FastembedRanker

Rank documents based on their similarity to the query using Fastembed models.

Key Features

• Ranks documents from most to least semantically relevant to the query.
• Uses Fastembed reranking models for fast, efficient reranking.
• Configurable number of results returned via top_k.
• Supports embedding metadata fields alongside document content for richer reranking.
• Improves quality of generated answers by surfacing the most relevant documents at the top.

Configuration

1. Drag the FastembedRanker component onto the canvas from the Component Library.
2. Click on the component to open the configuration panel.
3. On the General tab:
   • Set the reranking model name. You can find supported models in the Fastembed documentation.
   • Set top_k to control how many documents to return.
4. Go to the Advanced tab to configure additional settings such as batch_size, parallel, and meta_fields_to_embed.

Connections

FastembedRanker accepts a query string and a list of documents as inputs. Connect it after a retriever or DocumentJoiner in a query pipeline.

It outputs a ranked list of documents sorted from most to least relevant. Connect its documents output to ChatPromptBuilder, AnswerBuilder, or another downstream component.

Source Code

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

Usage Examples

Basic Configuration

  FastembedRanker:
    type: haystack_integrations.components.rankers.fastembed.ranker.FastembedRanker
    init_parameters:
      model_name: Xenova/ms-marco-MiniLM-L-6-v2
      top_k: 5
      batch_size: 64
      local_files_only: false
      meta_data_separator: "\n"

This query pipeline uses FastembedRanker to rerank documents after retrieval:

components:
  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
      fuzziness: 0

  FastembedRanker:
    type: haystack_integrations.components.rankers.fastembed.ranker.FastembedRanker
    init_parameters:
      model_name: Xenova/ms-marco-MiniLM-L-6-v2
      top_k: 5
      cache_dir:
      threads:
      batch_size: 64
      parallel:
      local_files_only: false
      meta_fields_to_embed:
      meta_data_separator: "\n"

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

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

outputs:
  documents: FastembedRanker.documents
  answers: answer_builder.answers

max_runs_per_component: 100

metadata: {}

Parameters

Inputs

Parameter	Type	Default	Description
query	str		The input query to compare the documents to.
documents	List[Document]		A list of documents to be ranked.
top_k	Optional[int]	None	The maximum number of documents to return.

Outputs

Parameter	Type	Default	Description
documents	List[Document]		A list of documents sorted from most similar to least similar to the query.

Init Parameters

These are the parameters you can configure in Pipeline Builder:

Parameter	Type	Default	Description
model_name	str	Xenova/ms-marco-MiniLM-L-6-v2	Fastembed model name. Check the list of supported models in the Fastembed documentation.
top_k	int	10	The maximum number of documents to return.
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	64	Number of strings to encode at once.
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 concatenated with the document content for reranking.
meta_data_separator	str	\n	Separator used to concatenate the meta fields to the Document content.

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	str		The input query to compare the documents to.
documents	List[Document]		A list of documents to be ranked.
top_k	Optional[int]	None	The maximum number of documents to return.