mirror of
https://github.com/lancedb/lancedb.git
synced 2026-05-19 21:10:41 +00:00
feat!: upgrade lance to v0.28.0 (#2404)
this introduces some breaking changes in terms of rust API of creating FTS index, and the default index params changed Signed-off-by: BubbleCal <bubble-cal@outlook.com> <!-- This is an auto-generated comment: release notes by coderabbit.ai --> ## Summary by CodeRabbit - **New Features** - Updated default settings for full-text search (FTS) index creation: stemming, stop word removal, and ASCII folding are now enabled by default, while token position storage is disabled by default. - **Refactor** - Simplified and streamlined the configuration and handling of FTS index parameters for improved maintainability and consistency across interfaces. - Enhanced serialization and request construction for FTS index parameters to reduce manual handling and improve code clarity. - Improved test coverage by explicitly enabling positional indexing in FTS tests to support phrase queries. - **Chores** - Upgraded all internal dependencies related to FTS indexing to the latest version for enhanced compatibility and performance. - Updated package versions for Node.js, Python, and Rust components to the latest beta releases. - Improved CI workflows by adding Rust toolchain setup with formatting and linting tools. <!-- end of auto-generated comment: release notes by coderabbit.ai --> --------- Signed-off-by: BubbleCal <bubble-cal@outlook.com> Co-authored-by: Will Jones <willjones127@gmail.com>
This commit is contained in:
@@ -125,32 +125,30 @@ impl Index {
|
||||
ascii_folding: Option<bool>,
|
||||
) -> Self {
|
||||
let mut opts = FtsIndexBuilder::default();
|
||||
let mut tokenizer_configs = opts.tokenizer_configs.clone();
|
||||
if let Some(with_position) = with_position {
|
||||
opts = opts.with_position(with_position);
|
||||
}
|
||||
if let Some(base_tokenizer) = base_tokenizer {
|
||||
tokenizer_configs = tokenizer_configs.base_tokenizer(base_tokenizer);
|
||||
opts = opts.base_tokenizer(base_tokenizer);
|
||||
}
|
||||
if let Some(language) = language {
|
||||
tokenizer_configs = tokenizer_configs.language(&language).unwrap();
|
||||
opts = opts.language(&language).unwrap();
|
||||
}
|
||||
if let Some(max_token_length) = max_token_length {
|
||||
tokenizer_configs = tokenizer_configs.max_token_length(Some(max_token_length as usize));
|
||||
opts = opts.max_token_length(Some(max_token_length as usize));
|
||||
}
|
||||
if let Some(lower_case) = lower_case {
|
||||
tokenizer_configs = tokenizer_configs.lower_case(lower_case);
|
||||
opts = opts.lower_case(lower_case);
|
||||
}
|
||||
if let Some(stem) = stem {
|
||||
tokenizer_configs = tokenizer_configs.stem(stem);
|
||||
opts = opts.stem(stem);
|
||||
}
|
||||
if let Some(remove_stop_words) = remove_stop_words {
|
||||
tokenizer_configs = tokenizer_configs.remove_stop_words(remove_stop_words);
|
||||
opts = opts.remove_stop_words(remove_stop_words);
|
||||
}
|
||||
if let Some(ascii_folding) = ascii_folding {
|
||||
tokenizer_configs = tokenizer_configs.ascii_folding(ascii_folding);
|
||||
opts = opts.ascii_folding(ascii_folding);
|
||||
}
|
||||
opts.tokenizer_configs = tokenizer_configs;
|
||||
|
||||
Self {
|
||||
inner: Mutex::new(Some(LanceDbIndex::FTS(opts))),
|
||||
|
||||
Reference in New Issue
Block a user