MultiQueryEmbeddingRetriever

Retrieve documents using multiple text queries in parallel with an embedding-based retriever. The component converts each query to an embedding, retrieves documents for each query, then combines and deduplicates the results. This improves recall by finding documents relevant to multiple query variations.

Key Features

• Processes multiple queries in parallel using an embedding-based retriever.
• Deduplicates results based on document content across all queries.
• Sorts the combined results by relevance score.
• Configurable parallel processing with a thread pool.
• Works best with QueryExpander to generate semantically varied query versions.

Configuration

1. Drag the MultiQueryEmbeddingRetriever 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 underlying retriever (an embedding-based retriever such as OpenSearchEmbeddingRetriever).
   • Configure the query_embedder (a text embedder to convert queries to embeddings).
4. Go to the Advanced tab to set max_workers for controlling parallel thread execution.

Connections

MultiQueryEmbeddingRetriever receives a list of queries through its queries input, typically from QueryExpander. It outputs a deduplicated documents list sorted by relevance score. Connect the documents output to a Ranker, DocumentJoiner, or directly to an LLM component.

Source Code

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

Usage Examples

Basic Configuration

  multi_query_retriever:
    type: haystack.components.retrievers.multi_query_embedding_retriever.MultiQueryEmbeddingRetriever
    init_parameters:
      query_embedder:
        type: haystack.components.embedders.sentence_transformers_text_embedder.SentenceTransformersTextEmbedder
        init_parameters:
          model: sentence-transformers/all-MiniLM-L6-v2
      retriever:
        type: haystack_integrations.components.retrievers.opensearch.embedding_retriever.OpenSearchEmbeddingRetriever
        init_parameters:
          document_store:
            type: haystack_integrations.document_stores.opensearch.document_store.OpenSearchDocumentStore
          top_k: 5
      max_workers: 3

Connections

This example combines QueryExpander with MultiQueryEmbeddingRetriever. You can then send the retrieved documents to a Ranker or DocumentJoiner to combine the results:

components:
  query_expander:
    type: haystack.components.query.query_expander.QueryExpander
    init_parameters:
      n_expansions: 3
      include_original_query: true

      chat_generator:
        type: haystack_integrations.components.generators.anthropic.chat.chat_generator.AnthropicChatGenerator
        init_parameters: {}
  multi_query_retriever:
    type: haystack.components.retrievers.multi_query_embedding_retriever.MultiQueryEmbeddingRetriever
    init_parameters:
      query_embedder:
        type: haystack.components.embedders.sentence_transformers_text_embedder.SentenceTransformersTextEmbedder
        init_parameters:
          model: sentence-transformers/all-MiniLM-L6-v2
      retriever:
        type: haystack_integrations.components.retrievers.opensearch.embedding_retriever.OpenSearchEmbeddingRetriever
        init_parameters:
          document_store:
            type: haystack_integrations.document_stores.opensearch.document_store.OpenSearchDocumentStore
          top_k: 5
      max_workers: 3

connections:
- sender: query_expander.queries
  receiver: multi_query_retriever.queries

max_runs_per_component: 100

metadata: {}

inputs:
  query:
  - query_expander.query

Parameters

Inputs

Parameter	Type	Description
queries	List[str]	List of text queries to process.
retriever_kwargs	Optional[Dict[str, Any]]	Optional dictionary of arguments for the retriever.

Outputs

Parameter	Type	Description
documents	List[Document]	List of retrieved documents sorted by relevance score, deduplicated by content.

Init Parameters

These are the parameters you can configure in Pipeline Builder:

Parameter	Type	Default	Description
retriever	EmbeddingRetriever		The embedding-based retriever to use for document retrieval. Must implement the EmbeddingRetriever protocol.
query_embedder	TextEmbedder		The query embedder to convert text queries to embeddings. Must implement the TextEmbedder protocol.
max_workers	int	3	Maximum number of worker threads for parallel processing.

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
queries	List[str]		List of text queries to process.
retriever_kwargs	Optional[Dict[str, Any]]	None	Optional dictionary of arguments to pass to the retriever's run method (for example, filters, top_k).

Related Information

• QueryExpander
• MultiQueryTextRetriever