Vectara’s platform offers a range of options for getting data in, from a no-code admin interface to a complete library of APIs. The platform enables developers to easily build, debug and test applications of semantic search. Vectara provides everything you need to empower marketing, IT, support and sales with immediate access to answers for their toughest questions.
APIs
Vectara is a modern, API-first search platform. Developer friendly and easily accessible, the APIs are designed for consumption by application developers and data engineers who wish to include one or more elements of a search pipeline within their site or application. They provide a clear blueprint for how search services can be consumed. Vectara APIs abstract away the underlying complexity of operating a ML search pipeline.
Custom Dimensions
Vectara supports custom dimensions that can be used to directly influence the search results returned. Custom dimensions allow developers to attach key data attributes that could be relevant in scoring results. For example, star ratings in product reviews, product categories, document freshness or custom probability scores can help in ordering results before serving them to users.
Broad File Type Support
Vectara automatically extracts text from documents of nearly any type, with auto-detection of file formats and multi-stage extraction routines. Vectara can accurately extract text, index and create vector embeddings from documents in formats including PDF, Microsoft Word, Microsoft Powerpoint, Open Office, HTML, JSON, XML, email in RFC822, text, RTF, ePUB, or CommonMark. Vectara extracts text from tables, images and other document elements automatically.
Confidence Scores
Vectara provides automatic scoring of result relevance from all applied AI models to identify the confidence the engine has in the precision of the results. Scores reveal the aggregate confidence the engine has in the relevance of the result, after accounting for developer-specified custom dimensions.
Metadata Annotation
Vectara supports both platform automated and customer defined annotation of labels to any ingested data. Annotations commonly applied might include language, date of ingestion, author, version, or other more unique identifiers of interest. There are no restrictions on what Administrators can use annotations for. Vectara lets you store useful data directly alongside your documents instead of having to refer to external databases.
