WeaviateBM25Retriever

Retrieve documents from a Weaviate document store using the BM25 algorithm for keyword-based search.

Key Features

• Keyword-based BM25 retrieval from a Weaviate vector database.
• Configurable number of results with top_k.
• Supports metadata filtering to narrow down the search space.
• Configurable filter policy (replace or merge) for runtime filters.

Configuration

1. Drag the WeaviateBM25Retriever component onto the canvas from the Component Library.
2. Click on the component to open the configuration panel.
3. On the General tab:
   • Configure the WeaviateDocumentStore with your Weaviate instance URL.
   • Set top_k to control the maximum number of documents to retrieve.
4. Go to the Advanced tab to configure filter_policy and default filters.

Connections

WeaviateBM25Retriever receives a query text string as input. It sends retrieved documents to downstream components such as PromptBuilder or a ranker.

Source Code

To check this component's source code, open bm25_retriever.py in the Haystack Core Integrations repository.

Usage Examples

Basic Configuration

  WeaviateBM25Retriever:
    type: weaviate.src.haystack_integrations.components.retrievers.weaviate.bm25_retriever.WeaviateBM25Retriever
    init_parameters: {}

Connect the pipeline's query input to its query input. Connect its documents output to a PromptBuilder, Ranker, or answer builder.

components:
  WeaviateBM25Retriever:
    type: weaviate.src.haystack_integrations.components.retrievers.weaviate.bm25_retriever.WeaviateBM25Retriever
    init_parameters:

Parameters

Inputs

Parameter	Type	Description
query	str	The query text.
filters	Optional[Dict[str, Any]]	Filters applied to the retrieved Documents. The way runtime filters are applied depends on the filter_policy chosen at retriever initialization.
top_k	Optional[int]	The maximum number of documents to return.

Outputs

Parameter	Type	Description
documents	List[Document]	Retrieved documents.

Init Parameters

These are the parameters you can configure in Pipeline Builder:

Parameter	Type	Default	Description
document_store	WeaviateDocumentStore		Instance of WeaviateDocumentStore that will be used from this retriever.
filters	Optional[Dict[str, Any]]	None	Custom filters applied when running the retriever.
top_k	int	10	Maximum number of documents to return.
filter_policy	Union[str, FilterPolicy]	FilterPolicy.REPLACE	Policy to determine how filters are applied.

Run Method Parameters

These are the parameters you can configure for the component's run() method. This means you can pass these parameters at query time through the API, in Playground, or when running a job. For details, see Modify Pipeline Parameters at Query Time.

Parameter	Type	Default	Description
query	str		The query text.
filters	Optional[Dict[str, Any]]	None	Filters applied to the retrieved Documents. The way runtime filters are applied depends on the filter_policy chosen at retriever initialization. See init method docstring for more details.
top_k	Optional[int]	None	The maximum number of documents to return.