Merge branch 'main' into change-proximity-precision-settings

This commit is contained in:
Many the fish 2023-12-18 09:08:47 +01:00 committed by GitHub
commit 9e1b458010
No known key found for this signature in database
GPG key ID: 4AEE18F83AFDEB23
55 changed files with 5801 additions and 723 deletions

View file

@ -13,9 +13,9 @@ use crate::analytics::{Analytics, FacetSearchAggregator};
use crate::extractors::authentication::policies::*;
use crate::extractors::authentication::GuardedData;
use crate::search::{
add_search_rules, perform_facet_search, MatchingStrategy, SearchQuery, DEFAULT_CROP_LENGTH,
DEFAULT_CROP_MARKER, DEFAULT_HIGHLIGHT_POST_TAG, DEFAULT_HIGHLIGHT_PRE_TAG,
DEFAULT_SEARCH_LIMIT, DEFAULT_SEARCH_OFFSET,
add_search_rules, perform_facet_search, HybridQuery, MatchingStrategy, SearchQuery,
DEFAULT_CROP_LENGTH, DEFAULT_CROP_MARKER, DEFAULT_HIGHLIGHT_POST_TAG,
DEFAULT_HIGHLIGHT_PRE_TAG, DEFAULT_SEARCH_LIMIT, DEFAULT_SEARCH_OFFSET,
};
pub fn configure(cfg: &mut web::ServiceConfig) {
@ -36,6 +36,8 @@ pub struct FacetSearchQuery {
pub q: Option<String>,
#[deserr(default, error = DeserrJsonError<InvalidSearchVector>)]
pub vector: Option<Vec<f32>>,
#[deserr(default, error = DeserrJsonError<InvalidHybridQuery>)]
pub hybrid: Option<HybridQuery>,
#[deserr(default, error = DeserrJsonError<InvalidSearchFilter>)]
pub filter: Option<Value>,
#[deserr(default, error = DeserrJsonError<InvalidSearchMatchingStrategy>, default)]
@ -95,6 +97,7 @@ impl From<FacetSearchQuery> for SearchQuery {
filter,
matching_strategy,
attributes_to_search_on,
hybrid,
} = value;
SearchQuery {
@ -119,6 +122,7 @@ impl From<FacetSearchQuery> for SearchQuery {
matching_strategy,
vector,
attributes_to_search_on,
hybrid,
}
}
}

View file

@ -2,12 +2,14 @@ use actix_web::web::Data;
use actix_web::{web, HttpRequest, HttpResponse};
use deserr::actix_web::{AwebJson, AwebQueryParameter};
use index_scheduler::IndexScheduler;
use log::debug;
use log::{debug, warn};
use meilisearch_types::deserr::query_params::Param;
use meilisearch_types::deserr::{DeserrJsonError, DeserrQueryParamError};
use meilisearch_types::error::deserr_codes::*;
use meilisearch_types::error::ResponseError;
use meilisearch_types::index_uid::IndexUid;
use meilisearch_types::milli;
use meilisearch_types::milli::vector::DistributionShift;
use meilisearch_types::serde_cs::vec::CS;
use serde_json::Value;
@ -16,9 +18,9 @@ use crate::extractors::authentication::policies::*;
use crate::extractors::authentication::GuardedData;
use crate::extractors::sequential_extractor::SeqHandler;
use crate::search::{
add_search_rules, perform_search, MatchingStrategy, SearchQuery, DEFAULT_CROP_LENGTH,
DEFAULT_CROP_MARKER, DEFAULT_HIGHLIGHT_POST_TAG, DEFAULT_HIGHLIGHT_PRE_TAG,
DEFAULT_SEARCH_LIMIT, DEFAULT_SEARCH_OFFSET,
add_search_rules, perform_search, HybridQuery, MatchingStrategy, SearchQuery, SemanticRatio,
DEFAULT_CROP_LENGTH, DEFAULT_CROP_MARKER, DEFAULT_HIGHLIGHT_POST_TAG,
DEFAULT_HIGHLIGHT_PRE_TAG, DEFAULT_SEARCH_LIMIT, DEFAULT_SEARCH_OFFSET, DEFAULT_SEMANTIC_RATIO,
};
pub fn configure(cfg: &mut web::ServiceConfig) {
@ -74,6 +76,31 @@ pub struct SearchQueryGet {
matching_strategy: MatchingStrategy,
#[deserr(default, error = DeserrQueryParamError<InvalidSearchAttributesToSearchOn>)]
pub attributes_to_search_on: Option<CS<String>>,
#[deserr(default, error = DeserrQueryParamError<InvalidEmbedder>)]
pub hybrid_embedder: Option<String>,
#[deserr(default, error = DeserrQueryParamError<InvalidSearchSemanticRatio>)]
pub hybrid_semantic_ratio: Option<SemanticRatioGet>,
}
#[derive(Debug, Clone, Copy, Default, PartialEq, deserr::Deserr)]
#[deserr(try_from(String) = TryFrom::try_from -> InvalidSearchSemanticRatio)]
pub struct SemanticRatioGet(SemanticRatio);
impl std::convert::TryFrom<String> for SemanticRatioGet {
type Error = InvalidSearchSemanticRatio;
fn try_from(s: String) -> Result<Self, Self::Error> {
let f: f32 = s.parse().map_err(|_| InvalidSearchSemanticRatio)?;
Ok(SemanticRatioGet(SemanticRatio::try_from(f)?))
}
}
impl std::ops::Deref for SemanticRatioGet {
type Target = SemanticRatio;
fn deref(&self) -> &Self::Target {
&self.0
}
}
impl From<SearchQueryGet> for SearchQuery {
@ -86,6 +113,20 @@ impl From<SearchQueryGet> for SearchQuery {
None => None,
};
let hybrid = match (other.hybrid_embedder, other.hybrid_semantic_ratio) {
(None, None) => None,
(None, Some(semantic_ratio)) => {
Some(HybridQuery { semantic_ratio: *semantic_ratio, embedder: None })
}
(Some(embedder), None) => Some(HybridQuery {
semantic_ratio: DEFAULT_SEMANTIC_RATIO(),
embedder: Some(embedder),
}),
(Some(embedder), Some(semantic_ratio)) => {
Some(HybridQuery { semantic_ratio: *semantic_ratio, embedder: Some(embedder) })
}
};
Self {
q: other.q,
vector: other.vector.map(CS::into_inner),
@ -108,6 +149,7 @@ impl From<SearchQueryGet> for SearchQuery {
crop_marker: other.crop_marker,
matching_strategy: other.matching_strategy,
attributes_to_search_on: other.attributes_to_search_on.map(|o| o.into_iter().collect()),
hybrid,
}
}
}
@ -158,8 +200,12 @@ pub async fn search_with_url_query(
let index = index_scheduler.index(&index_uid)?;
let features = index_scheduler.features();
let distribution = embed(&mut query, index_scheduler.get_ref(), &index).await?;
let search_result =
tokio::task::spawn_blocking(move || perform_search(&index, query, features)).await?;
tokio::task::spawn_blocking(move || perform_search(&index, query, features, distribution))
.await?;
if let Ok(ref search_result) = search_result {
aggregate.succeed(search_result);
}
@ -193,8 +239,12 @@ pub async fn search_with_post(
let index = index_scheduler.index(&index_uid)?;
let features = index_scheduler.features();
let distribution = embed(&mut query, index_scheduler.get_ref(), &index).await?;
let search_result =
tokio::task::spawn_blocking(move || perform_search(&index, query, features)).await?;
tokio::task::spawn_blocking(move || perform_search(&index, query, features, distribution))
.await?;
if let Ok(ref search_result) = search_result {
aggregate.succeed(search_result);
}
@ -206,6 +256,80 @@ pub async fn search_with_post(
Ok(HttpResponse::Ok().json(search_result))
}
pub async fn embed(
query: &mut SearchQuery,
index_scheduler: &IndexScheduler,
index: &milli::Index,
) -> Result<Option<DistributionShift>, ResponseError> {
match (&query.hybrid, &query.vector, &query.q) {
(Some(HybridQuery { semantic_ratio: _, embedder }), None, Some(q))
if !q.trim().is_empty() =>
{
let embedder_configs = index.embedding_configs(&index.read_txn()?)?;
let embedders = index_scheduler.embedders(embedder_configs)?;
let embedder = if let Some(embedder_name) = embedder {
embedders.get(embedder_name)
} else {
embedders.get_default()
};
let embedder = embedder
.ok_or(milli::UserError::InvalidEmbedder("default".to_owned()))
.map_err(milli::Error::from)?
.0;
let distribution = embedder.distribution();
let embeddings = embedder
.embed(vec![q.to_owned()])
.await
.map_err(milli::vector::Error::from)
.map_err(milli::Error::from)?
.pop()
.expect("No vector returned from embedding");
if embeddings.iter().nth(1).is_some() {
warn!("Ignoring embeddings past the first one in long search query");
query.vector = Some(embeddings.iter().next().unwrap().to_vec());
} else {
query.vector = Some(embeddings.into_inner());
}
Ok(distribution)
}
(Some(hybrid), vector, _) => {
let embedder_configs = index.embedding_configs(&index.read_txn()?)?;
let embedders = index_scheduler.embedders(embedder_configs)?;
let embedder = if let Some(embedder_name) = &hybrid.embedder {
embedders.get(embedder_name)
} else {
embedders.get_default()
};
let embedder = embedder
.ok_or(milli::UserError::InvalidEmbedder("default".to_owned()))
.map_err(milli::Error::from)?
.0;
if let Some(vector) = vector {
if vector.len() != embedder.dimensions() {
return Err(meilisearch_types::milli::Error::UserError(
meilisearch_types::milli::UserError::InvalidVectorDimensions {
expected: embedder.dimensions(),
found: vector.len(),
},
)
.into());
}
}
Ok(embedder.distribution())
}
_ => Ok(None),
}
}
#[cfg(test)]
mod test {
use super::*;

View file

@ -7,6 +7,7 @@ use meilisearch_types::deserr::DeserrJsonError;
use meilisearch_types::error::ResponseError;
use meilisearch_types::facet_values_sort::FacetValuesSort;
use meilisearch_types::index_uid::IndexUid;
use meilisearch_types::milli::update::Setting;
use meilisearch_types::settings::{settings, RankingRuleView, Settings, Unchecked};
use meilisearch_types::tasks::KindWithContent;
use serde_json::json;
@ -546,6 +547,67 @@ make_setting_route!(
}
);
make_setting_route!(
"/embedders",
patch,
std::collections::BTreeMap<String, Setting<meilisearch_types::milli::vector::settings::EmbeddingSettings>>,
meilisearch_types::deserr::DeserrJsonError<
meilisearch_types::error::deserr_codes::InvalidSettingsEmbedders,
>,
embedders,
"embedders",
analytics,
|setting: &Option<std::collections::BTreeMap<String, Setting<meilisearch_types::milli::vector::settings::EmbeddingSettings>>>, req: &HttpRequest| {
analytics.publish(
"Embedders Updated".to_string(),
serde_json::json!({"embedders": crate::routes::indexes::settings::embedder_analytics(setting.as_ref())}),
Some(req),
);
}
);
fn embedder_analytics(
setting: Option<
&std::collections::BTreeMap<
String,
Setting<meilisearch_types::milli::vector::settings::EmbeddingSettings>,
>,
>,
) -> serde_json::Value {
let mut sources = std::collections::HashSet::new();
if let Some(s) = &setting {
for source in s
.values()
.filter_map(|config| config.clone().set())
.filter_map(|config| config.embedder_options.set())
{
use meilisearch_types::milli::vector::settings::EmbedderSettings;
match source {
EmbedderSettings::OpenAi(_) => sources.insert("openAi"),
EmbedderSettings::HuggingFace(_) => sources.insert("huggingFace"),
EmbedderSettings::UserProvided(_) => sources.insert("userProvided"),
};
}
};
let document_template_used = setting.as_ref().map(|map| {
map.values()
.filter_map(|config| config.clone().set())
.any(|config| config.document_template.set().is_some())
});
json!(
{
"total": setting.as_ref().map(|s| s.len()),
"sources": sources,
"document_template_used": document_template_used,
}
)
}
macro_rules! generate_configure {
($($mod:ident),*) => {
pub fn configure(cfg: &mut web::ServiceConfig) {
@ -575,7 +637,8 @@ generate_configure!(
ranking_rules,
typo_tolerance,
pagination,
faceting
faceting,
embedders
);
pub async fn update_all(
@ -682,6 +745,7 @@ pub async fn update_all(
"synonyms": {
"total": new_settings.synonyms.as_ref().set().map(|synonyms| synonyms.len()),
},
"embedders": crate::routes::indexes::settings::embedder_analytics(new_settings.embedders.as_ref().set())
}),
Some(&req),
);

View file

@ -13,6 +13,7 @@ use crate::analytics::{Analytics, MultiSearchAggregator};
use crate::extractors::authentication::policies::ActionPolicy;
use crate::extractors::authentication::{AuthenticationError, GuardedData};
use crate::extractors::sequential_extractor::SeqHandler;
use crate::routes::indexes::search::embed;
use crate::search::{
add_search_rules, perform_search, SearchQueryWithIndex, SearchResultWithIndex,
};
@ -74,10 +75,15 @@ pub async fn multi_search_with_post(
})
.with_index(query_index)?;
let search_result =
tokio::task::spawn_blocking(move || perform_search(&index, query, features))
.await
.with_index(query_index)?;
let distribution = embed(&mut query, index_scheduler.get_ref(), &index)
.await
.with_index(query_index)?;
let search_result = tokio::task::spawn_blocking(move || {
perform_search(&index, query, features, distribution)
})
.await
.with_index(query_index)?;
search_results.push(SearchResultWithIndex {
index_uid: index_uid.into_inner(),