Skip to main content

Documentation Index

Fetch the complete documentation index at: https://docs.cyborg.co/llms.txt

Use this file to discover all available pages before exploring further.

Retrieves the nearest neighbors for given query vectors. 
QueryResults Query(Array2D<float>& query_vectors,
                   const QueryParams& query_params = QueryParams());

​
Parameters

ParameterTypeDescription
query_vectorsArray2D<float>Query vectors to search.
query_paramsQueryParams(Optional) Parameters for querying, such as top_k and n_probes.
If this function is called on an index where TrainIndex() has not been executed, the query will use encrypted exhaustive search. This may cause queries to be slower, especially when there are many vector embeddings in the index.

​
Returns

QueryResults: Results top_k containing decrypted nearest neighbors IDs and distances.

​
Exceptions

  • Throws if the query vectors have incompatible dimensions with the index.
  • Throws if the index was not created or loaded yet.
  • Throws if the query could not be executed.

​
Example Usage

cyborg::Array2D<float> queries{/*...*/}; // Populate with one or more query vectors
cyborg::QueryParams params(10, 5);  // top_k = 10, n_probes = 5

QueryResults results = index->Query(queries, params);
std::cout << "ID: " << results.ids[j] << ", Distance: " << results.distances[j] << std::endl;
// Process query results...