pg.ddx.io pgvector/pgvector GitHub issues and pull requestshelp / color / mirror / Atom feed
[pgvector/pgvector] issue #1051: [Bug] Dense scalar distances overflow on finite `vector` inputs 3+ messages / 2 participants [nested] [flat]
* [pgvector/pgvector] issue #1051: [Bug] Dense scalar distances overflow on finite `vector` inputs @ 2026-10-31 08:55 "JoeyLYZ666 (@JoeyLYZ666)" <noreply+JoeyLYZ666@github.com> 0 siblings, 0 replies; 3+ messages in thread From: JoeyLYZ666 (@JoeyLYZ666) @ 2026-10-31 08:55 UTC (permalink / raw) To: pgvector/pgvector <noreply+pgvector-pgvector@github.com> ## Describe the bug pgvector 0.8.7 returns `Infinity` or `NaN` from dense `vector` scalar distance functions for finite input values whose exact result is still representable as `double precision`. ## Reproduce Run `testcase.py` against PostgreSQL with pgvector 0.8.7: ```powershell python testcase.py ``` The query evaluates `l1_distance`, `l2_distance`, and `cosine_distance` on finite dense vectors containing `1e38` and `1e20`. [testcase.py](https://github.com/user-attachments/files/34213300/testcase.py) ## Expected behavior All results should be finite. For the selected values, the expected results are approximately `4e38`, `2.828427e38`, and `0` for the identical cosine input. ## Actual behavior The affected release returns: ```text Infinity, Infinity, NaN ``` The dense implementation accumulates intermediate values in `float` before converting the result to the declared `double precision` return type. ## Impact Finite vectors can produce non-finite scalar distances, breaking ordering, threshold checks, and any oracle requiring finite non-negative distances. ## Environment - pgvector 0.8.7 - PostgreSQL 18 - dense `vector(2)` values ^ permalink raw [nested|flat] 3+ messages in thread
* Re: [pgvector/pgvector] issue #1051: [Bug] Dense scalar distances overflow on finite `vector` inputs @ 2026-10-31 09:45 "ankane (@ankane)" <noreply+ankane@github.com> 1 sibling, 0 replies; 3+ messages in thread From: ankane (@ankane) @ 2026-10-31 09:45 UTC (permalink / raw) To: pgvector/pgvector <noreply+pgvector-pgvector@github.com> Hi @JoeyLYZ666, see https://github.com/pgvector/pgvector/issues/1033#issuecomment-5884285142. ^ permalink raw [nested|flat] 3+ messages in thread
* Re: [pgvector/pgvector] issue #1051: [Bug] Dense scalar distances overflow on finite `vector` inputs @ 2026-10-31 09:45 "ankane (@ankane)" <noreply+ankane@github.com> 1 sibling, 0 replies; 3+ messages in thread From: ankane (@ankane) @ 2026-10-31 09:45 UTC (permalink / raw) To: pgvector/pgvector <noreply+pgvector-pgvector@github.com> @ankane closed this. ^ permalink raw [nested|flat] 3+ messages in thread
end of thread, other threads:[~2026-10-31 09:45 UTC | newest] Thread overview: 3+ messages (download: mbox mbox.gz follow: Atom feed) -- links below jump to the message on this page -- 2026-10-31 08:55 [pgvector/pgvector] issue #1051: [Bug] Dense scalar distances overflow on finite `vector` inputs "JoeyLYZ666 (@JoeyLYZ666)" <noreply+JoeyLYZ666@github.com> 2026-10-31 09:45 ` "ankane (@ankane)" <noreply+ankane@github.com> 2026-10-31 09:45 ` "ankane (@ankane)" <noreply+ankane@github.com>
This inbox is served by DDX for PostgreSQL; see mirroring instructions for how to clone and mirror all data and code used for this inbox