Struct Engine 

pub struct Engine { /* private fields */ }

The main Engine client.

Provides high-level operations for document indexing and retrieval. Uses interior mutability to allow sharing across async tasks.

Cloning

Cloning is cheap - it only increments reference counts (Arc). All clones share the same underlying resources.

Thread Safety

The client is Clone + Send + Sync and can be safely shared across threads.

Implementations

impl Engine

pub fn builder() -> EngineBuilder

Create a builder for custom configuration.

pub async fn index(&self, path: impl AsRef<Path>) -> Result<String>

Index a document from a file path.

Returns a unique document ID.

Errors

Returns an error if:

• The file does not exist
• The file format is not supported
• The pipeline execution fails

pub async fn index_with_options( &self, path: impl AsRef<Path>, options: IndexOptions, ) -> Result<String>

Index a document with custom options.

Errors

See Engine::index.

pub async fn query(&self, doc_id: &str, question: &str) -> Result<QueryResult>

Query a document.

Uses the adaptive retriever to find relevant content.

Errors

Returns an error if:

• No workspace is configured
• The document is not found
• The retrieval fails

pub async fn query_with_context( &self, doc_id: &str, question: &str, ctx: &ClientContext, ) -> Result<QueryResult>

Query a document with context.

Allows request-specific configuration overrides.

pub fn session(&self) -> Session

Create a session for multi-document operations.

Sessions provide:

• Automatic caching of document trees
• Cross-document queries
• Session statistics

pub fn list_documents(&self) -> Vec<DocumentInfo>

Get a list of all indexed documents.

pub fn get_structure(&self, doc_id: &str) -> Result<DocumentTree>

Get document structure (tree).

Errors

Returns an error if:

• No workspace is configured
• The document is not found

pub fn get_page_content(&self, doc_id: &str, pages: &str) -> Result<String>

Get page content for PDFs.

Errors

Returns an error if:

• No workspace is configured
• The document is not found
• No page content is available

pub fn load(&self, doc_id: &str) -> Result<bool>

Load a document from the workspace into cache.

This preloads the document into the LRU cache for faster access.

Errors

Returns an error if no workspace is configured.

pub fn remove(&self, doc_id: &str) -> Result<bool>

Remove a document from the workspace.

Errors

Returns an error if no workspace is configured.

pub fn exists(&self, doc_id: &str) -> Result<bool>

Check if a document exists in the workspace.

Errors

Returns an error if no workspace is configured.

pub fn get_metadata(&self, doc_id: &str) -> Result<Option<DocumentInfo>>

Get metadata for a document.

Errors

Returns an error if no workspace is configured.

pub fn batch_remove(&self, doc_ids: &[&str]) -> Result<usize>

Remove multiple documents from the workspace.

Returns the number of documents successfully removed.

Errors

Returns an error if no workspace is configured.

pub fn clear(&self) -> Result<usize>

Remove all documents from the workspace.

Returns the number of documents removed.

Errors

Returns an error if no workspace is configured.

pub fn len(&self) -> usize

Get the number of indexed documents.

pub fn is_empty(&self) -> bool

Check if there are no documents.

pub fn indexer(&self) -> &IndexerClient

Get the indexer client.

pub fn retriever(&self) -> &RetrieverClient

Get the retriever client.

pub fn workspace(&self) -> Option<&WorkspaceClient>

Get the workspace client.

pub fn config(&self) -> &Config

Get the configuration.

Trait Implementations

impl Clone for Engine

fn clone(&self) -> Self

Returns a duplicate of the value.

fn clone_from(&mut self, source: &Self)

Performs copy-assignment from source.

impl Debug for Engine

fn fmt(&self, f: &mut Formatter<'_>) -> Result

Formats the value using the given formatter.

impl Default for Engine

fn default() -> Self

Returns the “default value” for a type.