feat: add table FTS query tokenization (#3659)

## Summary
- add table-level FTS query tokenization returning token text and
position
- use the native index tokenizer for local tables and remote index
metadata for remote tables
- expose sync and async Python table wrappers with focused coverage
This commit is contained in:
Jack Ye
2026-07-14 10:59:33 -07:00
committed by GitHub
parent 711e05619b
commit 06b53c97d6
26 changed files with 1175 additions and 16 deletions
+4 -2
View File
@@ -15,8 +15,8 @@ use pyo3::{
use query::{FTSQuery, HybridQuery, Query, VectorQuery};
use session::Session;
use table::{
AddColumnsResult, AddResult, AlterColumnsResult, DeleteResult, DropColumnsResult, LsmWriteSpec,
MergeResult, PyBlobFile, Table, UpdateFieldMetadataResult, UpdateResult,
AddColumnsResult, AddResult, AlterColumnsResult, DeleteResult, DropColumnsResult, FtsToken,
LsmWriteSpec, MergeResult, PyBlobFile, Table, UpdateFieldMetadataResult, UpdateResult,
};
pub mod arrow;
@@ -60,6 +60,7 @@ pub fn _lancedb(_py: Python, m: &Bound<'_, PyModule>) -> PyResult<()> {
m.add_class::<DeleteResult>()?;
m.add_class::<DropColumnsResult>()?;
m.add_class::<UpdateResult>()?;
m.add_class::<FtsToken>()?;
m.add_class::<PyAsyncPermutationBuilder>()?;
m.add_class::<PyPermutationReader>()?;
m.add_class::<PyExpr>()?;
@@ -75,6 +76,7 @@ pub fn _lancedb(_py: Python, m: &Bound<'_, PyModule>) -> PyResult<()> {
m.add_function(wrap_pyfunction!(connect, m)?)?;
m.add_function(wrap_pyfunction!(connect_namespace, m)?)?;
m.add_function(wrap_pyfunction!(connect_namespace_client, m)?)?;
m.add_function(wrap_pyfunction!(table::tokenize, m)?)?;
m.add_function(wrap_pyfunction!(permutation::async_permutation_builder, m)?)?;
m.add_function(wrap_pyfunction!(util::validate_table_name, m)?)?;
m.add_function(wrap_pyfunction!(query::fts_query_to_json, m)?)?;