AstraEmbeddingRetriever

Retrieve documents from an Astra DB document store using vector similarity.

Basic Information

• Type: haystack_integrations.components.retrievers.astra.retriever.AstraEmbeddingRetriever
• Components it can connect with:
  • TextEmbedder: AstraEmbeddingRetriever receives query embeddings from a text embedder.
  • Ranker: AstraEmbeddingRetriever sends retrieved documents to a Ranker for reranking.

Inputs

Parameter	Type	Default	Description
query_embedding	List[float]		Floats representing the query embedding.
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.
top_k	Optional[int]	None	The maximum number of documents to retrieve.

Outputs

Parameter	Type	Default	Description
documents	List[Document]		A list of documents retrieved from the AstraDocumentStore.

Overview

Use AstraEmbeddingRetriever to retrieve documents from an Astra DB document store using vector similarity search. This retriever must be connected to an AstraDocumentStore to run.

Astra DB is a cloud-native, multi-cloud database service built on Apache Cassandra, optimized for modern, data-intensive applications.

Astra DB Setup

To use this retriever, you need an Astra DB account and a properly configured collection. For more information, see the Astra DB documentation.

Usage Example

Initializing the Component

components:
  AstraEmbeddingRetriever:
    type: haystack_integrations.components.retrievers.astra.retriever.AstraEmbeddingRetriever
    init_parameters:
      document_store:
        type: haystack_integrations.document_stores.astra.document_store.AstraDocumentStore
        init_parameters:
          api_endpoint:
            type: env_var
            env_vars:
            - ASTRA_API_ENDPOINT
            strict: false
          token:
            type: env_var
            env_vars:
            - ASTRA_TOKEN
            strict: false
          collection_name: my-collection
          embedding_dim: 768
      top_k: 10

Parameters

Init Parameters

These are the parameters you can configure in Pipeline Builder:

Parameter	Type	Default	Description
document_store	AstraDocumentStore		An instance of AstraDocumentStore to use with the retriever.
filters	Optional[Dict[str, Any]]	None	A dictionary with filters to narrow down the search space.
top_k	int	10	The maximum number of documents to retrieve.
filter_policy	Union[str, FilterPolicy]	FilterPolicy.REPLACE	Policy to determine how filters are applied. Can be REPLACE (runtime filters replace initialization filters) or MERGE (runtime filters are merged with initialization filters).

Run Method Parameters

These are the parameters you can configure for the component's run() method. You can pass these parameters at query time through the API, in Playground, or when running a job.

Parameter	Type	Default	Description
query_embedding	List[float]		Floats representing the query embedding.
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.
top_k	Optional[int]	None	The maximum number of documents to retrieve.