add a settings for the search cutoff

This commit is contained in:
Tamo 2024-03-11 18:24:21 +01:00
parent 4a467739cd
commit d1db495119
11 changed files with 169 additions and 35 deletions

View file

@ -67,6 +67,7 @@ pub mod main_key {
pub const PAGINATION_MAX_TOTAL_HITS: &str = "pagination-max-total-hits";
pub const PROXIMITY_PRECISION: &str = "proximity-precision";
pub const EMBEDDING_CONFIGS: &str = "embedding_configs";
pub const SEARCH_CUTOFF: &str = "search_cutoff";
}
pub mod db_name {
@ -1505,6 +1506,18 @@ impl Index {
_ => "default".to_owned(),
})
}
pub(crate) fn put_search_cutoff(&self, wtxn: &mut RwTxn<'_>, cutoff: u64) -> heed::Result<()> {
self.main.remap_types::<Str, BEU64>().put(wtxn, main_key::SEARCH_CUTOFF, &cutoff)
}
pub fn search_cutoff(&self, rtxn: &RoTxn<'_>) -> Result<Option<u64>> {
Ok(self.main.remap_types::<Str, BEU64>().get(rtxn, main_key::SEARCH_CUTOFF)?)
}
pub(crate) fn delete_search_cutoff(&self, wtxn: &mut RwTxn<'_>) -> heed::Result<bool> {
self.main.remap_key_type::<Str>().delete(wtxn, main_key::SEARCH_CUTOFF)
}
}
#[cfg(test)]

View file

@ -121,6 +121,12 @@ impl fmt::Debug for TimeBudget {
}
}
impl Default for TimeBudget {
fn default() -> Self {
Self::new(std::time::Duration::from_millis(150))
}
}
impl TimeBudget {
pub fn new(budget: std::time::Duration) -> Self {
Self { started_at: std::time::Instant::now(), budget }

View file

@ -150,6 +150,7 @@ pub struct Settings<'a, 't, 'i> {
pagination_max_total_hits: Setting<usize>,
proximity_precision: Setting<ProximityPrecision>,
embedder_settings: Setting<BTreeMap<String, Setting<EmbeddingSettings>>>,
search_cutoff: Setting<u64>,
}
impl<'a, 't, 'i> Settings<'a, 't, 'i> {
@ -183,6 +184,7 @@ impl<'a, 't, 'i> Settings<'a, 't, 'i> {
pagination_max_total_hits: Setting::NotSet,
proximity_precision: Setting::NotSet,
embedder_settings: Setting::NotSet,
search_cutoff: Setting::NotSet,
indexer_config,
}
}
@ -373,6 +375,14 @@ impl<'a, 't, 'i> Settings<'a, 't, 'i> {
self.embedder_settings = Setting::Reset;
}
pub fn set_search_cutoff(&mut self, value: u64) {
self.search_cutoff = Setting::Set(value);
}
pub fn reset_search_cutoff(&mut self) {
self.search_cutoff = Setting::Reset;
}
#[tracing::instrument(
level = "trace"
skip(self, progress_callback, should_abort, old_fields_ids_map),
@ -1026,6 +1036,24 @@ impl<'a, 't, 'i> Settings<'a, 't, 'i> {
Ok(update)
}
fn update_search_cutoff(&mut self) -> Result<bool> {
let changed = match self.search_cutoff {
Setting::Set(new) => {
let old = self.index.search_cutoff(self.wtxn)?;
if old == Some(new) {
false
} else {
self.index.put_search_cutoff(self.wtxn, new)?;
true
}
}
Setting::Reset => self.index.delete_search_cutoff(self.wtxn)?,
Setting::NotSet => false,
};
Ok(changed)
}
pub fn execute<FP, FA>(mut self, progress_callback: FP, should_abort: FA) -> Result<()>
where
FP: Fn(UpdateIndexingStep) + Sync,
@ -1071,6 +1099,9 @@ impl<'a, 't, 'i> Settings<'a, 't, 'i> {
// 3. Keep the old vectors but reattempt indexing on a prompt change: only actually changed prompt will need embedding + storage
let embedding_configs_updated = self.update_embedding_configs()?;
// never trigger re-indexing
self.update_search_cutoff()?;
if stop_words_updated
|| non_separator_tokens_updated
|| separator_tokens_updated
@ -2027,6 +2058,7 @@ mod tests {
pagination_max_total_hits,
proximity_precision,
embedder_settings,
search_cutoff,
} = settings;
assert!(matches!(searchable_fields, Setting::NotSet));
assert!(matches!(displayed_fields, Setting::NotSet));
@ -2050,6 +2082,7 @@ mod tests {
assert!(matches!(pagination_max_total_hits, Setting::NotSet));
assert!(matches!(proximity_precision, Setting::NotSet));
assert!(matches!(embedder_settings, Setting::NotSet));
assert!(matches!(search_cutoff, Setting::NotSet));
})
.unwrap();
}