SentenceWindowRetriever

Retrieve the context window of documents surrounding a relevant result. When a retriever finds a relevant sentence, this component fetches the neighboring sentences before and after it to provide full context for downstream components.

Key Features

• Retrieves neighboring documents around each relevant document.
• Window size is configurable and can be overridden at query time.
• Uses source_id and split_id metadata fields to locate surrounding documents.
• Accepts a single field name or a list of field names as the source ID.
• Compatible with multiple document stores: Astra, Elasticsearch, OpenSearch, Pgvector, Pinecone, and Qdrant.

Configuration

1. Drag the SentenceWindowRetriever component onto the canvas from the Component Library.
2. Click the component to open the configuration panel.
3. On the General tab:
   1. Select the document store. The document store determines where documents are retrieved from.
4. Go to the Advanced tab to configure window_size, source_id_meta_field, and split_id_meta_field.

Connections

SentenceWindowRetriever accepts retrieved_documents (a list of documents from a previous retriever) and an optional window_size override as inputs. It outputs context_windows (a list of concatenated context strings) and context_documents (a list of documents including surrounding context).

Typically, you place SentenceWindowRetriever after a retriever (such as OpenSearchBM25Retriever or OpenSearchEmbeddingRetriever) and before a PromptBuilder. The surrounding context helps the LLM generate better answers.

Usage Example

components:
  SentenceWindowRetriever:
    type: components.retrievers.sentence_window_retriever.SentenceWindowRetriever
    init_parameters:
      document_store:
        type: haystack_integrations.document_stores.opensearch.document_store.OpenSearchDocumentStore
        init_parameters:
          hosts:
          index: 'Standard-Index-English'
      window_size: 3
      source_id_meta_field: source_id  # Can also be a list: ["source_id", "file_id"]

Parameters

Inputs

Parameter	Type	Default	Description
retrieved_documents	List[Document]		List of retrieved documents from the previous retriever.
window_size	Optional[int]	None	The number of documents to retrieve before and after the relevant one. This will overwrite the window_size parameter set in the constructor.

Outputs

Parameter	Type	Default	Description
context_windows	List[str]		A list of strings, where each string represents the concatenated text from the context window of the corresponding document in retrieved_documents.
context_documents	List[Document]		A list of Document objects, containing the retrieved documents plus the context documents surrounding them. The documents are sorted by the split_idx_start meta field.

Init Parameters

These are the parameters you can configure in Pipeline Builder:

Parameter	Type	Default	Description
document_store	DocumentStore		The Document Store to retrieve the surrounding documents from.
window_size	int	3	The number of documents to retrieve before and after the relevant one. For example, window_size: 2 fetches 2 preceding and 2 following documents.
source_id_meta_field	Union[str, List[str]]	source_id	The metadata field containing the ID of the original document. Can be a single field name or a list of field names. When a list is provided, only documents matching all specified fields will be retrieved.
split_id_meta_field	str	"split_id"	The metadata field that contains the split ID of the document.
raise_on_missing_meta_fields	bool	True	If True, raises an error if the documents do not contain the required metadata fields. If False, it skips retrieving the context for documents that are missing the required metadata fields, but still includes the original document in the results.

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
retrieved_documents	List[Document]		List of retrieved documents from the previous retriever.
window_size	Optional[int]	None	The number of documents to retrieve before and after the relevant one. This will overwrite the window_size parameter set in the constructor.