rust/lancedb
1
0
Fork 0
mirror of https://github.com/lancedb/lancedb.git synced 2026-01-05 19:32:56 +00:00
Code Issues Packages Projects Releases Wiki Activity

docs: use bypass_vector_index() instead of use_index=false (#2115)

Browse Source
This commit is contained in:
QianZhu
2025-03-12 09:31:09 -07:00
committed by GitHub
parent 581bcfbb88
commit c9d6fc43a6
1 changed files with 1 additions and 1 deletions
Download Patch File Download Diff File Expand all files Collapse all files

2
docs/src/sql.md
View File

@@ -7,7 +7,7 @@ performed on the top-k results returned by the vector search. However, pre-filte
option that performs the filter prior to vector search. This can be useful to narrow down
the search space of a very large dataset to reduce query latency.
Note that both pre-filtering and post-filtering can yield false positives. For pre-filtering, if the filter is too selective, it might eliminate relevant items that the vector search would have otherwise identified as a good match. In this case, increasing `nprobes` parameter will help reduce such false positives. It is recommended to set `use_index=false` if you know that the filter is highly selective.
Note that both pre-filtering and post-filtering can yield false positives. For pre-filtering, if the filter is too selective, it might eliminate relevant items that the vector search would have otherwise identified as a good match. In this case, increasing `nprobes` parameter will help reduce such false positives. It is recommended to call `bypass_vector_index()` if you know that the filter is highly selective.
Similarly, a highly selective post-filter can lead to false positives. Increasing both `nprobes` and `refine_factor` can mitigate this issue. When deciding between pre-filtering and post-filtering, pre-filtering is generally the safer choice if you're uncertain.