feat: expose list-element FTS document granularity (#4050)

## Summary

LanceDB could not request Lance's list-element FTS document granularity
through Python or Remote APIs, and generic nested-field resolution
exposed Arrow's internal `item` segment instead of the public field
path.

This exposes typed `row | list_element` configuration for Python FTS
index creation and match/phrase queries, preserves `_doc_index`, and
keeps nested FTS paths public (for example, `docs.content`). Remote
list-element requests require server API version 0.6.0 so older servers
cannot silently execute them with row semantics; explicit row requests
remain compatible.

## Compatibility

Omitted index and query parameters retain row granularity. Remote row
index creation omits the new wire field.

## Tracking


[ENT-2342](https://linear.app/lancedb/issue/ENT-2342/expose-list-element-fts-document-granularity-end-to-end)
This commit is contained in:
Xuanwo
2026-08-26 23:27:39 +08:00
committed by GitHub
parent 06872463cf
commit b78f2a5044
15 changed files with 723 additions and 55 deletions
+8 -2
View File
@@ -8,7 +8,7 @@ use lancedb::index::vector::{
};
use lancedb::index::{
Index as LanceDbIndex,
scalar::{BTreeIndexBuilder, FmIndexBuilder, FtsIndexBuilder},
scalar::{BTreeIndexBuilder, DocumentGranularity, FmIndexBuilder, FtsIndexBuilder},
};
use pyo3::IntoPyObject;
use pyo3::types::PyStringMethods;
@@ -60,7 +60,11 @@ pub fn extract_index_params(source: &Option<Bound<'_, PyAny>>) -> PyResult<Lance
.ngram_min_length(params.ngram_min_length)
.ngram_max_length(params.ngram_max_length)
.ngram_prefix_only(params.prefix_only)
.custom_stop_words(params.custom_stop_words);
.custom_stop_words(params.custom_stop_words)
.document_granularity(
DocumentGranularity::try_from(params.document_granularity.as_str())
.map_err(|err| PyValueError::new_err(err.to_string()))?,
);
if let Some(memory_limit) = params.memory_limit {
inner_opts = inner_opts.memory_limit_mb(memory_limit);
}
@@ -221,6 +225,7 @@ struct FtsParams {
block_size: usize,
memory_limit: Option<u64>,
num_workers: Option<usize>,
document_granularity: String,
}
#[derive(FromPyObject)]
@@ -481,6 +486,7 @@ mod tests {
block_size = 128
memory_limit = 2048
num_workers = 7
document_granularity = 'row'
config = FTS()",
None,