> ## Documentation Index
> Fetch the complete documentation index at: https://ultrarag.openbmb.cn/llms.txt
> Use this file to discover all available pages before exploring further.

# Search-o1

## Introduction

Search-o1 proposes a framework that combines large-scale reasoning models with **Agentic Retrieval-Augmented Generation (Agentic RAG)** and **Reason-in-Documents**. When the model encounters a knowledge gap during the reasoning process, it actively retrieves external information, refines it, and injects the result into the reasoning chain, thereby improving the reasoning accuracy and robustness in complex tasks such as science, mathematics, and programming.

<Note>Paper link: [Arxiv](https://arxiv.org/abs/2501.05366).</Note>

### Process

<img src="https://mintcdn.com/ultrarag/eZB30PCHMVOmoD_u/images/pipeline/searcho1/suanfa.png?fit=max&auto=format&n=eZB30PCHMVOmoD_u&q=85&s=9e2cece695d930c1d41091e85524dc67" alt="" width="1366" height="940" data-path="images/pipeline/searcho1/suanfa.png" />

In short, Search-o1 starts reasoning with the original question; once an information gap is identified, it generates a sub-question and triggers retrieval; then it refines the retrieved response, extracting key information to inject back into the reasoning process until a credible final answer is formed.

## Reproduction

### Write Pipeline

Based on the above logic, the following Pipeline can be written:

```yaml examples/search_o1.yaml icon="https://mintcdn.com/ultrarag/T7GffHzZitf6TThi/images/yaml.svg?fit=max&auto=format&n=T7GffHzZitf6TThi&q=85&s=69b41e79144bc908039c2ee3abbb1c3b" theme={null}
# Search-o1 Demo

# 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
- custom.search_o1_init_list
- 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
          - custom.search_o1_reasoning_extract
          - custom.search_o1_combine_list
          - prompt.search_o1_reasoning_indocument
          - generation.generate
          - custom.search_o1_extract_final_information
          - custom.search_o1_combine_final_information
          - prompt.search_o1_insert
          - generation.generate
          stop: []   
- custom.output_extract_from_boxed
- evaluation.evaluate
```

### Compile Pipeline File

```shell theme={null}
ultrarag build examples/search_o1.yaml
```

### Modify Parameter File

```yaml examples/parameters/search_o1_parameter.yaml icon="https://mintcdn.com/ultrarag/T7GffHzZitf6TThi/images/yaml.svg?fit=max&auto=format&n=T7GffHzZitf6TThi&q=85&s=69b41e79144bc908039c2ee3abbb1c3b"  theme={null}
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: abc
      base_delay: 1.0
      base_url: http://localhost:8000/v1
      concurrency: 8
      model_name: MiniCPM4-8B
      retries: 3
    vllm:
      dtype: auto
      gpu_ids: 2,3
      gpu_memory_utilization: 0.9
      model_name_or_path: openbmb/MiniCPM4-8B # [!code --]
      model_name_or_path: Qwen/QwQ-32B # [!code ++]
      trust_remote_code: true
  extra_params:
    chat_template_kwargs: # [!code --]
      enable_thinking: false # [!code --]
    top_k: 20 # [!code ++]
    repetition_penalty: 1.05 # [!code ++]
    include_stop_str_in_output: true # [!code ++]
    stop: # [!code ++]
    - <|im_end|> # [!code ++]
    - <|end_search_query|> # [!code ++]
  sampling_params:
    max_tokens: 2048 # [!code --]
    max_tokens: 32768 # [!code ++]
    temperature: 0.7
    top_p: 0.8
  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
      model_warmup: false
      pooling_method: auto
      trust_remote_code: true
    openai:
      api_key: abc
      base_url: https://api.openai.com/v1
      model_name: text-embedding-3-small
    sentence_transformers:
      sentence_transformers_encode:
        encode_chunk_size: 256
        normalize_embeddings: false
        psg_prompt_name: document
        psg_task: null
        q_prompt_name: query
        q_task: null
      trust_remote_code: true
  batch_size: 16
  collection_name: wiki
  corpus_path: data/corpus_example.jsonl
  gpu_ids: '1'
  index_backend: faiss
  index_backend_configs:
    faiss:
      index_chunk_size: 10000
      index_path: index/index.index
      index_use_gpu: true
    milvus:
      id_field_name: id
      id_max_length: 64
      index_chunk_size: 1000
      index_params:
        index_type: AUTOINDEX
        metric_type: IP
      metric_type: IP
      search_params:
        metric_type: IP
        params: {}
      text_field_name: contents
      text_max_length: 60000
      token: null
      uri: index/milvus_demo.db
      vector_field_name: vector
  is_demo: false
  is_multimodal: false
  model_name_or_path: openbmb/MiniCPM-Embedding-Light # [!code --]
  model_name_or_path: Qwen/Qwen3-Embedding-0.6B # [!code ++]
  query_instruction: ''
  top_k: 5
```

### Run Pipeline File

```shell theme={null}
ultrarag run examples/search_o1.yaml
```