Hypergraph is more powerful. Transform unstructured text into structured knowledge with LLMs. Graphs, hypergraphs, and spatio-temporal extractions — with one command.
Merge branch 'main' of github.com:yifanfeng97/Hyper-Extract
yifanfeng97af690aea5d62
diff --cc examples/auto_hypergraph_demo.pyindex 476d5d7,6f77ae4..84b4f66--- a/examples/auto_hypergraph_demo.py+++ b/examples/auto_hypergraph_demo.py@@@ -49,15 -51,13 +49,13 @@@ class NarrativeUnit(BaseModel)关键在于:它通过一个 'type' 字段来区分语义,但结构上都是连接多个实体的超边。"""- summary: str = Field(..., description="简短描述这个单元发生了什么,或者是什么关系")+ summary: str = Field(description="简短描述这个单元发生了什么,或者是什么关系")# 这里体现了"多类型":LLM 会判断这具体是什么类型的连接- edge_type: str = Field(- description="超边类型: Conflict(冲突), Alliance(结盟), Possession(持有), Meeting(会议), State(状态)",- )+ edge_type: str = Field(description="超边类型: Conflict(冲突), Alliance(结盟), Possession(持有), Meeting(会议), State(状态)")# 核心:连接所有相关的实体- participants: List[str] = Field(..., description="所有牵涉其中的实体名称列表")+ participants: List[str] = Field(description="所有牵涉其中的实体名称列表")# ==============================================================================