lancedb_haystack.embedding_retriever

Classes

LanceDBEmbeddingRetriever

A component for retrieving documents from an LanceDBDocumentStore using embeddings and vector similarity.

Module Contents

class lancedb_haystack.embedding_retriever.LanceDBEmbeddingRetriever(document_store: lancedb_haystack.document_store.LanceDBDocumentStore, filters: Dict[str, Any] | None = None, top_k: int | None = 10)

A component for retrieving documents from an LanceDBDocumentStore using embeddings and vector similarity.

NAME = 'lancedb_haystack.embedding_retriever.LanceDBEmbeddingRetriever'

_document_store

_filters

_top_k

run(query_embedding: List[float], filters: Dict[str, Any] | None = None, top_k: int | None = None)

Run the LanceDBEmbeddingRetriever on the given input data.

Parameters:

• query_embedding – Embedding of the query.

• filters – A dictionary with filters to narrow down the search space.

• top_k – The maximum number of documents to return.

Returns:

The retrieved documents.

to_dict() → Dict[str, Any]

Serialize this component to a dictionary.

classmethod from_dict(data: Dict[str, Any]) → LanceDBEmbeddingRetriever

Deserialize this component from a dictionary.