1  ---
 2  enhancements:
 3    - |
 4      The parameters ``query_suffix`` and ``document_suffix`` have been added to ``SentenceTransformersSimilarityRanker`` to support the Qwen3 reranker model family.
 5  
 6      Here is an example of how to use these new parameters to use the Qwen3-Reranker-0.6B:
 7  
 8      .. code:: python
 9  
10         from haystack import Document
11         from haystack.components.rankers.sentence_transformers_similarity import SentenceTransformersSimilarityRanker
12  
13         ranker = SentenceTransformersSimilarityRanker(
14             model="tomaarsen/Qwen3-Reranker-0.6B-seq-cls",
15             query_prefix='<|im_start|>system\nJudge whether the Document meets the requirements based on the Query and the Instruct provided. Note that the answer can only be "yes" or "no".<|im_end|>\n<|im_start|>user\n<Instruct>: Given a web search query, retrieve relevant passages that answer the query\n<Query>: ',
16             query_suffix="\n",
17             document_prefix="<Document>: ",
18             document_suffix="<|im_end|>\n<|im_start|>assistant\n<think>\n\n</think>\n\n",
19         )
20  
21         result = ranker.run(
22             query="Which planet is known as the Red Planet?",
23             documents=[
24                 Document(content="Venus is often called Earth's twin because of its similar size and proximity."),
25                 Document(content="Mars, known for its reddish appearance, is often referred to as the Red Planet."),
26                 Document(content="Jupiter, the largest planet in our solar system, has a prominent red spot."),
27                 Document(content="Saturn, famous for its rings, is sometimes mistaken for the Red Planet."),
28             ],
29         )
30  
31         print(result)
32  
33      NOTE: This only works with the Qwen3 reranker models that use the sequence classification architecture.
34      For example, you can find some on ``tomaarsen``'s Hugging Face profile.