简介
Search-o1 提出一种将大规模推理模型与 自主检索增强生成（Agentic RAG） 和 文档内推理（Reason-in-Documents） 结合的框架。当模型在推理过程中遇到知识空缺时，会主动检索外部信息、进行精炼，并将结果注入推理链，从而提升科学、数学、编程等复杂任务中的推理准确性与稳健性。论文链接：Arxiv。
流程
复现
编写Pipeline
基于上面的逻辑，可以写出如下 Pipeline：
examples/search_o1.yaml# 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
编译Pipeline文件
ultrarag build examples/search_o1.yaml
修改参数文件
examples/parameters/search_o1_parameter.yamlbenchmark:
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
model_name_or_path: Qwen/QwQ-32B
trust_remote_code: true
extra_params:
chat_template_kwargs:
enable_thinking: false
top_k: 20
repetition_penalty: 1.05
include_stop_str_in_output: true
stop:
- <|im_end|>
- <|end_search_query|>
sampling_params:
max_tokens: 2048
max_tokens: 32768
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
model_name_or_path: Qwen/Qwen3-Embedding-0.6B
query_instruction: ''
top_k: 5
运行Pipeline文件
ultrarag run examples/search_o1.yaml