collab: Remove unused embeddings queries and model (#42463)

This PR removes the queries and database model for embeddings, as
they're no longer used.

Release Notes:

- N/A
This commit is contained in:
Marshall Bowers
2025-11-11 16:13:59 +00:00
committed by GitHub
parent 0268b17096
commit 03acbb7de3
7 changed files with 1 additions and 207 deletions
-1
View File
@@ -5,7 +5,6 @@ pub mod buffers;
pub mod channels;
pub mod contacts;
pub mod contributors;
pub mod embeddings;
pub mod extensions;
pub mod notifications;
pub mod projects;
@@ -1,94 +0,0 @@
use super::*;
use time::Duration;
use time::OffsetDateTime;
impl Database {
pub async fn get_embeddings(
&self,
model: &str,
digests: &[Vec<u8>],
) -> Result<HashMap<Vec<u8>, Vec<f32>>> {
self.transaction(|tx| async move {
let embeddings = {
let mut db_embeddings = embedding::Entity::find()
.filter(
embedding::Column::Model.eq(model).and(
embedding::Column::Digest
.is_in(digests.iter().map(|digest| digest.as_slice())),
),
)
.stream(&*tx)
.await?;
let mut embeddings = HashMap::default();
while let Some(db_embedding) = db_embeddings.next().await {
let db_embedding = db_embedding?;
embeddings.insert(db_embedding.digest, db_embedding.dimensions);
}
embeddings
};
if !embeddings.is_empty() {
let now = OffsetDateTime::now_utc();
let retrieved_at = PrimitiveDateTime::new(now.date(), now.time());
embedding::Entity::update_many()
.filter(
embedding::Column::Digest
.is_in(embeddings.keys().map(|digest| digest.as_slice())),
)
.col_expr(embedding::Column::RetrievedAt, Expr::value(retrieved_at))
.exec(&*tx)
.await?;
}
Ok(embeddings)
})
.await
}
pub async fn save_embeddings(
&self,
model: &str,
embeddings: &HashMap<Vec<u8>, Vec<f32>>,
) -> Result<()> {
self.transaction(|tx| async move {
embedding::Entity::insert_many(embeddings.iter().map(|(digest, dimensions)| {
let now_offset_datetime = OffsetDateTime::now_utc();
let retrieved_at =
PrimitiveDateTime::new(now_offset_datetime.date(), now_offset_datetime.time());
embedding::ActiveModel {
model: ActiveValue::set(model.to_string()),
digest: ActiveValue::set(digest.clone()),
dimensions: ActiveValue::set(dimensions.clone()),
retrieved_at: ActiveValue::set(retrieved_at),
}
}))
.on_conflict(
OnConflict::columns([embedding::Column::Model, embedding::Column::Digest])
.do_nothing()
.to_owned(),
)
.exec_without_returning(&*tx)
.await?;
Ok(())
})
.await
}
pub async fn purge_old_embeddings(&self) -> Result<()> {
self.transaction(|tx| async move {
embedding::Entity::delete_many()
.filter(
embedding::Column::RetrievedAt
.lte(OffsetDateTime::now_utc() - Duration::days(60)),
)
.exec(&*tx)
.await?;
Ok(())
})
.await
}
}
-1
View File
@@ -8,7 +8,6 @@ pub mod channel_chat_participant;
pub mod channel_member;
pub mod contact;
pub mod contributor;
pub mod embedding;
pub mod extension;
pub mod extension_version;
pub mod follower;
-18
View File
@@ -1,18 +0,0 @@
use sea_orm::entity::prelude::*;
use time::PrimitiveDateTime;
#[derive(Clone, Debug, PartialEq, DeriveEntityModel)]
#[sea_orm(table_name = "embeddings")]
pub struct Model {
#[sea_orm(primary_key)]
pub model: String,
#[sea_orm(primary_key)]
pub digest: Vec<u8>,
pub dimensions: Vec<f32>,
pub retrieved_at: PrimitiveDateTime,
}
#[derive(Copy, Clone, Debug, EnumIter, DeriveRelation)]
pub enum Relation {}
impl ActiveModelBehavior for ActiveModel {}
-3
View File
@@ -2,9 +2,6 @@ mod buffer_tests;
mod channel_tests;
mod contributor_tests;
mod db_tests;
// we only run postgres tests on macos right now
#[cfg(target_os = "macos")]
mod embedding_tests;
mod extension_tests;
use crate::migrations::run_database_migrations;
@@ -1,87 +0,0 @@
use super::TestDb;
use crate::db::embedding;
use collections::HashMap;
use sea_orm::{ColumnTrait, EntityTrait, QueryFilter, sea_query::Expr};
use std::ops::Sub;
use time::{Duration, OffsetDateTime, PrimitiveDateTime};
// SQLite does not support array arguments, so we only test this against a real postgres instance
#[gpui::test]
async fn test_get_embeddings_postgres(cx: &mut gpui::TestAppContext) {
let test_db = TestDb::postgres(cx.executor());
let db = test_db.db();
let provider = "test_model";
let digest1 = vec![1, 2, 3];
let digest2 = vec![4, 5, 6];
let embeddings = HashMap::from_iter([
(digest1.clone(), vec![0.1, 0.2, 0.3]),
(digest2.clone(), vec![0.4, 0.5, 0.6]),
]);
// Save embeddings
db.save_embeddings(provider, &embeddings).await.unwrap();
// Retrieve embeddings
let retrieved_embeddings = db
.get_embeddings(provider, &[digest1.clone(), digest2.clone()])
.await
.unwrap();
assert_eq!(retrieved_embeddings.len(), 2);
assert!(retrieved_embeddings.contains_key(&digest1));
assert!(retrieved_embeddings.contains_key(&digest2));
// Check if the retrieved embeddings are correct
assert_eq!(retrieved_embeddings[&digest1], vec![0.1, 0.2, 0.3]);
assert_eq!(retrieved_embeddings[&digest2], vec![0.4, 0.5, 0.6]);
}
#[gpui::test]
async fn test_purge_old_embeddings(cx: &mut gpui::TestAppContext) {
let test_db = TestDb::postgres(cx.executor());
let db = test_db.db();
let model = "test_model";
let digest = vec![7, 8, 9];
let embeddings = HashMap::from_iter([(digest.clone(), vec![0.7, 0.8, 0.9])]);
// Save old embeddings
db.save_embeddings(model, &embeddings).await.unwrap();
// Reach into the DB and change the retrieved at to be > 60 days
db.transaction(|tx| {
let digest = digest.clone();
async move {
let sixty_days_ago = OffsetDateTime::now_utc().sub(Duration::days(61));
let retrieved_at = PrimitiveDateTime::new(sixty_days_ago.date(), sixty_days_ago.time());
embedding::Entity::update_many()
.filter(
embedding::Column::Model
.eq(model)
.and(embedding::Column::Digest.eq(digest)),
)
.col_expr(embedding::Column::RetrievedAt, Expr::value(retrieved_at))
.exec(&*tx)
.await
.unwrap();
Ok(())
}
})
.await
.unwrap();
// Purge old embeddings
db.purge_old_embeddings().await.unwrap();
// Try to retrieve the purged embeddings
let retrieved_embeddings = db
.get_embeddings(model, std::slice::from_ref(&digest))
.await
.unwrap();
assert!(
retrieved_embeddings.is_empty(),
"Old embeddings should have been purged"
);
}
+1 -3
View File
@@ -13,7 +13,7 @@ use collab::llm::db::LlmDatabase;
use collab::migrations::run_database_migrations;
use collab::{
AppState, Config, Result, api::fetch_extensions_from_blob_store_periodically, db, env,
executor::Executor, rpc::ResultExt,
executor::Executor,
};
use db::Database;
use std::{
@@ -95,8 +95,6 @@ async fn main() -> Result<()> {
let state = AppState::new(config, Executor::Production).await?;
if mode.is_collab() {
state.db.purge_old_embeddings().await.trace_err();
let epoch = state
.db
.create_server(&state.config.zed_environment)