Struct EmbeddingEngine 

pub struct EmbeddingEngine { /* private fields */ }

Implementations

impl EmbeddingEngine

pub fn new(project: &ProjectRoot) -> Result<Self>

pub fn model_name(&self) -> &str

pub fn runtime_info(&self) -> &EmbeddingRuntimeInfo

pub fn is_indexing(&self) -> bool

Index all symbols from the project’s symbol database into the embedding index.

Reconciles the embedding store file-by-file so unchanged symbols can reuse their existing vectors and only changed/new symbols are re-embedded. Caps at a configurable max to prevent runaway on huge projects. Returns true if a full reindex is currently in progress.

pub fn index_from_project(&self, project: &ProjectRoot) -> Result<usize>

pub fn search( &self, query: &str, max_results: usize, ) -> Result<Vec<SemanticMatch>>

Search for symbols semantically similar to the query.

pub fn search_scored( &self, query: &str, max_results: usize, ) -> Result<Vec<ScoredChunk>>

Search returning raw ScoredChunks (for ranking integration). When a cross-encoder reranker is loaded, fetches 3× candidates from the bi-encoder and reranks to return the top max_results.

pub fn index_changed_files( &self, project: &ProjectRoot, changed_files: &[&str], ) -> Result<usize>

Incrementally re-index only the given files.

pub fn is_indexed(&self) -> bool

Whether the embedding index has been populated.

pub fn index_info(&self) -> EmbeddingIndexInfo

pub fn inspect_existing_index( project: &ProjectRoot, ) -> Result<Option<EmbeddingIndexInfo>>

pub fn find_similar_code( &self, file_path: &str, symbol_name: &str, max_results: usize, ) -> Result<Vec<SemanticMatch>>

Find code symbols most similar to the given symbol.

pub fn find_duplicates( &self, threshold: f64, max_pairs: usize, ) -> Result<Vec<DuplicatePair>>

Find near-duplicate code pairs across the codebase. Returns pairs with cosine similarity above the threshold (default 0.85).

impl EmbeddingEngine

pub fn classify_symbol( &self, file_path: &str, symbol_name: &str, categories: &[&str], ) -> Result<Vec<CategoryScore>>

Classify a code symbol into one of the given categories using zero-shot embedding similarity.

pub fn find_misplaced_code( &self, max_results: usize, ) -> Result<Vec<OutlierSymbol>>

Find symbols that are outliers — semantically distant from their file’s other symbols.