snowykami/meilisearch
1
0
Fork 0
mirror of https://github.com/meilisearch/meilisearch.git synced 2025-07-27 00:31:02 +00:00
Code Issues Packages Projects Releases Wiki Activity

Add embedding cache

Browse Source
This commit is contained in:
Louis Dureuil
2025-03-13 11:13:14 +01:00
parent d9111fe8ce
commit b08544e86d
8 changed files with 159 additions and 19 deletions
Download Patch File Download Diff File Expand all files Collapse all files

34
crates/milli/src/vector/composite.rs
View File

@ -4,7 +4,8 @@ use arroy::Distance;
use super::error::CompositeEmbedderContainsHuggingFace;
use super::{
hf, manual, ollama, openai, rest, DistributionShift, EmbedError, Embedding, NewEmbedderError,
hf, manual, ollama, openai, rest, DistributionShift, EmbedError, Embedding, EmbeddingCache,
NewEmbedderError,
};
use crate::ThreadPoolNoAbort;
@ -148,6 +149,27 @@ impl SubEmbedder {
}
}
pub fn embed_one(
&self,
text: &str,
deadline: Option<Instant>,
) -> std::result::Result<Embedding, EmbedError> {
match self {
SubEmbedder::HuggingFace(embedder) => embedder.embed_one(text),
SubEmbedder::OpenAi(embedder) => {
embedder.embed(&[text], deadline)?.pop().ok_or_else(EmbedError::missing_embedding)
}
SubEmbedder::Ollama(embedder) => {
embedder.embed(&[text], deadline)?.pop().ok_or_else(EmbedError::missing_embedding)
}
SubEmbedder::UserProvided(embedder) => embedder.embed_one(text),
SubEmbedder::Rest(embedder) => embedder
.embed_ref(&[text], deadline)?
.pop()
.ok_or_else(EmbedError::missing_embedding),
}
}
/// Embed multiple chunks of texts.
///
/// Each chunk is composed of one or multiple texts.
@ -233,6 +255,16 @@ impl SubEmbedder {
SubEmbedder::Rest(embedder) => embedder.distribution(),
}
}
pub(super) fn cache(&self) -> Option<&EmbeddingCache> {
match self {
SubEmbedder::HuggingFace(embedder) => Some(embedder.cache()),
SubEmbedder::OpenAi(embedder) => Some(embedder.cache()),
SubEmbedder::UserProvided(_) => None,
SubEmbedder::Ollama(embedder) => Some(embedder.cache()),
SubEmbedder::Rest(embedder) => Some(embedder.cache()),
}
}
}
fn check_similarity(