QdrantHybridRetriever

Retrieves documents from a QdrantDocumentStore using both dense and sparse vectors, fusing results with Reciprocal Rank Fusion.

Key Features

• Hybrid retrieval combining dense and sparse vector search.
• Reciprocal Rank Fusion (RRF) for merging dense and sparse results.
• Optional document grouping by payload fields.
• Score threshold filtering to limit returned results.
• Optional return of document embeddings alongside content.

Configuration

1. Drag the QdrantHybridRetriever component onto the canvas from the Component Library.
2. Click the component to open the configuration panel.
3. On the General tab:
   1. Configure the document_store with your Qdrant connection details. Make sure the document store has use_sparse_embeddings enabled.
4. Go to the Advanced tab to configure top_k, filters, return_embedding, and scale_score.

Connections

QdrantHybridRetriever accepts both a dense query_embedding and a sparse query_sparse_embedding as inputs. It outputs a list of retrieved documents.

Connect a text embedder to query_embedding and a sparse text embedder to query_sparse_embedding. Connect the documents output to a PromptBuilder, Ranker, or answer builder.

Usage Example

components:
  QdrantHybridRetriever:
    type: qdrant.src.haystack_integrations.components.retrievers.qdrant.retriever.QdrantHybridRetriever
    init_parameters:

Parameters

Inputs

Parameter	Type	Default	Description
query_embedding	List[float]		Dense embedding of the query.
query_sparse_embedding	SparseEmbedding		Sparse embedding of the query.
filters	Optional[Union[Dict[str, Any], models.Filter]]	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. If using group_by parameters, maximum number of groups to return.
return_embedding	Optional[bool]	None	Whether to return the embedding of the retrieved Documents.
score_threshold	Optional[float]	None	A minimal score threshold for the result. Score of the returned result might be higher or smaller than the threshold depending on the Distance function used. E.g. for cosine similarity only higher scores will be returned.
group_by	Optional[str]	None	Payload field to group by, must be a string or number field. If the field contains more than 1 value, all values will be used for grouping. One point can be in multiple groups.
group_size	Optional[int]	None	Maximum amount of points to return per group. Default is 3.

Outputs

Parameter	Type	Default	Description
documents	List[Document]		The retrieved documents.

Init Parameters

These are the parameters you can configure in Pipeline Builder:

Parameter	Type	Default	Description
document_store	QdrantDocumentStore		An instance of QdrantDocumentStore.
filters	Optional[Union[Dict[str, Any], models.Filter]]	None	A dictionary with filters to narrow down the search space.
top_k	int	10	The maximum number of documents to retrieve. If using group_by parameters, maximum number of groups to return.
return_embedding	bool	False	Whether to return the embeddings of the retrieved Documents.
filter_policy	Union[str, FilterPolicy]	FilterPolicy.REPLACE	Policy to determine how filters are applied.
score_threshold	Optional[float]	None	A minimal score threshold for the result. Score of the returned result might be higher or smaller than the threshold depending on the Distance function used. E.g. for cosine similarity only higher scores will be returned.
group_by	Optional[str]	None	Payload field to group by, must be a string or number field. If the field contains more than 1 value, all values will be used for grouping. One point can be in multiple groups.
group_size	Optional[int]	None	Maximum amount of points to return per group. Default is 3.

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_embedding	List[float]		Dense embedding of the query.
query_sparse_embedding	SparseEmbedding		Sparse embedding of the query.
filters	Optional[Union[Dict[str, Any], models.Filter]]	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. If using group_by parameters, maximum number of groups to return.
return_embedding	Optional[bool]	None	Whether to return the embedding of the retrieved Documents.
score_threshold	Optional[float]	None	A minimal score threshold for the result. Score of the returned result might be higher or smaller than the threshold depending on the Distance function used. E.g. for cosine similarity only higher scores will be returned.
group_by	Optional[str]	None	Payload field to group by, must be a string or number field. If the field contains more than 1 value, all values will be used for grouping. One point can be in multiple groups.
group_size	Optional[int]	None	Maximum amount of points to return per group. Default is 3.