EmbeddingConfigs -> RuntimeEmbedders

This commit is contained in:
Louis Dureuil 2025-06-30 00:07:32 +02:00
parent 422a786ffd
commit 5716ab70f3
No known key found for this signature in database
19 changed files with 118 additions and 117 deletions

View file

@ -57,12 +57,15 @@ use meilisearch_types::features::{
use meilisearch_types::heed::byteorder::BE;
use meilisearch_types::heed::types::{DecodeIgnore, SerdeJson, Str, I128};
use meilisearch_types::heed::{self, Database, Env, RoTxn, WithoutTls};
use meilisearch_types::milli::index::IndexEmbeddingConfig;
use meilisearch_types::milli::update::IndexerConfig;
use meilisearch_types::milli::vector::{Embedder, EmbedderOptions, EmbeddingConfigs};
use meilisearch_types::milli::vector::json_template::JsonTemplate;
use meilisearch_types::milli::vector::{
Embedder, EmbedderOptions, RuntimeEmbedder, RuntimeEmbedders, RuntimeFragment,
};
use meilisearch_types::milli::{self, Index};
use meilisearch_types::task_view::TaskView;
use meilisearch_types::tasks::{KindWithContent, Task};
use milli::vector::db::IndexEmbeddingConfig;
use processing::ProcessingTasks;
pub use queue::Query;
use queue::Queue;
@ -851,29 +854,42 @@ impl IndexScheduler {
&self,
index_uid: String,
embedding_configs: Vec<IndexEmbeddingConfig>,
) -> Result<EmbeddingConfigs> {
) -> Result<RuntimeEmbedders> {
let res: Result<_> = embedding_configs
.into_iter()
.map(
|IndexEmbeddingConfig {
name,
config: milli::vector::EmbeddingConfig { embedder_options, prompt, quantized },
..
}| {
let prompt = Arc::new(
prompt
.try_into()
.map_err(meilisearch_types::milli::Error::from)
.map_err(|err| Error::from_milli(err, Some(index_uid.clone())))?,
);
fragments,
}|
-> Result<(String, Arc<RuntimeEmbedder>)> {
let document_template = prompt
.try_into()
.map_err(meilisearch_types::milli::Error::from)
.map_err(|err| Error::from_milli(err, Some(index_uid.clone())))?;
let fragments = fragments
.into_inner()
.into_iter()
.map(|fragment| {
let value = embedder_options.fragment(&fragment.name).unwrap();
let template = JsonTemplate::new(value.clone()).unwrap();
RuntimeFragment { name: fragment.name, id: fragment.id, template }
})
.collect();
// optimistically return existing embedder
{
let embedders = self.embedders.read().unwrap();
if let Some(embedder) = embedders.get(&embedder_options) {
return Ok((
name,
(embedder.clone(), prompt, quantized.unwrap_or_default()),
));
let runtime = Arc::new(RuntimeEmbedder {
embedder: embedder.clone(),
document_template,
fragments,
is_quantized: quantized.unwrap_or_default(),
});
return Ok((name, runtime));
}
}
@ -889,11 +905,19 @@ impl IndexScheduler {
let mut embedders = self.embedders.write().unwrap();
embedders.insert(embedder_options, embedder.clone());
}
Ok((name, (embedder, prompt, quantized.unwrap_or_default())))
let runtime = Arc::new(RuntimeEmbedder {
embedder: embedder.clone(),
document_template,
fragments,
is_quantized: quantized.unwrap_or_default(),
});
Ok((name, runtime))
},
)
.collect();
res.map(EmbeddingConfigs::new)
res.map(RuntimeEmbedders::new)
}
pub fn chat_settings(&self, uid: &str) -> Result<Option<ChatCompletionSettings>> {

View file

@ -165,9 +165,6 @@ impl IndexScheduler {
let fields_ids_map = index.fields_ids_map(&rtxn)?;
let all_fields: Vec<_> = fields_ids_map.iter().map(|(id, _)| id).collect();
let embedding_configs = index
.embedding_configs(&rtxn)
.map_err(|e| Error::from_milli(e, Some(uid.to_string())))?;
let nb_documents = index
.number_of_documents(&rtxn)
@ -221,16 +218,12 @@ impl IndexScheduler {
return Err(Error::from_milli(user_err, Some(uid.to_string())));
};
for (embedder_name, embeddings) in embeddings {
let user_provided = embedding_configs
.iter()
.find(|conf| conf.name == embedder_name)
.is_some_and(|conf| conf.user_provided.contains(id));
for (embedder_name, (embeddings, regenerate)) in embeddings {
let embeddings = ExplicitVectors {
embeddings: Some(VectorOrArrayOfVectors::from_array_of_vectors(
embeddings,
)),
regenerate: !user_provided,
regenerate,
};
vectors.insert(embedder_name, serde_json::to_value(embeddings).unwrap());
}

View file

@ -89,8 +89,9 @@ impl IndexScheduler {
let mut content_files_iter = content_files.iter();
let mut indexer = indexer::DocumentOperation::new();
let embedders = index
.embedding_configs()
.embedding_configs(index_wtxn)
.map_err(|e| Error::from_milli(e, Some(index_uid.clone())))?;
.map_err(|e| Error::from_milli(e.into(), Some(index_uid.clone())))?;
let embedders = self.embedders(index_uid.clone(), embedders)?;
for operation in operations {
match operation {
@ -274,8 +275,9 @@ impl IndexScheduler {
})
.unwrap()?;
let embedders = index
.embedding_configs()
.embedding_configs(index_wtxn)
.map_err(|err| Error::from_milli(err, Some(index_uid.clone())))?;
.map_err(|err| Error::from_milli(err.into(), Some(index_uid.clone())))?;
let embedders = self.embedders(index_uid.clone(), embedders)?;
progress.update_progress(DocumentEditionProgress::Indexing);
@ -423,8 +425,9 @@ impl IndexScheduler {
indexer.delete_documents_by_docids(to_delete);
let document_changes = indexer.into_changes(&indexer_alloc, primary_key);
let embedders = index
.embedding_configs()
.embedding_configs(index_wtxn)
.map_err(|err| Error::from_milli(err, Some(index_uid.clone())))?;
.map_err(|err| Error::from_milli(err.into(), Some(index_uid.clone())))?;
let embedders = self.embedders(index_uid.clone(), embedders)?;
progress.update_progress(DocumentDeletionProgress::Indexing);

View file

@ -3,11 +3,11 @@ use std::collections::BTreeMap;
use big_s::S;
use meili_snap::{json_string, snapshot};
use meilisearch_auth::AuthFilter;
use meilisearch_types::milli::index::IndexEmbeddingConfig;
use meilisearch_types::milli::update::IndexDocumentsMethod::*;
use meilisearch_types::milli::{self};
use meilisearch_types::settings::SettingEmbeddingSettings;
use meilisearch_types::tasks::{IndexSwap, KindWithContent};
use milli::vector::db::IndexEmbeddingConfig;
use roaring::RoaringBitmap;
use crate::insta_snapshot::snapshot_index_scheduler;