Reconstruct heap graph from disk graph

[sam-herman]

Description

Multiple database projects such as C* and OpenSearch/Solr/Lucene use LSM mechanism with frequent merges.
This in turn creates a high overhead that forces us to reconstruct the entire graph from scratch upon every merge.
A more economic approach would be to pick a leading graph that was previously persisted to disk and incrementally add small graph nodes to it.

This PR makes some of the required changes to support that behavior in upstream systems such as C* and OpenSearch.

Changes

1. Serializable Neighbor Distance Cache - Add a serializable cache that can store the node distances within the OnDiskGraphIndex for a faster re-creation of the OnHeapGraphIndex when read back from disk. The cache is separate and is optional, therefore we can choose whether to apply it or not, without any breaking changes to the current OnDiskGraphIndex. This can later be augmented to a format if we choose to.
2. Help Methods And Constructors - Add helper method and constructors to facilitate easier usage by other projects with graph merge use cases.

Testing

Added tests for graph overlap and recall for reconstructed graphs.