rust/lancedb
1
0
Fork 0
mirror of https://github.com/lancedb/lancedb.git synced 2026-07-04 11:30:46 +00:00
Code Issues Packages Projects Releases Wiki Activity

feat(refresh): batch_size is a per-refresh knob (refresh_column), not a function-only option

Browse Source 
batch_size / num_workers / max_workers are invocation concerns (how to schedule THIS
refresh), so expose batch_size on refresh_column through every layer (Python sync+async
-> pyo3 -> Rust client -> the REST RefreshColumnRequest.batch_size, which the handler
already forwards into the backfill). num_workers/max_workers were already invocation-
placed; batch_size was the gap. The function may still carry a default; the refresh
override wins (extends the batch_size_override model). Both crates cargo-check clean.

Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
This commit is contained in:
Wyatt Alt
2026-06-14 06:30:08 -07:00
committed by Jack Ye
parent fbe6a5a3fd
commit d4f4fef3ba
4 changed files with 24 additions and 5 deletions
Download Patch File Download Diff File Expand all files Collapse all files

6
rust/lancedb/src/remote/table.rs
View File

@@ -2338,6 +2338,7 @@ impl<S: HttpSend> BaseTable for RemoteTable<S> {
where_clause: Option<String>,
num_workers: Option<u32>,
max_workers: Option<u32>,
batch_size: Option<u32>,
) -> Result<String> {
let mut body = serde_json::json!({ "columns": columns });
if let Some(w) = where_clause {
@@ -2349,6 +2350,9 @@ impl<S: HttpSend> BaseTable for RemoteTable<S> {
if let Some(n) = max_workers {
body["max_workers"] = n.into();
}
if let Some(n) = batch_size {
body["batch_size"] = n.into();
}
let request = self
.client
.post(&format!("/v1/table/{}/refresh_column", self.identifier))
@@ -2873,7 +2877,7 @@ mod tests {
});
let job_id = table
.refresh_column(&["vec".to_string()], None, Some(2), None)
.refresh_column(&["vec".to_string()], None, Some(2), None, None)
.await
.unwrap();
assert_eq!(job_id, "j-9");

4
rust/lancedb/src/table.rs
View File

@@ -646,6 +646,7 @@ pub trait BaseTable: std::fmt::Display + std::fmt::Debug + Send + Sync {
_where_clause: Option<String>,
_num_workers: Option<u32>,
_max_workers: Option<u32>,
_batch_size: Option<u32>,
) -> Result<String> {
Err(Error::NotSupported {
message: "refresh_column is not supported by this table".into(),
@@ -1513,9 +1514,10 @@ impl Table {
where_clause: Option<String>,
num_workers: Option<u32>,
max_workers: Option<u32>,
batch_size: Option<u32>,
) -> Result<String> {
self.inner
.refresh_column(columns, where_clause, num_workers, max_workers)
.refresh_column(columns, where_clause, num_workers, max_workers, batch_size)
.await
}