rust/lancedb
1
0
Fork 0
mirror of https://github.com/lancedb/lancedb.git synced 2026-11-13 14:16:54 +00:00
Code Issues Packages Projects Releases Wiki Activity

feat(nodejs): expose Function refresh publication intervals (#4957)

Browse Source 
Expose `publicationIntervalRows` on TypeScript refresh options and
forward it as `publication_interval_rows`. Accept positive safe integers
and preserve whole-fragment publication when omitted.

```typescript
const job = await table.refreshColumnAsync("embedding", {
  publicationIntervalRows: 10000,
});
await job.wait();
```

Document the threshold semantics and add coverage for serialization,
omission, invalid values, safe-integer boundaries, and Embedded
rejection.

Closes ENT-3755.
This commit is contained in:
Jack Ye
2026-11-11 07:34:54 -08:00
committed by GitHub
parent c1fee36045
commit e9774ed168
7 changed files with 103 additions and 6 deletions
Download Patch File Download Diff File Expand all files Collapse all files
nodejs/src/table.rs
+12 -3
View File
@@ -1649,7 +1649,7 @@ pub struct FunctionWorkerResourceBudget {
pub gpu_count: Option<f64>,
}
fn resource_budget_integer(value: f64, name: &str) -> napi::Result<u64> {
fn positive_safe_integer(value: f64, name: &str) -> napi::Result<u64> {
const MAX_SAFE_INTEGER: f64 = 9_007_199_254_740_991.0;
if !value.is_finite() || value.fract() != 0.0 || !(1.0..=MAX_SAFE_INTEGER).contains(&value) {
return Err(napi::Error::from_reason(format!(
@@ -1699,6 +1699,11 @@ pub struct RefreshColumnOptions {
pub where_clause: Option<String>,
/// Maximum rows per Function call; must be greater than zero.
pub batch_size: Option<u32>,
/// Row-count threshold for publishing completed Function split ranges.
/// Must be a positive safe integer. Omit for whole-fragment publication.
/// Actual publications can be larger; remaining rows publish at completion.
/// Requires LanceDB Enterprise with non-Blob Function outputs.
pub publication_interval_rows: Option<f64>,
/// Override the registered Function's maximum concurrent user-code calls
/// for this logical execution.
pub max_concurrency: Option<f64>,
@@ -1735,6 +1740,10 @@ impl TryFrom<RefreshColumnOptions> for lancedb::table::RefreshColumnOptions {
let mut options = Self::default();
options.where_clause = value.where_clause;
options.batch_size = value.batch_size.map(|size| size as usize);
options.publication_interval_rows = value
.publication_interval_rows
.map(|rows| positive_safe_integer(rows, "publicationIntervalRows"))
.transpose()?;
options.max_concurrency = positive_u32(value.max_concurrency, "maxConcurrency")?;
options.gpu_class = value.gpu_class;
options.resource_budget = value
@@ -1742,8 +1751,8 @@ impl TryFrom<RefreshColumnOptions> for lancedb::table::RefreshColumnOptions {
.map(|budget| {
Ok::<_, napi::Error>(
LanceFunctionWorkerResourceBudget::new(
resource_budget_integer(budget.cpu_millis, "resourceBudget.cpuMillis")?,
resource_budget_integer(budget.memory_bytes, "resourceBudget.memoryBytes")?,
positive_safe_integer(budget.cpu_millis, "resourceBudget.cpuMillis")?,
positive_safe_integer(budget.memory_bytes, "resourceBudget.memoryBytes")?,
)
.with_gpu_count(resource_budget_gpu_count(budget.gpu_count)?),
)