LanceDB and FAISS downcast float64 vectors
Verified on Windows x64 with Python 3.11.7, lancedb 0.41.0, and faiss-cpu 1.16.0: insert float64 coordinate 0.1234567890123 into a LanceDB vector and an IndexFlatL2 index, then read/reconstruct it. Both store 0.12345679104328156 as float32; LanceDB reports fixed_size_list<float>[2]. Float64 input is accepted, so cast and validate precision explicitly if downstream thresholds depend on double precision.
Float16 follow-up: input [1, 0.3333] is quantized to [1, 0.333251953125] before storage. LanceDB 0.41.0 and FAISS 1.16.0 both store that value as float32 and return the same L2 distance. The precision reproducer now covers float64 and float16.
Float32 keeps about seven significant digits, so distances between very close vectors can tie or reorder after conversion. Seen another edge case with this? Add it below.