AgenticRerankerRetriever

Retriever

DashAI.back.models.RAG.retrievers.composite.AgenticRerankerRetriever

---

Selects the best top_k candidates from a child with an LLM.

The child is queried with k1 as a retrieval-size hint. Its output is deduplicated and capped to k1; when it already fits top_k the model is skipped and the candidates are returned unchanged. Otherwise the model receives the numbered candidates and must return up to top_k 1-based indices through the select_best_chunks function call. The configured llm_model must support function calling.

Parameters

enable_retrieve_then_expand : boolean, default=False

Widen each retrieved chunk with its neighbouring chunks before the chunks are returned as the retriever's context.

expand_window : integer, default=3

Total number of chunks in the expanded window, the retrieved one included. Odd values are centred exactly on the retrieved chunk; even values keep the extra chunk after it. Windows never leave the document, and overlapping windows merge into one concatenated chunk.

children : array, default=[{'component': 'ParallelRetriever', 'params': {'children': [{'component': 'BM25Retriever', 'params': {'b': 0.75, 'delta': 0.0, 'k1': 1.5, 'similarity_function': 'cosine', 'top_k': 5, 'vectorizer': {'component': 'BagOfWordsConverter', 'params': {'analyzer': 'word', 'custom_stop_words': None, 'drop_source_columns': False, 'lower_bound_ngrams': 1, 'lowercase': True, 'max_df': 1.0, 'max_features': None, 'min_df': 0.0, 'stop_words': None, 'strip_accents': None, 'upper_bound_ngrams': 1}}}}, {'component': 'DenseEmbeddingRetriever', 'params': {'embedding_model': {'component': 'ParaphraseMultilingualMiniLML12V2Embedding', 'params': {'batch_size': 32, 'device': 'CPU', 'normalize': True, 'overflow_strategy': 'truncate'}}, 'similarity_metric': 'cosine', 'top_k': 5}}], 'merge_strategy': 'round_robin'}}]

The single child retriever that supplies the candidate chunks. Defaults to the default hybrid retriever; you can change it.

k1 : integer, default=10

Number of candidate chunks fetched from the child retriever.

top_k : integer, default=5

Number of best chunks the model selects. Cannot exceed k1.

function_call_max_trials : integer, default=3

Maximum number of selection attempts on the configured route, including the first. Malformed or invalid selections are retried up to this limit; unexpected backend exception types propagate instead of being retried.

prompt : object

The prompt used to select the best candidate chunks.

llm_model : object

The language model that selects the best chunks. Defaults to the default RAG function-calling LLM; you can change it.

Methods

add(self, child: 'BaseRetriever') -> 'None'

Defined on AgenticRerankerRetriever

Reject adding a child after construction.

Parameters

child : BaseRetriever

The child that would be added; ignored.

close(self) -> 'None'

Defined on AgenticRerankerRetriever

Release the selection LLM and then the child retriever.

Returns

None

Nothing.

remove(self, child: 'BaseRetriever') -> 'None'

Defined on AgenticRerankerRetriever

Reject removing the child after construction.

Parameters

child : BaseRetriever

The child that would be removed; ignored.

retrieve(self, query: 'str', **kwargs: 'Any') -> 'Tuple[List[Chunk], Dict[str, Any]]'

Defined on AgenticRerankerRetriever

Retrieve candidates from the child and select the best ones.

Parameters

query : str

The search query string.

**kwargs

Ignored. A parent composite may pass a top_k hint, but the reranker retriever keeps its own configured k1 candidate budget and top_k final budget.

Returns

Tuple[List[Chunk], Dict[str, Any]]

The selected chunks and this retriever's trace node, whose children holds the child node and whose selection holds a JSON-serializable summary of the filter decision. The result holds at most top_k chunks.

score_chunks(self, chunk_ids: 'List[int]', query: 'str') -> 'List[Tuple[int, float]]'

Defined on AgenticRerankerRetriever

Score chunks by delegating to the single child.

Parameters

chunk_ids : List[int]

List of chunk IDs to score.

query : str

The search query string.

Returns

List[Tuple[int, float]]

A list of (chunk_id, distance) tuples from the child.

expand_retrieved_chunks(self, chunks: List[DashAI.back.models.RAG.documents.chunk.Chunk], window_size: int) -> List[DashAI.back.models.RAG.documents.chunk.Chunk]

Defined on BaseRetriever

Expand chunks into centred windows and merge overlapping windows.

get_children(self) -> List[DashAI.back.models.RAG.retrievers.base_retriever.BaseRetriever]

Defined on CompositeRetriever

Return a copy of the children list.

get_credential(self, name: str)

Defined on ConfigObject

Resolve a registered credential component by name.

Parameters

name : str

Credential component class name (e.g. "HuggingFaceCredential").

Returns

BaseCredential

An instance of the requested credential component.

get_id(self) -> int | None

Defined on BaseRetriever

Return the database ID of this retriever, or None.

get_metadata(cls) -> Dict[str, Any]

Defined on BaseRetriever

Return the UI metadata shared by every retriever.

Returns

Dict[str, Any]

Dictionary with the icon shown for the retriever in the frontend and, when declared, its representation template and the category the retriever pickers group it under.

get_representation(cls) -> DashAI.back.core.utils.MultilingualString | None

Defined on BaseRetriever

Return the retriever's representation template, if any.

Returns

MultilingualString | None

The template with {param} / {nested.param} placeholders, or None when the frontend should fall back to the component description.

get_schema(cls) -> dict

Defined on ConfigObject

Generates the component related Json Schema.

Returns

dict

Dictionary representing the Json Schema of the component.

get_schema_summary(self) -> DashAI.back.models.RAG.retrievers.retrieval_contracts.SchemaSummary

Defined on BaseRetriever

Return a recursive, JSON-serializable summary of this retriever.

Returns

SchemaSummary

{"class": ..., "params": ...} plus children when present.

get_schema_summary_parameters(cls) -> Dict[str, str]

Defined on BaseRetriever

Return a copy of the summary parameter mapping for the frontend.

init_model(self) -> None

Defined on BaseRetriever

Called by the factory after inject_infra().

inject_infra(self, env_RAG_path: str | os.PathLike, chunks: Dict[int, Dict[int, DashAI.back.models.RAG.documents.chunk.Chunk]], persistence: Any, documents: Optional[Dict[int, DashAI.back.models.RAG.documents.source_document.SourceDocument]] = None) -> None

Defined on BaseRetriever

Inject runtime infrastructure after schema validation.

load(self, filename: str = '') -> None

Defined on BaseRetriever

Restore the retriever's state from disk.

merge_expanded_chunks(self, chunks: List[DashAI.back.models.RAG.documents.chunk.Chunk]) -> List[DashAI.back.models.RAG.documents.chunk.Chunk]

Defined on BaseRetriever

Merge overlapping expanded units without widening plain chunks.

save(self, filename: str = '') -> None

Defined on BaseRetriever

Persist the retriever's state to disk.

set_id(self, id: int) -> None

Defined on BaseRetriever

Assign a database ID to this retriever.

set_trace_params(self, params: Dict[str, Any]) -> None

Defined on BaseRetriever

Store a JSON-serializable snapshot of this retriever's configuration.

Parameters

params : Dict[str, Any]

Raw construction parameters captured by the factory before any nested component reference is consumed. A deep copy is stored so later mutations of the original mapping cannot affect trace rendering.

validate_and_transform(self, raw_data: dict) -> dict

Defined on ConfigObject

It takes the data given by the user to initialize the model and returns it with all the objects that the model needs to work.

Parameters

raw_data : dict

A dictionary with the data provided by the user to initialize the model.

Returns

dict

A validated dictionary with the necessary objects.