We're thrilled to hear you're learning more about how to leverage the Layar APIs in your projects! For those of you who haven't come read the product offering on the website, please check it out here. Within this link, you will find helpful overviews of the different types of APIs we offer, as well as links to our GitHub, API Demo App, and the pricing structure. For those of you ready to dig in deeper, read on!
I. Deep Learning Text Analytics
Search: This collection of search APIs that search and return results for data across a user's Layar Data Fabrics.
/autocomplete - Search capability that enables the rapid completion of words used in various domains across the Layar Data Fabrics.
/ontologyTerms – Create, read, update, and delete operations for ontologies used within a user’s Layar Data Fabrics.
/savedList – Create, add, or retrieve items from a saved set of documents, images, or other types of data.
/sourceDocument – A large API with multiple endpoints focused on the retrieval and utilization of documents pulled into Layar via connectors: search, upload, add, or retrieve documents, annotate documents, download raw files, extract images or tables, and more.
/statement – Search for sentences or statements from documents within Layar. For tables, each row is considered a statement endpoint. For example, a user can search for a statement and retrieve the top 100 statements in a given document, ordered by location in the original document.
Q/A Service: A collection of Vyasa's natural language processing (NLP) APIs that provide natural language answers to user-generated questions based on integrated content in a user's Layar Data Fabrics.
/questionAnswer – A Vyasa NLP algorithm API that powers the Vyasa Q/A Service. The /ask endpoint returns natural language answers back to user-generated questions based on integrated content in Layar Data Fabrics. Also includes a /queryExpansion endpoint, which will broaden input queries beyond original input to include additional words or phrases, to improve answer precision.
/group - Merge like-terms (“Vyasa Analytics”, “Vyasa Analytics, LLC” ) into a single grouping or single output term.
Named Entity Recognition (NER): A collection of NER APIs that identify and tag terms and phrases with custom and Vyasa-built NER concepts. Learn more!
/namedEntity – Identifies and tags terms and phrases via Vyasa’s named entity recognition algorithms. To find a hard-coded list of the current named “entities” that Vyasa tags, or types, use endpoint type.
/concept – Create, manage, and delete named entities (aka “concepts”) that are applied to a user’s data within their Layar Data Fabrics. Identify, assign, and extract hierarchical relationships between terms and their named entities (ie preferred synonyms). A user can also identify additional relationships between a term and other concepts via their co-occurrences within statements and documents.
/conceptType – Search, filter, create, update, and delete concept types implemented in a user’s Layar Data Fabrics, similar to namedEntity. This API is designated for both user-created concepts as well as Vyasa’s official named entity list.
/radar – Identify similar words and phrases that exist within close proximity in vector space, collected from across the integrated content in Layar Data Fabrics.
II. Small Compound Analytics
/compound – Render an svg image of the chemical structure for a compound SMILE string
/smiles – Perform Vyasa’s toxicity analysis algorithm on a set of compound SMILE strings and return a .csv output or a self-organizing map (SOM) that groups compounds based on similar toxicity profiles.
III. Model Management
/model – Search and implement Vyasa’s commercially available pre-built models to assign to different modules in a project. Users can also upload their own custom models with this API.
/module – Within a project, users can define the type of module they are performing (ie image classification). Search or save modules implemented by Vyasa for an assortment of use cases to use in custom projects for similar applications, including fine-tuning a transfer model for a private dataset.
/project – Create, edit, or remove projects from a user’s instance. Projects have a versatile design that may include several results as a component of the project management endpoints.
/projectComputation – Output files for any quantitative readouts implemented by the user as defined by the project and module. Most users utilize this API for output files pertaining to number of iterations, model assessments, etc.
IV. Data Fabric Management
/administration – View and manage which version of Layar APIs are currently being utilized.
/connector – Specifically for dynamic connectors (ie Twitter) where users can identify, delete, or update what data is being pulled in by the connector. For example, a user can update their “News Media” connector with an additional set of hashtags, which will pull in the tweets with that hashtag in them.
/event – View metadata for an event performed with a Layar API, such as user, date of event logged, project ids, and more.
/eventLog – View metadata for an event performed with a Layar API, such as user, date of event logged, project ids, and more.
/liveSource – Performs the import jobs for connectors such as S3 buckets, Twitter feeds, and Google Drives (but does not capture or maintain local file uploads). Imports any new data that exists in the connectors but is not currently ingested by Layar. Defines the connectors and reports on import job statuses.