FastembedSparseTextEmbedder

Compute sparse text embeddings using Fastembed sparse models.

Key Features

• Uses Fastembed sparse models like SPLADE to generate sparse embeddings.
• Designed for query pipelines — embeds the user query for sparse retrieval.
• Supports hybrid search scenarios combining sparse and dense retrieval.
• Configurable batch size and data-parallel processing options.
• Works with any Fastembed-compatible sparse model.

Configuration

1. Drag the FastembedSparseTextEmbedder component onto the canvas from the Component Library.
2. Click the component to open the configuration panel.
3. On the General tab:
   1. Enter the model name or local path, such as prithivida/Splade_PP_en_v1.
4. Go to the Advanced tab to configure batch size, parallel processing, cache directory, thread count, and local files only setting.

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.

Compatible Models

You can find the supported models in the FastEmbed documentation.

Connections

FastembedSparseTextEmbedder receives a text string (the user query) as input. It outputs a sparse_embedding object. Connect its output to a sparse retriever to find matching documents. Use the same sparse embedding model as the one used to embed documents in the document store.

Usage Example

This query pipeline uses FastembedSparseTextEmbedder for sparse retrieval:

components:
  FastembedSparseTextEmbedder:
    type: haystack_integrations.components.embedders.fastembed.fastembed_sparse_text_embedder.FastembedSparseTextEmbedder
    init_parameters:
      model: prithivida/Splade_PP_en_v1
      cache_dir:
      threads:
      progress_bar: true
      parallel:
      local_files_only: false
      model_kwargs:

  bm25_retriever:
    type: haystack_integrations.components.retrievers.opensearch.bm25_retriever.OpenSearchBM25Retriever
    init_parameters:
      document_store:
        type: haystack_integrations.document_stores.opensearch.document_store.OpenSearchDocumentStore
        init_parameters:
          hosts:
          index: 'default'
          max_chunk_bytes: 104857600
          embedding_dim: 768
          return_embedding: false
          method:
          mappings:
          settings:
          create_index: true
          http_auth:
          use_ssl:
          verify_certs:
          timeout:
      top_k: 20

  ChatPromptBuilder:
    type: haystack.components.builders.chat_prompt_builder.ChatPromptBuilder
    init_parameters:
      template:
        - role: system
          content: "You are a helpful assistant answering questions based on the provided documents."
        - role: user
          content: "Documents:\n{% for doc in documents %}\n{{ doc.content }}\n{% endfor %}\n\nQuestion: {{ query }}"

  OpenAIChatGenerator:
    type: haystack.components.generators.chat.openai.OpenAIChatGenerator
    init_parameters:
      api_key:
        type: env_var
        env_vars:
          - OPENAI_API_KEY
        strict: false
      model: gpt-4o-mini

  OutputAdapter:
    type: haystack.components.converters.output_adapter.OutputAdapter
    init_parameters:
      template: '{{ replies[0] }}'
      output_type: List[str]

  answer_builder:
    type: deepset_cloud_custom_nodes.augmenters.deepset_answer_builder.DeepsetAnswerBuilder
    init_parameters:
      reference_pattern: acm

connections:
  - sender: bm25_retriever.documents
    receiver: ChatPromptBuilder.documents
  - sender: ChatPromptBuilder.prompt
    receiver: OpenAIChatGenerator.messages
  - sender: OpenAIChatGenerator.replies
    receiver: OutputAdapter.replies
  - sender: OutputAdapter.output
    receiver: answer_builder.replies
  - sender: bm25_retriever.documents
    receiver: answer_builder.documents

inputs:
  query:
    - bm25_retriever.query
    - ChatPromptBuilder.query
    - answer_builder.query
  filters:
    - bm25_retriever.filters

outputs:
  documents: bm25_retriever.documents
  answers: answer_builder.answers

max_runs_per_component: 100

metadata: {}

Parameters

Inputs

Parameter	Type	Default	Description
text	str		A string to embed.

Outputs

Parameter	Type	Default	Description
sparse_embedding	SparseEmbedding		A sparse embedding representing the input text.

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 Fastembed'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.
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.
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 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
text	str		A string to embed.