This section lists and briefly describes all the components that are especially useful for semantic search.
|Ranker||SentenceTransformersRanker||Orders documents based on how relevant they are to the query.|
In a query pipeline, after a keyword-based Retriever to rank the documents it returns.
|Finds an answer by selecting a text span in documents.|
In a query pipeline when you want to know the location of the answer.
|Fetches relevant documents from the DocumentStore.|
Coupling Retriever with a Reader in a query pipeline to speed up the search (the Reader only goes through the documents it gets from the Retriever).
|QuestionGenerator||QuestionGenerator||When given a document, it generates questions this document can answer.|
Auto-suggested questions in your search app.
Updated about 1 month ago