Vector retriever

Defines an abstract base class to create a retriever.

This module provides the BaseRetriever class, which serves as a foundation for implementing retrieval systems in Gen AI applications.

Authors

Henry Wicaksono (henry.wicaksono@gdplabs.id) Resti Febriana (resti.febriana@gdplabs.id)

References

[1] https://python.langchain.com/docs/modules/data_connection/retrievers/

BaseVectorRetriever(data_store)

Bases: Component, ABC

An abstract base class for the retriever used in Gen AI applications.

This class defines the interface for retriever components, which are responsible for retrieving relevant documents or information based on a given query.

Attributes:

Name	Type	Description
data_store	BaseVectorDataStore | list[BaseVectorDataStore]	The data store or list of data stores to be used.

Initializes the BaseRetriever object.

Parameters:

Name	Type	Description	Default
data_store	BaseVectorDataStore | list[BaseVectorDataStore]	The data store or list of data stores to be used.	required

retrieve(query, top_k=DEFAULT_TOP_K, retrieval_params=None, event_emitter=None, timeout=None, threshold=None) async

Retrieve documents based on the query.

This method performs the retrieval process by calling the _retrieve method. If the retrieval process fails or times out, it will return an empty list.

Parameters:

Name	Type	Description	Default
query	str	The query string to retrieve documents.	required
top_k	int	The maximum number of documents to retrieve. Defaults to DEFAULT_TOP_K.	DEFAULT_TOP_K
retrieval_params	dict[str, Any] | None	Additional parameters for the retrieval process. These could include 'max_results', 'sort_order', etc., specific to the retrieval logic. Defaults to None.	None
event_emitter	EventEmitter | None	The event emitter to emit events. Defaults to None.	None
timeout	float | int | None	Maximum time in seconds to wait for retrieval to complete. If None, no timeout is applied. Defaults to None.	None
threshold	float | None	The minimum score threshold for filtering results.	None

Returns:

Type	Description
list[Chunk]	list[Chunk]: A list of retrieved documents.