Struct PipelineRetriever 

pub struct PipelineRetriever { /* private fields */ }

Pipeline-based retriever using the stage architecture.

This retriever uses the new pipeline architecture with:

• Analyze stage: Query complexity and keyword extraction
• Plan stage: Strategy and algorithm selection
• Search stage: Tree traversal
• Evaluate stage: Sufficiency checking

Example

let retriever = PipelineRetriever::new()
    .with_llm_client(llm_client);

let response = retriever.retrieve(&tree, "query", &options).await?;

Implementations

impl PipelineRetriever

pub fn new() -> Self

Create a new pipeline retriever.

pub fn with_llm_client(self, client: LlmClient) -> Self

Add LLM client for enhanced retrieval.

pub fn with_max_backtracks(self, n: usize) -> Self

Set maximum backtracks for incremental retrieval.

pub fn with_max_iterations(self, n: usize) -> Self

Set maximum total iterations.

pub fn with_content_config(self, config: ContentAggregatorConfig) -> Self

Set content aggregator configuration.

When enabled, the Evaluate stage uses precision-focused content aggregation with relevance scoring and token budget control.

Trait Implementations

impl Clone for PipelineRetriever

fn clone(&self) -> Self

Returns a duplicate of the value.

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

Performs copy-assignment from source.

impl Default for PipelineRetriever

fn default() -> Self

Returns the “default value” for a type.

impl Retriever for PipelineRetriever

fn retrieve<'life0, 'life1, 'life2, 'life3, 'async_trait>( &'life0 self, tree: &'life1 DocumentTree, query: &'life2 str, options: &'life3 RetrieveOptions, ) -> Pin<Box<dyn Future<Output = RetrieverResult<RetrieveResponse>> + Send + 'async_trait>>

where Self: 'async_trait, 'life0: 'async_trait, 'life1: 'async_trait, 'life2: 'async_trait, 'life3: 'async_trait,

Retrieve relevant content for the given query.

fn name(&self) -> &'static str

Get the name of this retriever for logging/debugging.

fn supports_options(&self, _options: &RetrieveOptions) -> bool

Check if this retriever supports the given options.

fn estimate_cost( &self, tree: &DocumentTree, options: &RetrieveOptions, ) -> CostEstimate

Estimate the cost of a retrieval operation.