Search-o1

# MCP Servers
servers:
  benchmark: servers/benchmark
  generation: servers/generation
  retriever: servers/retriever
  prompt: servers/prompt
  evaluation: servers/evaluation
  router: servers/router
  custom: servers/custom

# MCP Client Pipeline
pipeline:
- benchmark.get_data
- retriever.retriever_init
- generation.generation_init
- prompt.search_o1_init
- generation.generate
- loop:
    times: 10
    steps:
    - branch:
        router:
        - router.search_o1_check
        branches:
          retrieve:
          - custom.search_o1_query_extract
          - retriever.retriever_search:
              input:
                query_list: extract_query_list
          - prompt.searcho1_reasoning_indocument
          - generation.generate
          - prompt.search_o1_insert
          - generation.generate
          stop: []   
- custom.output_extract_from_boxed
- evaluation.evaluate

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
custom: {}
evaluation:
  metrics:
  - acc
  - f1
  - em
  - coverem
  - stringem
  - rouge-1
  - rouge-2
  - rouge-l
  save_path: output/evaluate_results.json
generation:
  backend: vllm
  backend_configs:
    hf:
      batch_size: 8
      gpu_ids: 2,3
      model_name_or_path: openbmb/MiniCPM4-8B
      trust_remote_code: true
    openai:
      api_key: ''
      base_delay: 1.0
      base_url: http://localhost:8000/v1
      concurrency: 8
      model_name: MiniCPM4-8B
      retries: 3
    vllm:
      dtype: auto
      gpu_ids: 4,5,6,7
      gpu_memory_utilization: 0.9
      model_name_or_path: openbmb/MiniCPM4-8B
      model_name_or_path: Qwen/QwQ-32B
      trust_remote_code: true
  sampling_params:
  chat_template_kwargs: 
      enable_thinking: false
    max_tokens: 2048
    max_tokens: 32768
    temperature: 0.7
    top_p: 0.8
    top_k: 20
    repetition_penalty: 1.05
    include_stop_str_in_output: true
    stop: [ "<|im_end|>", "<|end_search_query|>" ] 
  system_prompt: ''
prompt:
  searcho1_reasoning_template: prompt/search_o1_reasoning.jinja
  searcho1_refine_template: prompt/search_o1_refinement.jinja
retriever:
  backend: sentence_transformers
  backend_configs:
    bm25:
      lang: en
      save_path: index/bm25
    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
  gpu_ids: 0,1
  index_backend: faiss
  index_backend_configs:
    faiss:
      index_chunk_size: 50000
      index_path: index/index.index
      index_use_gpu: true
    milvus:
      collection_name: ultrarag_embeddings
      id_field_name: id
      index_chunk_size: 50000
      index_params:
        index_type: AUTOINDEX
        metric_type: IP
      metric_type: IP
      search_params:
        metric_type: IP
        params: {}
      token: null
      uri: index/milvus_demo.db
      vector_field_name: vector
  is_multimodal: false
  model_name_or_path: openbmb/MiniCPM-Embedding-Light
  model_name_or_path: Qwen/Qwen3-Embedding-0.6B
  query_instruction: ''
  top_k: 5