configs/datasets.yaml

DEFAULT:
    pdf_cached: /data/llms/data/scipip-data/pdf_cached
    ignore_paper_id_list: ./assets/data/ignore_paper_id_list.json
    log_level: "DEBUG"
    log_dir: ./log
    embedding: "sentence-transformers/all-MiniLM-L6-v2"
    device: "cpu" # "cpu"

ARTICLE:
    summarizing_prompt: ./prompt/summarizing.xml

RETRIEVE:
    cite_type: "all_cite_id_list"
    limit_num: 100  # 限制entity对应的paper数量
    sn_num_for_entity: 5 # SN搜索的文章数量，扩充entity
    kg_jump_num: 1   # 跳数
    kg_cover_num: 3  # entity重合数量
    max_paper_num_after_filter: 10 # 过滤后最多保留的论文数量
    min_paper_num_after_filter: 5 # 过滤后最多保留的论文数量
    sum_paper_num: 100  # 最多检索到的paper数量
    sn_retrieve_paper_num: 55 # 通过SN检索到的文章
    cocite_top_k: 1
    use_cocite: True
    use_cluster_to_filter: True # 过滤器中使用聚类算法
    need_normalize: True
    alpha: 1
    beta: 0
    relation_name: "related" # "connect"
    top_p_list: [0.1, 0.2, 0.3, 0.4, 0.5]
    top_k_list: [10, 20, 30, 40, 50]
    s_bg: 0
    s_contribution: 0.5
    s_summary: 0.5
    similarity_threshold: 0.55

used_llms_apis:
    summarization: ZhipuAI
    generation: OpenAI