Struct RetrievalQA 

pub struct RetrievalQA { /* private fields */ }

RetrievalQA Chain

One-stop retrieval QA chain that automatically:

1. Retrieves relevant documents
2. Assembles prompt (context + question)
3. LLM generates answer

Implementations

impl RetrievalQA

pub fn new<L>(llm: L, retriever: Arc<dyn RetrieverTrait>) -> Self

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

Create a new RetrievalQA chain with the given LLM and retriever.

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

Set the prompt template.

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_k(self, k: usize) -> Self

Set the number of documents to retrieve.

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

Set verbose mode.

pub fn with_return_source_documents(self, return_source: bool) -> Self

Set whether to return the source documents with the answer.

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

Set the key under which source documents are placed in the output.

pub fn retriever(&self) -> &Arc<dyn RetrieverTrait>

Get the retriever reference.

pub fn k(&self) -> usize

Get the number of documents retrieved (k).

pub async fn query( &self, question: impl Into<String>, ) -> Result<String, ChainError>

Simplified query interface returning the answer string.

pub async fn query_with_sources( &self, question: impl Into<String>, ) -> Result<(String, Vec<Document>), ChainError>

Query the chain, returning both the answer and the retrieved source documents.

Trait Implementations

impl BaseChain for RetrievalQA

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 RetrievalQA – token by token output.

P2-2: real streaming — retrieves and assembles the prompt first, then pushes LLM tokens via stream_chat instead of wrapping invoke in a single chunk (the base default).

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.