ElasticsearchBM25Retriever

Retrieve documents from the ElasticsearchDocumentStore using the BM25 algorithm to find keywords matching the user's query.

Key Features

• Keyword-based retrieval using the BM25 algorithm.
• Only compatible with ElasticsearchDocumentStore.
• Calculates weighted word overlap between the query and documents.
• Works well for exact keyword matching, product codes, and proper names.
• Lightweight and performs well on out-of-domain data.
• Can be combined with ElasticsearchEmbeddingRetriever and DocumentJoiner for hybrid retrieval.

Configuration

1. Drag the ElasticsearchBM25Retriever component onto the canvas from the Component Library.
2. Click on the component to open the configuration panel.
3. On the General tab:
   1. Configure the document_store connection with your Elasticsearch hosts and index name.
   2. Set top_k to the maximum number of documents to return.
4. Go to the Advanced tab to configure filters, fuzziness, scale_score, and filter_policy.

Connections

ElasticsearchBM25Retriever receives a query string from the Input component. It outputs a list of matching documents through its documents output. You can connect its output to a ranker or DocumentJoiner for hybrid retrieval with ElasticsearchEmbeddingRetriever.

Source Code

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

Usage Examples

Basic Configuration

  ElasticsearchBM25Retriever:
    type: haystack_integrations.components.retrievers.elasticsearch.bm25_retriever.ElasticsearchBM25Retriever
    init_parameters:
      fuzziness: AUTO
      top_k: 10
      scale_score: false
      filter_policy: replace
      document_store:
        type: haystack_integrations.document_stores.elasticsearch.document_store.ElasticsearchDocumentStore
        init_parameters:
          index: my_index
          embedding_similarity_function: cosine

Using the Component in a Pipeline

This is an example of a document search pipeline that combines keyword-based retrieval with embedding-based retrieval. It uses ElasticsearchBM25Retriever and ElasticsearchEmbeddingRetriever to retrieve documents from the document store. It then joins the results of the two with a DocumentJoiner.

components:
  query_embedder:
    type: deepset_cloud_custom_nodes.embedders.nvidia.text_embedder.DeepsetNvidiaTextEmbedder
    init_parameters:
      normalize_embeddings: true
      model: intfloat/e5-base-v2

  document_joiner:
    type: haystack.components.joiners.document_joiner.DocumentJoiner
    init_parameters:
      join_mode: concatenate

  ranker:
    type: deepset_cloud_custom_nodes.rankers.nvidia.ranker.DeepsetNvidiaRanker
    init_parameters:
      model: "intfloat/simlm-msmarco-reranker"
      top_k: 20

  ElasticsearchEmbeddingRetriever:
    type: haystack_integrations.components.retrievers.elasticsearch.embedding_retriever.ElasticsearchEmbeddingRetriever
    init_parameters:
      filters:
      top_k: 10
      num_candidates:
      filter_policy: replace
      document_store:
        type: haystack_integrations.document_stores.elasticsearch.document_store.ElasticsearchDocumentStore
        init_parameters:
          hosts:
          custom_mapping:
          index: 'my_index'
          embedding_similarity_function: cosine
  ElasticsearchBM25Retriever:
    type: haystack_integrations.components.retrievers.elasticsearch.bm25_retriever.ElasticsearchBM25Retriever
    init_parameters:
      filters:
      fuzziness: AUTO
      top_k: 10
      scale_score: false
      filter_policy: replace
      document_store:
        type: haystack_integrations.document_stores.elasticsearch.document_store.ElasticsearchDocumentStore
        init_parameters:
          hosts:
          custom_mapping:
          index: 'my_index'
          embedding_similarity_function: cosine

connections:  # Defines how the components are connected
- sender: document_joiner.documents
  receiver: ranker.documents
- sender: query_embedder.embedding
  receiver: ElasticsearchEmbeddingRetriever.query_embedding
- sender: ElasticsearchEmbeddingRetriever.documents
  receiver: document_joiner.documents
- sender: ElasticsearchBM25Retriever.documents
  receiver: document_joiner.documents

inputs:  # Define the inputs for your pipeline
  query:  # These components will receive the query as input
  - "query_embedder.text"
  - "ranker.query"
  - ElasticsearchBM25Retriever.query

  filters:  # These components will receive a potential query filter as input
  - "ElasticsearchEmbeddingRetriever.filters"
  - "ElasticsearchBM25Retriever.filters"

outputs:  # Defines the output of your pipeline
  documents: "ranker.documents"  # The output of the pipeline is the retrieved documents

max_runs_per_component: 100

metadata: {}

Parameters

Inputs

Parameter	Type	Default	Description
query	str		String to search in the document 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. For details, check the Init Parameters section.
top_k	Optional[int]	None	Maximum number of documents to return.

Outputs

Parameter	Type	Default	Description
documents	List[Document]		List of documents that match the query.

Init Parameters

These are the parameters you can configure in Pipeline Builder:

Parameter	Type	Default	Description
document_store	ElasticsearchDocumentStore		An instance of ElasticsearchDocumentStore to retrieve documents from.
filters	Optional[Dict[str, Any]]	None	Filters applied to the retrieved documents.
fuzziness	str	AUTO	Fuzziness parameter passed to Elasticsearch. For details, see Elasticsearch documentation.
top_k	int	10	Maximum number of documents to return.
scale_score	bool	False	If True scales the Document`s scores between 0 and 1.
filter_policy	Union[str, FilterPolicy]	FilterPolicy.REPLACE	Policy to determine how filters are applied. Possible options: - REPLACE (default): Overrides the initialization filters with the filters specified at runtime. Use this policy to dynamically change filtering for specific queries. - MERGE: Combines runtime filters with initialization filters to narrow down the search.

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		String to search in the Documents 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.
top_k	Optional[int]	None	Maximum number of Document to return.

Related Information

• Pipeline Components