0.1.0-PRE8

• Removed the num_tables argument from JaccardLshOptions as it's redundant to num_bands.
• Profiled and refactored the JaccardLshModel using the Ann-benchmarks Kosarak Jaccard dataset.
• Added an example program that grid-searches JaccardLshOptions for best performance and plots the Pareto front.

0.1.0-PRE7

• Got rid of base64 encoding/decoding in ElastiKnnVectorFieldMapper. This improves ann-benchmarks performance by about 20%.

0.1.0-PRE6

• Improved exact Jaccard performance by implementing a critical path in Java so that it uses primitive int [] arrays instead of boxed integers in scala.

0.1.0-PRE5

• Fixed performance regression.

0.1.0-PRE4

• Client and core library interface improvements.
• Added use_cache parameter to KNearestNeighborsQuery which signals that the vectors should only be read once from Lucene and then cached in memory.

0.1.0-PRE3

• Releasing versioned python client library to PyPi.

0.1.0-PRE2

• Releasing versioned elastiknn plugin zip file.