

  • Read

    Supported languages

    Returns a list of supported languages for the /relationships endpoint

  • Write

    Extract relationships from input

    Returns the relationships between entities in the input text. The response is a list of extracted relationships.

Semantics similar

  • Read

    Supported languages

    Returns a list of supported languages for the /semantics/similar endpoint

  • Write

    Finds terms similar to the input

    Provides the terms similar to the input. Returns a mapping of each requested language to a list of terms similar to the input

Semantics vector

  • Read

    Supported languages

    Returns a list of supported languages for the /semantics/vector endpoint

  • Write

    Create embeddings from input

    Provides the embedding for the input text. Returns a single vector of floating point numbers for your input, known as a text embedding. Among other uses, a text embedding enables you to calculate the similarity between two documents or two words.

Sentences

  • Read

    Supported languages

    Returns a list of supported languages for the /sentences endpoint

  • Write

    Determine sentences

    Divides the input into sentences. The response contains a list of sentences.

Sentiment

  • Read

    Supported languages

    Returns a list of supported languages for the /sentiment endpoint

  • Write

    Analyze sentiment of input

    Analyzes the positive and negative sentiment expressed by the input. The response contains sentiment analysis results.

Syntax dependencies

  • Read

    Supported languages

    Returns a list of supported languages for the /syntax/dependencies endpoint

  • Write

    Create dependency data from input

    The Analytics API’s /syntax/dependencies endpoint will return the parse tree of the input text as a list of labeled directed links between tokens, as well as the list of tokens in the input sentence.

Tokens

  • Read

    Supported languages

    Returns a list of supported languages for the /tokens endpoint

  • Write

    Tokenize input

    Divides the input into tokens. The response contains a list of tokens.

Topics

  • Read

    Supported languages

    Returns a list of supported languages for the /topics endpoint

  • Write

    Extract topics from input

    Returns each topic extracted from the input. The response is a list of extracted keyphrases and a list of extracted concepts.

Transliteration

  • Read

    Supported languages

    Returns a list of supported languages for the /transliteration endpoint

  • Write

    Runs transliteration on input

    Returns transliteration of Arabic written in Arabizi or Romanized Arabic script and vice versa. The response is a transliteration string.

Info

  • Read

    Babel Street Analytics information

    Returns general information about Babel Street Analytics

Ping

  • Read

    Ping Babel Street Analytics

    Pings Babel Street Analytics for a response indicating the service is available.

See How connections work for access and permissions, or browse all integrations.