FastembedSparseDocumentEmbedder

Compute sparse document embeddings using Fastembed sparse models.

Basic Information

• Type: haystack_integrations.components.embedders.fastembed.fastembed_sparse_document_embedder.FastembedSparseDocumentEmbedder
• Components it can connect with:
  • Preprocessors: Receives documents from Converters or DocumentSplitter in an index.
  • DocumentWriter: Sends embedded documents to DocumentWriter for storage.

Inputs

Parameter	Type	Default	Description
documents	List[Document]		List of Documents to embed.

Outputs

Parameter	Type	Default	Description
documents	List[Document]		List of Documents with each Document's sparse_embedding field set to the computed embeddings.

Overview

FastembedSparseDocumentEmbedder computes sparse document embeddings using Fastembed sparse models like SPLADE. Sparse embeddings are useful for hybrid search scenarios where you want to combine semantic search with keyword-based retrieval.

The sparse embedding of each document is stored in the sparse_embedding field of the Document. Sparse embeddings are useful for performing sparse embedding retrieval on a set of documents. During retrieval, the sparse embedding representing the query is compared to sparse embeddings of the documents to identify the most similar or relevant ones.

Compatible Models

You can find the supported models in the FastEmbed documentation.

Embedding Models in Query Pipelines and Indexes

The embedding model you use to embed documents in your indexing pipeline must be the same as the embedding model you use to embed the query in your query pipeline.

This means the embedders for your indexing and query pipelines must match. For example, if you use CohereDocumentEmbedder to embed your documents, you should use CohereTextEmbedder with the same model to embed your queries.

Usage Example

This index uses FastembedSparseDocumentEmbedder to create sparse embeddings:

components:
  TextFileToDocument:
    type: haystack.components.converters.txt.TextFileToDocument
    init_parameters:
      encoding: utf-8
      store_full_path: false

  DocumentSplitter:
    type: haystack.components.preprocessors.document_splitter.DocumentSplitter
    init_parameters:
      split_by: sentence
      split_length: 5
      split_overlap: 1

  FastembedSparseDocumentEmbedder:
    type: haystack_integrations.components.embedders.fastembed.fastembed_sparse_document_embedder.FastembedSparseDocumentEmbedder
    init_parameters:
      model: prithivida/Splade_PP_en_v1
      cache_dir:
      threads:
      batch_size: 32
      progress_bar: true
      parallel:
      local_files_only: false
      meta_fields_to_embed:
      embedding_separator: "\n"
      model_kwargs:

  DocumentWriter:
    type: haystack.components.writers.document_writer.DocumentWriter
    init_parameters:
      document_store:
        type: haystack_integrations.document_stores.opensearch.document_store.OpenSearchDocumentStore
        init_parameters:
          hosts:
          index: 'sparse-index'
          max_chunk_bytes: 104857600
          embedding_dim: 768
          return_embedding: false
          method:
          mappings:
          settings:
          create_index: true
          http_auth:
          use_ssl:
          verify_certs:
          timeout:
      policy: OVERWRITE

connections:
  - sender: TextFileToDocument.documents
    receiver: DocumentSplitter.documents
  - sender: DocumentSplitter.documents
    receiver: FastembedSparseDocumentEmbedder.documents
  - sender: FastembedSparseDocumentEmbedder.documents
    receiver: DocumentWriter.documents

inputs:
  files:
    - TextFileToDocument.sources

max_runs_per_component: 100

metadata: {}

Parameters

Init Parameters

These are the parameters you can configure in Pipeline Builder:

Parameter	Type	Default	Description
model	str	prithivida/Splade_PP_en_v1	Local path or name of the model in Hugging Face's model hub, such as prithivida/Splade_PP_en_v1.
cache_dir	Optional[str]	None	The path to the cache directory. Can be set using the FASTEMBED_CACHE_PATH env variable. Defaults to fastembed_cache in the system's temp directory.
threads	Optional[int]	None	The number of threads single onnxruntime session can use.
batch_size	int	32	Number of strings to encode at once.
progress_bar	bool	True	If True, displays progress bar during embedding.
parallel	Optional[int]	None	If > 1, data-parallel encoding is used, recommended for offline encoding of large datasets. If 0, use all available cores. If None, don't use data-parallel processing, use default onnxruntime threading instead.
local_files_only	bool	False	If True, only use the model files in the cache_dir.
meta_fields_to_embed	Optional[List[str]]	None	List of meta fields that should be embedded along with the Document content.
embedding_separator	str	\n	Separator used to concatenate the meta fields to the Document content.
model_kwargs	Optional[Dict[str, Any]]	None	Dictionary containing model parameters such as k, b, avg_len, language.

Run Method Parameters

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

Parameter	Type	Default	Description
documents	List[Document]		List of Documents to embed.