Searching vector embeddings based on context radius
AssigneeView Systems, Inc.
InventorsBlake Martz, Joel Christner
Life of this patent
Estimating the term…
Loading patent…
AssigneeView Systems, Inc.
InventorsBlake Martz, Joel Christner
Estimating the term…
This disclosure provides methods, devices, and systems for data retrieval. The present implementations more specifically relate to techniques for searching vector embeddings based on contextual information. In some aspects, a data retrieval system may receive a search query including a search value and a context radius indicating a number (N) of terms representing a range of contextual information. The data retrieval system retrieves, from a vector repository storing vector embeddings associated with a data asset, a number (K) of vector embeddings that match the search value (such as based on cosine similarity, Euclidean distance, or other similarity measure). The data retrieval system further retrieves, from the vector repository, N additional vector embeddings for each of the K matching vector embeddings based on a hierarchy of terms associated with the data asset, where the hierarchy of terms indicates an ordinal position for each vector embedding relative to the data asset.
A method of data retrieval, comprising:
A data retrieval system comprising:
Dependencies are inferred from the claim text.