Ranker Parameters

Check the init and runtime parameters you can configure for the rankers available in deepset Cloud.

YAML Init Parameters

These are the parameters you can specify in pipeline YAML:

CohereRanker Parameters

Parameter	Type	Possible Values	Description
`api_key`	String		The Cohere API key so that you can use Cohere models. Required.
`model_name_or_path`	String		The name of the Cohere model you want to use for reranking. Check the list of supported models in the Cohere documentation. Required.
`top_k`	Integer	Default: `10`	The maximum number of documents to return. Required.
`max_chunks_per_doc`	Integer	Default: `None`	Specifies the maximum number of chunks your document is split into if the document exceeds 512 tokens. (This is because Cohere models break documents into chunks of 512 tokens.) The default `None` setting splits your documents into a maximum of 10 chunks. Note that this parameter counts in the length of the query as well. So if your query is 32 tokens, the split will be: First chunk: 32 tokens from query + first 480 tokens from the document Second chunk: 32 tokens from the query + tokens 481 to 961 from the document, and so on. If after splitting into 10 chunks there are still some tokens from the document left, they're disregarded. Optional.
`embed_meta_fields`	List of strings		Concatenates the provided metadata fields into the text passage that is then used in reranking. The concatenated metadata are not included in the documents that are returned. (Original documents are returned.)

DeepsetMetaFieldRanker Parameters

Parameter	Type	Possible Values	Description
`meta_field`	String		The name of the document's metadata field you want to rank by. Required.
`weight`	Float	Values in range [0,1]. Default: `1.0`	Specifies how documents are ranked: `0` - disables ranking by a metadata field. `0.5` - means both ranking done by a previous component and ranking by a metadata field have the same impact. `1` - ranks by a metadata field only. Required.
`top_k`	Integer	Default: `none`	The maximum number of documents to return per query. If not specified, the ranker returns all documents it received but reranked. Optional.
`ranking_mode`	Literal	`reciprocal_rank_fusion` `descending` Default: `descending`	The mode used to combine the retriever's and ranker's scores. Use `linear_score` only with retrievers or rankers that return a score in the range [0,1]. Required.
`sort_order`	Literal	`ascending` `descending` Default: `descending`	Defines whether to sort the documents in the ascending or descending order. Required.
`meta_value_type`	Literal	`float` `int` `date` Default: `none`	Parses the metadata field value into the data type specified before ranking. This only works if all metadata values stored under `meta_field` in the provided documents are strings. For example, if you specify `meta_value_type="date"` and then for the metadata field value: `"date": "2015-02-01"`, the ranker parses the string into a datetime object and sorts the documents by date. Possible values are: `float`: parses the values into floats. `int`: parses the values into integers `date`: parses the values into datetime objects. `none`: doesn't parse. Optional.

DiversityRanker Parameters

Parameter	Type	Possible Values	Description
`model_name_or_path`	Union[String, Path]	Model path Default: `all-MiniLM-L6-v2`	The path to the directory of a saved sentence transformers model. Mandatory.
`top_k`	Integer	Default: `None`	The maximum number of documents the Ranker should return. Optional.
`use_gpu`	Boolean	`True` `False` Default: `True`	Specifies whether to use all available GPUs or a CPU. Falls back on a CPU if no GPU is available. Optional.
`devices`	String, torch.device	Default: `None`	A list of devices to use for inference. Optional.
`similarity`	Literal	`dot_product` `cosine` Default: `dot_product`	Specifies the function to apply for calculating the similarity of query and passage embeddings. Required.

EmbeddingRanker Parameters

Parameters	Type	Possible Values	Description
`embedding_model`	Union[String, Path]	Model path	The path to the directory of a saved model or the name of a public model, for example: `sentence-transformers/all-mpnet-base-v2`. Required.
`top_k`	Integer	Default: `10`	The maximum number of documents the Ranker should return. Required.
`use_gpu`	Boolean	`True` `False` Default: `True`	Specifies whether to use all available GPUs or a CPU. Falls back on a CPU if no GPU is available. Required.
`devices`	String, torch.device	Default: `None`	A list of devices to use for inference. Optional.
`batch_size`	Integer	Default: `16`	The number of documents you want the ranker to process at a time. Required.
`scale_score`	Boolean	`True` `False` Default: `True`	Scales the similarity score to a unit interval in the range of 0 to 1, where 1 means extremely relevant. True - Scales similarity scores that naturally have a different value range, such as cosine or dot_product. False - Uses raw similarity scores. Required.
`max_seq_len`	Integer	Default: `512`	Specifies the maximum number of tokens the document text can have. Longer documents are truncated. Required.
`similarity`	String	`dot-product` `cosine` Default: `dot-product`	Specifies the function to apply for calculating the similarity of query and passage embeddings. Required.
`embedding_dim`	Integer	Default: `768`	Specifies the dimensionality of the embedding vector.
`return_embedding`	Boolean	`True` `False` Default:`False`	Returns document embeddings.
`use_auth_token`	Union[string, Boolean]	Default: `None`	If you're using a private model from Hugging Face, pass the API token used to download the model in this parameter. If this parameter is set to `True`, then the token generated when running `transformers-cli login` (stored in ~/.huggingface) is used. Optional.
`raise_for_missing_embeddings`	Boolean	`True` `False` Default: `True`	Raises an error if there are embeddings missing.

LostInTheMiddleRanker Parameters

Parameter	Type	Possible Values	Description
`word_count_threshold`	Integer	Default: `None`	The maximum total number of words across all documents the ranker selects. If you specify this parameter, the ranker includes all documents up to the point where adding another document would exceed the `word_count_threshold`. The last document that exceeds the threshold is included in the resulting list of documents, but all subsequent documents are discarded. Optional.
`top_k`	Integer	Default: `None`	The maximum number you want the ranker to return. Optional.

RecentnessRanker Parameters

Parameter	Type	Possible Values	Description
`date_meta_field`	String		The name of the metadata field in your documents that contains the date, for example `updated_at`. This is a required parameter, as dates are needed for sorting documents from newest to oldest. Required.
`top_k`	Integer	Default: `None` (all documents are returned)	Specifies how many documents to return. You may want to set larger `top_k` for the Retriever and then use the RecentnessRanker `top_k` to filter the documents down. Optional.
`weight`	Float	Values in range `[0,1]` Default: `0.5`	Specifies how documents are sorted. `0` means sorting by document age is disabled. `0.5` means both document content and its age have the same impact. `1` means documents are sorted by age only. The most recent documents come first. Optional.
`ranking_mode`	String	`score` `reciprocal_rank_fusion` Default: `reciprocal_rank_fusion`	Specifies the method used to combine the documents fetched by the Retriever with recentness ranking. `reciprocal_rank_fusion` - combines individual document rankings and uses the outcome to rank the documents. `score` - uses the document's score returned by the Retriever. Make sure you use `score` only with Retrievers or Rankers that return properly distributed scores in the range [0,1] If your Retriever doesn't return properly distributed scores (like BM25Retriever), you can either set the method to `reciprocal_rank_fusion` or combine RecentnessRanker with a model-based Ranker, such as SentenceTransfomersRanker.

SentenceTransformersRanker Parameters

Parameter	Type	Possible Values	Description
`model_name_or_path`	String	Example: `cross-encoder/ms-marco-MiniLM-L-12-v2`	The path to a saved model or the name of a public model from Hugging Face. For a list of available models, see cross encoders. Required.
`model_version`	String	Default: `None`	The version of the model from Hugging Face. This can be a tag name, a branch name, or a commit hash. Optional.
`top_k`	Integer	Default: `10`	The maximum number of documents to return. Required.
`use_gpu`	Boolean	`True` `False` Default: `True`	Specifies whether to use all available GPUs or a CPU. Falls back on a CPU if no GPU is available. Required
`batch_size`	Integer	Default: `16`	The number of documents you want the ranker to process at a time. Required
`scale_score`	Boolean	`True` `False` Default: `True`	If the model only predicts a single label, the raw predictions are transformed using a Sigmoid activation function. No scaling is applied to multi-label predictions. If you don't want to scale raw predictions, set this value to `False`. Required.
`progress_bar`	Boolean	`True` `False` Default: `True`	Shows a progress bar when processing the documents. Required.
`use_auth_token`	Union[string, Boolean]	Default: `None`	If you're using a private model from Hugging Face, pass the API token used to download the model in this parameter. If this parameter is set to `True`, then the token generated when running `transformers-cli login` (stored in ~/.huggingface) is used. Optional.
`embed_meta_fields`	List of strings	Default: `None`	Concatenates the provided meta fields to a text passage that is then used in reranking. The concatenated metadata are not included in the returned documents.
`model_kwargs`	Dictionary.	Default: `None`	Additional keyword arguments passed to `AutoModelForSequenceClassification.from_pretrained` when loading the model specified in `model_name_or_path`. See the model's documentation for details on what kwargs you can pass.

CNSentenceTransformersRanker Parameters

This ranker uses the same parameters as SentenceTransformersRanker with an additional tokenizer_kwargs parameter:

Parameter	Type	Possible Values	Description
`tokenizer_kwargs`	Dictionary	Default: `None`	Additional keyword arguments you can pass to the tokenizer. For details, check the model documentation. Optional.

REST API Runtime Parameters

For all Rankers, you can pass the following parameters at runtime:

Parameter	Type	Description
`top_k`	Integer	The maximum number of ranked documents to return. For default values, see the `top_k` parameter description in the YAML Parameters section for each ranker.