Mxbai Rerank Large V2 Seq

🚀 Rewritten Mixedbread Reranker as Classifier

This repository presents the Mixedbread reranker rewritten as a classifier, which, as of March 2025, stands as the most powerful reranker, particularly useful for RAG.

🚀 Quick Start

FP8 Deployment on NVIDIA L4/H100

The following is the configuration for deploying the model on NVIDIA L4/H100 using FP8.

build_commands: []
environment_variables: {}
external_package_dirs: []
model_metadata:
  example_model_input:
    input: 'ERROR: This redirects to the embedding endpoint. Use the /sync API to
      reach /sync/predict'
model_name: BEI-mixedbread-ai-mxbai-rerank-base-v2-reranker-fp8-truss-example
python_version: py39
requirements: []
resources:
  accelerator: L4
  cpu: '1'
  memory: 10Gi
  use_gpu: true
secrets: {}
system_packages: []
trt_llm:
  build:
    base_model: encoder
    checkpoint_repository:
      repo: michaelfeil/mxbai-rerank-large-v2-seq
      revision: main
      source: HF
    max_num_tokens: 32768
    max_seq_len: 1000001
    num_builder_gpus: 4
    quantization_type: fp8

To push the deployment on Baseten.co, follow these steps:

pip install truss --upgrade
nano config.yaml # above config
truss push --publish

For more information, refer to this link.

✨ Features

• State-of-the-art Performance and Efficiency: Delivers top-notch performance with high efficiency.
• Multilingual Support: Supports over 100 languages, excelling in English and Chinese.
• Code Support: Capable of handling code-related tasks.
• Long-context Support: Can process long contexts effectively.

📦 Installation

To install the mxbai-rerank library, run the following command:

pip install mxbai-rerank

💻 Usage Examples

Usage as Classifier

When using the model with Baseten.co or github.com/michaelfeil/infinity, you should utilize the classification API. You need to manually create the following prompt template, which is highly specific to this model. This template adheres to the reference implementation at this link.

def create_mxbai_v2_reranker_prompt_template(query: str, document: str, instruction: str = "") -> str:
    """
    Create a carefully formatted chat template string (without tokenizer) for ranking relevance.

    Parameters:
        query (str): The search query.
        document (str): The document text to evaluate.
        instruction (str): Special instructions (e.g., "You are an expert for Mockingbirds.")

    Returns:
        str: The formatted chat template.
    """
    instruction = f"instruction: {instruction}\n" if instruction else ""    
    # fixed system prompt, keep as is.
    system_prompt = "You are Qwen, created by Alibaba Cloud. You are a helpful assistant."
    assert not "\n" in system_prompt
    assert not "\n" in instruction[:-1]
    assert isinstance(query, str)
    assert isinstance(document, str)
    templated = (
        # keep spacing, newlines as is.
        # template for mixedbread reranker v2
        # https://huggingface.co/michaelfeil/mxbai-rerank-base-v2-seq/
       f"<|endoftext|><|im_start|>system\n{system_prompt}\n"
        "<|im_end|>\n"
        "<|im_start|>user\n"
        f"{instruction}"
        f"query: {query} \n"
        f"document: {document} \n"
        "You are a search relevance expert who evaluates how well documents match search queries. "
        "For each query-document pair, carefully analyze the semantic relationship between them, then provide your binary relevance judgment (0 for not relevant, 1 for relevant).\n"
        "Relevance:<|im_end|>\n"
        "<|im_start|>assistant\n"
    )
    return templated

Inference

from mxbai_rerank import MxbaiRerankV2

model = MxbaiRerankV2("mixedbread-ai/mxbai-rerank-large-v2")

query = "Who wrote 'To Kill a Mockingbird'?"
documents = [
    "'To Kill a Mockingbird' is a novel by Harper Lee published in 1960. It was immediately successful, winning the Pulitzer Prize, and has become a classic of modern American literature.",
    "The novel 'Moby-Dick' was written by Herman Melville and first published in 1851. It is considered a masterpiece of American literature and deals with complex themes of obsession, revenge, and the conflict between good and evil.",
    "Harper Lee, an American novelist widely known for her novel 'To Kill a Mockingbird', was born in 1926 in Monroeville, Alabama. She received the Pulitzer Prize for Fiction in 1961.",
    "Jane Austen was an English novelist known primarily for her six major novels, which interpret, critique and comment upon the British landed gentry at the end of the 18th century.",
    "The 'Harry Potter' series, which consists of seven fantasy novels written by British author J.K. Rowling, is among the most popular and critically acclaimed books of the modern era.",
    "'The Great Gatsby', a novel written by American author F. Scott Fitzgerald, was published in 1925. The story is set in the Jazz Age and follows the life of millionaire Jay Gatsby and his pursuit of Daisy Buchanan."
]

# Lets get the scores
results = model.rank(query, documents, return_documents=True, top_k=3)

print(results)

📚 Documentation

Performance

Benchmark Results

*Latency measured on A100 GPU

Training Details

The models were trained using a three-step process:

1. GRPO (Guided Reinforcement Prompt Optimization)
2. Contrastive Learning
3. Preference Learning

For more details, check our technical blog post. A research paper will be released soon.

🔧 Technical Details

Model Information

📄 License

The project uses the Apache 2.0 license.

🎓 Citation

@online{rerank2025mxbai,
  title={Every Byte Matters: Introducing mxbai-embed-xsmall-v1},
  author={Sean Lee and Aamir Shakir and Julius Lipp and Rui Huang},
  year={2025},
  url={https://www.mixedbread.com/blog/mxbai-rerank-v2},
}