Implement semantic embeddings and duplicate review

This commit is contained in:
2026-07-19 18:06:47 +02:00
parent fd4fd744e0
commit e8764262a3
42 changed files with 3808 additions and 79 deletions

View File

@@ -170,15 +170,18 @@ fn rebuild_from_filesystem_inner(
)));
}
progress(0.98, "Refreshing semantic index...");
crate::engine::embedding::EmbeddingService::production(conn, data_dir)
.index_unindexed(project_id)?;
progress(1.0, "Rebuild complete");
Ok(report)
}
fn clear_project_rows(conn: &Connection, project_id: &str) -> EngineResult<()> {
use crate::db::schema::{
dismissed_duplicate_pairs, embedding_keys, generated_file_hashes, import_definitions,
media, media_translations, post_links, post_media, post_translations, posts, scripts, tags,
templates,
generated_file_hashes, import_definitions, media, media_translations, post_links,
post_media, post_translations, posts, scripts, tags, templates,
};
let post_ids = crate::db::queries::post::list_posts_by_project(conn, project_id)?
@@ -219,13 +222,6 @@ fn clear_project_rows(conn: &Connection, project_id: &str) -> EngineResult<()> {
generated_file_hashes::table.filter(generated_file_hashes::project_id.eq(project_id)),
)
.execute(connection)?;
diesel::delete(embedding_keys::table.filter(embedding_keys::project_id.eq(project_id)))
.execute(connection)?;
diesel::delete(
dismissed_duplicate_pairs::table
.filter(dismissed_duplicate_pairs::project_id.eq(project_id)),
)
.execute(connection)?;
diesel::delete(
import_definitions::table.filter(import_definitions::project_id.eq(project_id)),
)