* In HNSW graph layer building, infer right capacity on collect
* Resize with empty vector, use constant function rather than clone
* Use resize_with in other places as well
* SparseVector implements VectorIndex
* dedicated telemetry
* conflict
* easy code reviews
* simplify tracking indexed points count
* move telemetry conversion to sparse file
* move max_result_count out of inverted index trait
* unify sparse vector fixtures
* simpler conversion
* add todo regarding OOM potential
* reuse check deleted from raw scorer with TODO
* change new to open to handle mmap index
* Sparse vector index
* better name
* fill properly postings
* conflict
* easy reviews
* use unstable sort
* use optional instead of bool flag
* clearer score type and future direction
* NonZeroUsize length for FixedLengthPriorityQueue
* rename id to record_id
* cleanup dimension inverted index
* standard Iterator
* code review
* Shift comment
* early return if no matching posting lists
* sprinkle iterators
* privatize the means of production
---------
Co-authored-by: timvisee <tim@visee.me>