SentenceTransformersDiversityRanker

A Diversity Ranker based on Sentence Transformers.

Basic Information

• Type: haystack_integrations.rankers.sentence_transformers_diversity.SentenceTransformersDiversityRanker

Inputs

Parameter	Type	Default	Description
query	str		The search query.
documents	List[Document]		List of Document objects to be ranker.
top_k	Optional[int]	None	Optional. An integer to override the top_k set during initialization.
lambda_threshold	Optional[float]	None	Override the trade-off parameter between relevance and diversity. Only used when strategy is "maximum_margin_relevance".

Outputs

Parameter	Type	Default	Description
documents	List[Document]		A dictionary with the following key: - documents: List of Document objects that have been selected based on the diversity ranking.

Overview

Work in Progress

Bear with us while we're working on adding pipeline examples and most common components connections.

A Diversity Ranker based on Sentence Transformers.

Applies a document ranking algorithm based on one of the two strategies:

1. Greedy Diversity Order:

   Implements a document ranking algorithm that orders documents in a way that maximizes the overall diversity of the documents based on their similarity to the query.

   It uses a pre-trained Sentence Transformers model to embed the query and the documents.

2. Maximum Margin Relevance:

   Implements a document ranking algorithm that orders documents based on their Maximum Margin Relevance (MMR) scores.

   MMR scores are calculated for each document based on their relevance to the query and diversity from already selected documents. The algorithm iteratively selects documents based on their MMR scores, balancing between relevance to the query and diversity from already selected documents. The 'lambda_threshold' controls the trade-off between relevance and diversity.

Usage Example

components:
  SentenceTransformersDiversityRanker:
    type: haystack.components.rankers.sentence_transformers_diversity.SentenceTransformersDiversityRanker
    init_parameters:

Parameters

Init Parameters

These are the parameters you can configure in Pipeline Builder:

Parameter	Type	Default	Description
model	str	sentence-transformers/all-MiniLM-L6-v2	Local path or name of the model in Hugging Face's model hub, such as 'sentence-transformers/all-MiniLM-L6-v2'.
top_k	int	10	The maximum number of Documents to return per query.
device	Optional[ComponentDevice]	None	The device on which the model is loaded. If None, the default device is automatically selected.
token	Optional[Secret]	Secret.from_env_var(['HF_API_TOKEN', 'HF_TOKEN'], strict=False)	The API token used to download private models from Hugging Face.
similarity	Union[str, DiversityRankingSimilarity]	cosine	Similarity metric for comparing embeddings. Can be set to "dot_product" (default) or "cosine".
query_prefix	str		A string to add to the beginning of the query text before ranking. Can be used to prepend the text with an instruction, as required by some embedding models, such as E5 and BGE.
query_suffix	str		A string to add to the end of the query text before ranking.
document_prefix	str		A string to add to the beginning of each Document text before ranking. Can be used to prepend the text with an instruction, as required by some embedding models, such as E5 and BGE.
document_suffix	str		A string to add to the end of each Document text before ranking.
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.
strategy	Union[str, DiversityRankingStrategy]	greedy_diversity_order	The strategy to use for diversity ranking. Can be either "greedy_diversity_order" or "maximum_margin_relevance".
lambda_threshold	float	0.5	The trade-off parameter between relevance and diversity. Only used when strategy is "maximum_margin_relevance".
model_kwargs	Optional[Dict[str, Any]]	None	Additional keyword arguments for AutoModelForSequenceClassification.from_pretrained when loading the model. Refer to specific model documentation for available kwargs.
tokenizer_kwargs	Optional[Dict[str, Any]]	None	Additional keyword arguments for AutoTokenizer.from_pretrained when loading the tokenizer. Refer to specific model documentation for available kwargs.
config_kwargs	Optional[Dict[str, Any]]	None	Additional keyword arguments for AutoConfig.from_pretrained when loading the model configuration.
backend	Literal['torch', 'onnx', 'openvino']	torch	The backend to use for the Sentence Transformers model. Choose from "torch", "onnx", or "openvino". Refer to the Sentence Transformers documentation for more information on acceleration and quantization options.

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 search query.
documents	List[Document]		List of Document objects to be ranker.
top_k	Optional[int]	None	Optional. An integer to override the top_k set during initialization.
lambda_threshold	Optional[float]	None	Override the trade-off parameter between relevance and diversity. Only used when strategy is "maximum_margin_relevance".