Skip to main content

​
Overview

The Reranker Server in UR-2.0 is responsible for fine-ranking retrieved results.
It takes the initial retrieval outputs from the Retriever Server and reorders the candidate documents based on semantic relevance, thereby improving retrieval precision and enhancing the quality of final generation results.
This module natively supports several mainstream backends, including Sentence-Transformers, Infinity, and OpenAI.

​
Usage Example

https://mintcdn.com/ultrarag/T7GffHzZitf6TThi/images/yaml.svg?fit=max&auto=format&n=T7GffHzZitf6TThi&q=85&s=69b41e79144bc908039c2ee3abbb1c3bexamples/corpus_rerank.yaml
# MCP Server
servers:
  benchmark: servers/benchmark
  retriever: servers/retriever
  reranker: servers/reranker

# MCP Client Pipeline
pipeline:
- benchmark.get_data
- retriever.retriever_init
- retriever.retriever_embed
- retriever.retriever_index
- retriever.retriever_search
- reranker.reranker_init
- reranker.reranker_rerank
Build the Pipeline: 
ultrarag build examples/corpus_rerank.yaml
Modify the parameters:
https://mintcdn.com/ultrarag/T7GffHzZitf6TThi/images/yaml.svg?fit=max&auto=format&n=T7GffHzZitf6TThi&q=85&s=69b41e79144bc908039c2ee3abbb1c3bexamples/parameters/corpus_search_parameter.yaml
benchmark:
  benchmark:
    key_map:
      gt_ls: golden_answers
      q_ls: question
    limit: -1
    name: nq
    path: data/sample_nq_10.jsonl
    seed: 42
    shuffle: false
reranker:
  backend: sentence_transformers
  backend_configs:
    infinity:
      bettertransformer: false
      device: cuda
      model_warmup: false
      pooling_method: auto
      trust_remote_code: true
    openai:
      api_key: ''
      base_url: https://api.openai.com/v1
      model_name: text-embedding-3-small
    sentence_transformers:
      device: cuda
      trust_remote_code: true
  batch_size: 16
  gpu_ids: 0
  model_name_or_path: openbmb/MiniCPM-Reranker-Light
  model_name_or_path: BAAI/bge-reranker-large
  query_instruction: ''
  top_k: 5
retriever:
  backend: sentence_transformers
  backend_configs:
    bm25:
      lang: en
    infinity:
      bettertransformer: false
      device: cuda
      model_warmup: false
      pooling_method: auto
      trust_remote_code: true
    openai:
      api_key: ''
      base_url: https://api.openai.com/v1
      model_name: text-embedding-3-small
    sentence_transformers:
      device: cuda
      sentence_transformers_encode:
        encode_chunk_size: 10000
        normalize_embeddings: false
        psg_prompt_name: document
        psg_task: null
        q_prompt_name: query
        q_task: null
      trust_remote_code: true
  batch_size: 16
  corpus_path: data/corpus_example.jsonl
  embedding_path: embedding/embedding.npy
  faiss_use_gpu: true
  gpu_ids: 0,1
  gpu_ids: 1
  index_chunk_size: 50000
  index_path: index/index.index
  is_multimodal: false
  model_name_or_path: openbmb/MiniCPM-Embedding-Light
  model_name_or_path: Qwen/Qwen3-Embedding-0.6B
  overwrite: false
  query_instruction: ''
  top_k: 5
Run the Pipeline: 
ultrarag run examples/corpus_rerank.yaml