Think of these concepts as a glossary. Each of these concepts include a link to detailed information, usually with examples. If you’re new to AI, these concepts can help you learn more about AI and the Qdrant approach.
Collections define a named set of points that you can use for your search.
A Payload describes information that you can store with vectors.
Points are a record which consists of a vector and an optional payload.
Search describes similarity search, which set up related objects close to each other in vector space.
Explore includes several APIs for exploring data in your collections.
Filtering defines various database-style clauses, conditions, and more.
Optimizer describes options to rebuild database structures for faster search. They include a vacuum, a merge, and an indexing optimizer.
Storage describes the configuration of storage in segments, which include indexes and an ID mapper.
Indexing lists and describes available indexes. They include payload, vector, sparse vector, and a filterable index.
Snapshots describe the backup/restore process (and more) for each node at specific times.