Struct MapRerankDocumentsChain 

pub struct MapRerankDocumentsChain { /* private fields */ }

MapRerankDocumentsChain

First calls LLM independently for each document to generate an answer and score, then ranks by relevance score and returns the highest-scoring answer.

Implementations

impl MapRerankDocumentsChain

pub fn new<L>(llm: L) -> Self

where L: BaseChatModel + Send + Sync + 'static, L::Error: Into<ProviderError>,

Create a new MapRerankDocumentsChain with the given LLM.

pub fn with_map_prompt(self, template: impl Into<String>) -> Self

Set the map-phase prompt template.

pub fn with_document_variable(self, name: impl Into<String>) -> Self

Set the document variable name used in the map prompt.

pub fn with_input_key(self, key: impl Into<String>) -> Self

Set the input key.

pub fn with_output_key(self, key: impl Into<String>) -> Self

Set the output key.

pub fn with_name(self, name: impl Into<String>) -> Self

Set the chain name.

pub fn with_verbose(self, verbose: bool) -> Self

Set verbose mode.

pub fn with_top_k(self, k: usize) -> Self

Set the number of top results to return.

pub fn with_default_score(self, score: u32) -> Self

Configure the fallback score for LLM output without a parseable score.

None (default) skips such documents; Some(n) ranks them with score n instead of silently assigning the old middle score 50 (P1-3).

pub fn build_map_prompt(&self, context: &str, input: &str) -> String

Build Map stage prompt.

pub async fn invoke_with_documents( &self, documents: Vec<Document>, input: &str, ) -> Result<Vec<(u32, String)>, ChainError>

Invoke with documents and input directly.

Trait Implementations

impl BaseChain for MapRerankDocumentsChain

fn stream<'life0, 'async_trait>( &'life0 self, inputs: HashMap<String, Value>, ) -> Pin<Box<dyn Future<Output = Result<ChainStream, ChainError>> + Send + 'async_trait>>

where Self: 'async_trait, 'life0: 'async_trait,

Stream execution for MapRerankDocumentsChain.

P2-2: the map phase runs via stream_chat per document (tokens accumulated for scoring), then the reranked top answer(s) are emitted. Raw token streaming of the final answer is impossible here — ranking requires each document’s complete output — so the ranked result is the stream payload, produced without the base default’s silent unwrap_or("").

fn input_keys(&self) -> Vec<&str>

Get input keys.

fn output_keys(&self) -> Vec<&str>

Get output keys.

fn invoke<'life0, 'async_trait>( &'life0 self, inputs: HashMap<String, Value>, ) -> Pin<Box<dyn Future<Output = Result<ChainResult, ChainError>> + Send + 'async_trait>>

where Self: 'async_trait, 'life0: 'async_trait,

Execute the Chain.

fn name(&self) -> &str

Get Chain name.

fn invoke_with_config<'life0, 'async_trait>( &'life0 self, inputs: HashMap<String, Value>, config: Option<RunnableConfig>, ) -> Pin<Box<dyn Future<Output = Result<ChainResult, ChainError>> + Send + 'async_trait>>

where Self: 'async_trait, 'life0: 'async_trait,

Execute the Chain with a RunnableConfig.

fn stream_with_config<'life0, 'async_trait>( &'life0 self, inputs: HashMap<String, Value>, config: Option<RunnableConfig>, ) -> Pin<Box<dyn Future<Output = Result<ChainStream, ChainError>> + Send + 'async_trait>>

where Self: 'async_trait, 'life0: 'async_trait,

Stream execute the Chain with a RunnableConfig.

fn validate_inputs( &self, inputs: &HashMap<String, Value>, ) -> Result<(), ChainError>

Validate inputs.