DEFAULT:
    pdf_cached: ./assets/paper/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
    # embedding: BAAI/llm-embedder
    embedding: jinaai/jina-embeddings-v3
    embedding_task: text-matching # ONLY FOR JINA_v3, retrieval.passage, text-matching, retrieval.query
    embedding_database: text-matching # ONLY FOR JINA_v3, retrieval.passage, text-matching, retrieval.query


ARTICLE:
    summarizing_prompt: ./assets/prompt/summarizing.xml

RETRIEVE:
    retriever_name: "SNKG"
    # retriever_name: "SN"
    SN_field_name: "background"
    use_cocite: True
    use_cluster_to_filter: False # 过滤器中使用聚类算法
    cite_type: "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，这个参数是不用的，就默认一次
    kg_cover_num: 7  # entity重合数量，就是两个entity共同同时出现在了kg_cover_num篇文章中
    sum_paper_num: 100  # 最多检索到的paper数量，指的是通过entity检索到的paper数量
    sn_retrieve_paper_num: 100 # 通过SN检索到的文章
    all_retrieve_paper_num: 10
    cocite_top_k: 1
    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, 60, 80, 100, 120, 150]
    s_bg: 1.0
    s_contribution: 0.0
    s_summary: 0.0
    s_abstract: 0.0
    similarity_threshold: 0.95
    # similarity_threshold: 0.55