rust/lancedb
1
0
Fork 0
mirror of https://github.com/lancedb/lancedb.git synced 2026-08-18 12:08:35 +00:00
Code Issues Packages Projects Releases Wiki Activity

feat: support distributed analyze plan metrics in clients (#3675)

Browse Source 
Adds client-side support for analyze_plan distributed metrics modes
across Rust, Python, and TypeScript clients. Defaults to aggregate for
backward compatibility and sends the remote distributed_metrics
parameter only when a non-default mode is requested.
This commit is contained in:
Jack Ye
2026-07-15 21:21:40 -07:00
committed by GitHub
parent 00c4a7b843
commit 37032151d3
22 changed files with 396 additions and 75 deletions
Download Patch File Download Diff File Expand all files Collapse all files
python/src/query.rs
+48 -8
View File
@@ -19,6 +19,7 @@ use lancedb::index::scalar::{
BooleanQuery, BoostQuery, FtsQuery, FullTextSearchQuery, MatchQuery, MultiMatchQuery, Occur,
Operator, PhraseQuery,
};
use lancedb::query::AnalyzePlanDistributedMetrics;
use lancedb::query::QueryBase;
use lancedb::query::QueryExecutionOptions;
use lancedb::query::QueryFilter;
@@ -42,6 +43,25 @@ use pyo3::{Borrowed, FromPyObject, exceptions::PyRuntimeError};
use pyo3::{PyErr, pyclass};
use pyo3::{exceptions::PyValueError, intern};
fn analyze_plan_options(distributed_metrics: Option<&str>) -> PyResult<QueryExecutionOptions> {
let analyze_plan_distributed_metrics = match distributed_metrics.unwrap_or("aggregate") {
"aggregate" => AnalyzePlanDistributedMetrics::Aggregate,
"per_worker" => AnalyzePlanDistributedMetrics::PerWorker,
"full" => AnalyzePlanDistributedMetrics::Full,
mode => {
return Err(PyValueError::new_err(format!(
"Invalid distributed_metrics value '{}'. Expected one of: \
'aggregate', 'per_worker', 'full'",
mode
)));
}
};
let mut options = QueryExecutionOptions::default();
options.analyze_plan_distributed_metrics = analyze_plan_distributed_metrics;
Ok(options)
}
impl<'a, 'py> FromPyObject<'a, 'py> for PyLanceDB<FtsQuery> {
type Error = PyErr;
@@ -571,11 +591,16 @@ impl Query {
})
}
pub fn analyze_plan(self_: PyRef<'_, Self>) -> PyResult<Bound<'_, PyAny>> {
#[pyo3(signature = (distributed_metrics=None))]
pub fn analyze_plan(
self_: PyRef<'_, Self>,
distributed_metrics: Option<String>,
) -> PyResult<Bound<'_, PyAny>> {
let inner = self_.inner.clone();
let options = analyze_plan_options(distributed_metrics.as_deref())?;
future_into_py(self_.py(), async move {
inner
.analyze_plan()
.analyze_plan_with_options(options)
.await
.map_err(|e| PyRuntimeError::new_err(e.to_string()))
})
@@ -650,11 +675,16 @@ impl TakeQuery {
})
}
pub fn analyze_plan(self_: PyRef<'_, Self>) -> PyResult<Bound<'_, PyAny>> {
#[pyo3(signature = (distributed_metrics=None))]
pub fn analyze_plan(
self_: PyRef<'_, Self>,
distributed_metrics: Option<String>,
) -> PyResult<Bound<'_, PyAny>> {
let inner = self_.inner.clone();
let options = analyze_plan_options(distributed_metrics.as_deref())?;
future_into_py(self_.py(), async move {
inner
.analyze_plan()
.analyze_plan_with_options(options)
.await
.map_err(|e| PyRuntimeError::new_err(e.to_string()))
})
@@ -777,14 +807,19 @@ impl FTSQuery {
})
}
pub fn analyze_plan(self_: PyRef<'_, Self>) -> PyResult<Bound<'_, PyAny>> {
#[pyo3(signature = (distributed_metrics=None))]
pub fn analyze_plan(
self_: PyRef<'_, Self>,
distributed_metrics: Option<String>,
) -> PyResult<Bound<'_, PyAny>> {
let inner = self_
.inner
.clone()
.full_text_search(self_.fts_query.clone());
let options = analyze_plan_options(distributed_metrics.as_deref())?;
future_into_py(self_.py(), async move {
inner
.analyze_plan()
.analyze_plan_with_options(options)
.await
.map_err(|e| PyRuntimeError::new_err(e.to_string()))
})
@@ -958,11 +993,16 @@ impl VectorQuery {
})
}
pub fn analyze_plan(self_: PyRef<'_, Self>) -> PyResult<Bound<'_, PyAny>> {
#[pyo3(signature = (distributed_metrics=None))]
pub fn analyze_plan(
self_: PyRef<'_, Self>,
distributed_metrics: Option<String>,
) -> PyResult<Bound<'_, PyAny>> {
let inner = self_.inner.clone();
let options = analyze_plan_options(distributed_metrics.as_deref())?;
future_into_py(self_.py(), async move {
inner
.analyze_plan()
.analyze_plan_with_options(options)
.await
.map_err(|e| PyRuntimeError::new_err(e.to_string()))
})