Skip to content

feat: support canonical Lumina index type #344

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Open
QuakeWang wants to merge 1 commit into
base: main
Choose a base branch
from
+138 −41
Open

feat: support canonical Lumina index type #344

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
22 changes: 21 additions & 1 deletion crates/paimon/src/lumina/mod.rs
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -20,7 +20,16 @@ pub mod reader;

use std::collections::HashMap;

pub const LUMINA_VECTOR_ANN_IDENTIFIER: &str = "lumina-vector-ann";
pub const LUMINA_IDENTIFIER: &str = "lumina";
pub const LEGACY_LUMINA_VECTOR_ANN_IDENTIFIER: &str = "lumina-vector-ann";
pub const LUMINA_VECTOR_ANN_IDENTIFIER: &str = LEGACY_LUMINA_VECTOR_ANN_IDENTIFIER;

pub fn is_lumina_index_type(index_type: &str) -> bool {
matches!(
index_type,
LUMINA_IDENTIFIER | LEGACY_LUMINA_VECTOR_ANN_IDENTIFIER
)
}

#[derive(Debug, Clone, Copy, PartialEq, Eq)]
pub enum LuminaVectorMetric {
Expand Down Expand Up @@ -507,6 +516,17 @@ mod tests {
assert!(LuminaVectorMetric::from_string("hamming").is_err());
}

#[test]
fn test_lumina_index_type_identifier_helper() {
assert!(is_lumina_index_type(LUMINA_IDENTIFIER));
assert!(is_lumina_index_type(LEGACY_LUMINA_VECTOR_ANN_IDENTIFIER));
assert!(is_lumina_index_type(LUMINA_VECTOR_ANN_IDENTIFIER));
assert!(!is_lumina_index_type(""));
assert!(!is_lumina_index_type("btree"));
assert!(!is_lumina_index_type("lumina-vector"));
assert!(!is_lumina_index_type("LUMINA"));
}

#[test]
fn test_index_meta_serialize_deserialize() {
let mut options = HashMap::new();
Expand Down
157 changes: 117 additions & 40 deletions crates/paimon/src/table/vector_search_builder.rs
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -16,7 +16,7 @@
// under the License.

use crate::lumina::reader::LuminaVectorGlobalIndexReader;
use crate::lumina::{GlobalIndexIOMeta, SearchResult, VectorSearch, LUMINA_VECTOR_ANN_IDENTIFIER};
use crate::lumina::{is_lumina_index_type, GlobalIndexIOMeta, SearchResult, VectorSearch};
use crate::spec::{DataField, FileKind, IndexManifest};
use crate::table::snapshot_manager::SnapshotManager;
use crate::table::{find_field_id_by_name, RowRange, Table};
Expand Down Expand Up @@ -130,7 +130,7 @@ async fn evaluate_vector_search(
.iter()
.filter(|e| {
e.kind == FileKind::Add
&& e.index_file.index_type == LUMINA_VECTOR_ANN_IDENTIFIER
&& is_lumina_index_type(&e.index_file.index_type)
&& e.index_file
.global_index_meta
.as_ref()
Expand Down Expand Up @@ -190,6 +190,7 @@ async fn evaluate_vector_search(
#[cfg(test)]
mod tests {
use super::*;
use crate::lumina::{LEGACY_LUMINA_VECTOR_ANN_IDENTIFIER, LUMINA_IDENTIFIER};
use crate::spec::{DataType, GlobalIndexMeta, IndexFileMeta, IndexManifestEntry, IntType};

fn make_field(id: i32, name: &str) -> DataField {
Expand Down Expand Up @@ -237,32 +238,39 @@ mod tests {
assert!(result.is_empty());
}

#[tokio::test]
async fn test_evaluate_ignores_non_lumina_index_type() {
let file_io = crate::io::FileIOBuilder::new("memory").build().unwrap();
let fields = vec![make_field(2, "embedding")];
let vs = VectorSearch::new(vec![1.0], 10, "embedding".to_string()).unwrap();

let entry = make_lumina_entry("test.idx", "btree", FileKind::Add, 2);

let result = evaluate_vector_search(
&file_io,
"memory:///test_table",
&HashMap::new(),
&[entry],
&vs,
&fields,
)
.await
.unwrap();
assert!(result.is_empty());
}

#[tokio::test]
async fn test_evaluate_no_matching_field() {
let file_io = crate::io::FileIOBuilder::new("memory").build().unwrap();
let fields = vec![make_field(1, "id")];
let vs = VectorSearch::new(vec![1.0], 10, "embedding".to_string()).unwrap();

let entry = IndexManifestEntry {
kind: FileKind::Add,
partition: vec![],
bucket: 0,
index_file: IndexFileMeta {
index_type: LUMINA_VECTOR_ANN_IDENTIFIER.to_string(),
file_name: "test.idx".to_string(),
file_size: 100,
row_count: 10,
deletion_vectors_ranges: None,
global_index_meta: Some(GlobalIndexMeta {
row_range_start: 0,
row_range_end: 9,
index_field_id: 99,
extra_field_ids: None,
index_meta: None,
}),
},
version: 1,
};
let entry = make_lumina_entry(
"test.idx",
LEGACY_LUMINA_VECTOR_ANN_IDENTIFIER,
FileKind::Add,
99,
);

let result = evaluate_vector_search(
&file_io,
Expand All @@ -283,37 +291,106 @@ mod tests {
let fields = vec![make_field(2, "embedding")];
let vs = VectorSearch::new(vec![1.0], 10, "embedding".to_string()).unwrap();

let entry = IndexManifestEntry {
kind: FileKind::Delete,
let entry = make_lumina_entry(
"test.idx",
LEGACY_LUMINA_VECTOR_ANN_IDENTIFIER,
FileKind::Delete,
2,
);

let result = evaluate_vector_search(
&file_io,
"memory:///test_table",
&HashMap::new(),
&[entry],
&vs,
&fields,
)
.await
.unwrap();
assert!(result.is_empty());
}

#[tokio::test]
async fn test_evaluate_accepts_canonical_lumina_index_type() {
let file_io = crate::io::FileIOBuilder::new("memory").build().unwrap();
let fields = vec![make_field(2, "embedding")];
let vs = VectorSearch::new(vec![1.0], 10, "embedding".to_string()).unwrap();

let entry = make_lumina_entry("missing.idx", LUMINA_IDENTIFIER, FileKind::Add, 2);

let err = evaluate_vector_search(
&file_io,
"memory:///test_table",
&HashMap::new(),
&[entry],
&vs,
&fields,
)
.await
.unwrap_err();
assert!(
err.to_string()
.contains("Failed to read Lumina index file 'missing.idx'"),
"unexpected error: {err}"
);
}

#[tokio::test]
async fn test_evaluate_accepts_legacy_lumina_index_type() {
let file_io = crate::io::FileIOBuilder::new("memory").build().unwrap();
let fields = vec![make_field(2, "embedding")];
let vs = VectorSearch::new(vec![1.0], 10, "embedding".to_string()).unwrap();

let entry = make_lumina_entry(
"missing.idx",
LEGACY_LUMINA_VECTOR_ANN_IDENTIFIER,
FileKind::Add,
2,
);

let err = evaluate_vector_search(
&file_io,
"memory:///test_table",
&HashMap::new(),
&[entry],
&vs,
&fields,
)
.await
.unwrap_err();
assert!(
err.to_string()
.contains("Failed to read Lumina index file 'missing.idx'"),
"unexpected error: {err}"
);
}

fn make_lumina_entry(
file_name: &str,
index_type: &str,
kind: FileKind,
index_field_id: i32,
) -> IndexManifestEntry {
IndexManifestEntry {
kind,
partition: vec![],
bucket: 0,
index_file: IndexFileMeta {
index_type: LUMINA_VECTOR_ANN_IDENTIFIER.to_string(),
file_name: "test.idx".to_string(),
index_type: index_type.to_string(),
file_name: file_name.to_string(),
file_size: 100,
row_count: 10,
deletion_vectors_ranges: None,
global_index_meta: Some(GlobalIndexMeta {
row_range_start: 0,
row_range_end: 9,
index_field_id: 2,
index_field_id,
extra_field_ids: None,
index_meta: None,
}),
},
version: 1,
};

let result = evaluate_vector_search(
&file_io,
"memory:///test_table",
&HashMap::new(),
&[entry],
&vs,
&fields,
)
.await
.unwrap();
assert!(result.is_empty());
}
}
}
Loading