Hypergraph is more powerful. Transform unstructured text into structured knowledge with LLMs. Graphs, hypergraphs, and spatio-temporal extractions — with one command.
feat: 为历史和中医学模板添加分块参数配置
yifanfeng97c841d426a422
diff --git a/examples/template_history_demo.py b/examples/template_history_demo.pyindex 71b78bc..1274404 100644--- a/examples/template_history_demo.py+++ b/examples/template_history_demo.py@@ -68,12 +68,12 @@ TEMPLATE_TO_INPUT = {# ==========================================# 历史专著-TEMPLATE = HistoricalKnowledgeGraph+# TEMPLATE = HistoricalKnowledgeGraph# TEMPLATE = MultiParticipantEventMap# 编年史# TEMPLATE = ChronologicalEventChain-# TEMPLATE = HistoricalContextGraph+TEMPLATE = HistoricalContextGraph# TEMPLATE = PoliticalStruggleHypergraph# 口述历史@@ -135,7 +135,6 @@ def main():llm_client=llm,embedder=embedder,verbose=True,- chunk_size=512,)# 喂入文本diff --git a/hyperextract/templates/zh/history/chronological_event_chain.py b/hyperextract/templates/zh/history/chronological_event_chain.pyindex 3b4e32d..2a85d1c 100644--- a/hyperextract/templates/zh/history/chronological_event_chain.py+++ b/hyperextract/templates/zh/history/chronological_event_chain.py@@ -128,6 +128,8 @@ class ChronologicalEventChain(AutoTemporalGraph[EventNode, TemporalEventEdge]):*,extraction_mode: str = "two_stage",observation_time: str | None = None,+ chunk_size: int = 512,+ chunk_overlap: int = 64,max_workers: int = 10,verbose: bool = False,**kwargs: Any,@@ -142,6 +144,8 @@ class ChronologicalEventChain(AutoTemporalGraph[EventNode, TemporalEventEdge]):或 "two_stage"(先提取节点,再提取边),默认为 "two_stage"observation_time: 观察时间,用于解析相对时间表达,如未指定则使用当前日期+ chunk_size: 每个分块的最大字符数,默认为 512(历史文本信息量大,需较小分块)+ chunk_overlap: 分块之间的重叠字符数,默认为 64max_workers: 最大工作线程数,默认为 10verbose: 是否输出详细日志,默认为 False**kwargs: 其他技术参数,传递给基类@@ -162,6 +166,8 @@ class ChronologicalEventChain(AutoTemporalGraph[EventNode, TemporalEventEdge]):prompt=_PROMPT,prompt_for_node_extraction=_NODE_PROMPT,prompt_for_edge_extraction=_EDGE_PROMPT,+ chunk_size=chunk_size,+ chunk_overlap=chunk_overlap,**kwargs,)diff --git a/hyperextract/templates/zh/history/epistolary_knowledge_graph.py b/hyperextract/templates/zh/history/epistolary_knowledge_graph.pyindex 49f28d4..b0c101c 100644--- a/hyperextract/templates/zh/history/epistolary_knowledge_graph.py+++ b/hyperextract/templates/zh/history/epistolary_knowledge_graph.py@@ -117,6 +117,8 @@ class EpistolaryKnowledgeGraph(AutoGraph[CorrespondentNode, LetterContentEdge]):embedder: Embeddings,*,extraction_mode: str = "two_stage",+ chunk_size: int = 512,+ chunk_overlap: int = 64,max_workers: int = 10,verbose: bool = False,**kwargs: Any,@@ -129,6 +131,8 @@ class EpistolaryKnowledgeGraph(AutoGraph[CorrespondentNode, LetterContentEdge]):embedder: 嵌入模型,用于语义检索extraction_mode: 提取模式,可选 "one_stage"(同时提取节点和边)或 "two_stage"(先提取节点,再提取边),默认为 "two_stage"+ chunk_size: 每个分块的最大字符数,默认为 512(历史文本信息量大,需较小分块)+ chunk_overlap: 分块之间的重叠字符数,默认为 64max_workers: 最大工作线程数,默认为 10verbose: 是否输出详细日志,默认为 False**kwargs: 其他技术参数,传递给基类@@ -147,6 +151,8 @@ class EpistolaryKnowledgeGraph(AutoGraph[CorrespondentNode, LetterContentEdge]):prompt=_PROMPT,prompt_for_node_extraction=_NODE_PROMPT,prompt_for_edge_extraction=_EDGE_PROMPT,+ chunk_size=chunk_size,+ chunk_overlap=chunk_overlap,**kwargs,)diff --git a/hyperextract/templates/zh/history/historical_context_graph.py b/hyperextract/templates/zh/history/historical_context_graph.pyindex c3b0081..c624e67 100644--- a/hyperextract/templates/zh/history/historical_context_graph.py+++ b/hyperextract/templates/zh/history/historical_context_graph.py@@ -106,6 +106,8 @@ class HistoricalContextGraph(AutoGraph[ContextEntityNode, ContextRelationEdge]):embedder: Embeddings,*,extraction_mode: str = "two_stage",+ chunk_size: int = 512,+ chunk_overlap: int = 64,max_workers: int = 10,verbose: bool = False,**kwargs: Any,@@ -118,6 +120,8 @@ class HistoricalContextGraph(AutoGraph[ContextEntityNode, ContextRelationEdge]):embedder: 嵌入模型,用于语义检索extraction_mode: 提取模式,可选 "one_stage"(同时提取节点和边)或 "two_stage"(先提取节点,再提取边),默认为 "two_stage"+ chunk_size: 每个分块的最大字符数,默认为 512(历史文本信息量大,需较小分块)+ chunk_overlap: 分块之间的重叠字符数,默认为 64max_workers: 最大工作线程数,默认为 10verbose: 是否输出详细日志,默认为 False**kwargs: 其他技术参数,传递给基类@@ -136,6 +140,8 @@ class HistoricalContextGraph(AutoGraph[ContextEntityNode, ContextRelationEdge]):prompt=_PROMPT,prompt_for_node_extraction=_NODE_PROMPT,prompt_for_edge_extraction=_EDGE_PROMPT,+ chunk_size=chunk_size,+ chunk_overlap=chunk_overlap,**kwargs,)diff --git a/hyperextract/templates/zh/history/historical_knowledge_graph.py b/hyperextract/templates/zh/history/historical_knowledge_graph.pyindex 5579a87..a3d615d 100644--- a/hyperextract/templates/zh/history/historical_knowledge_graph.py+++ b/hyperextract/templates/zh/history/historical_knowledge_graph.py@@ -108,6 +108,8 @@ class HistoricalKnowledgeGraph(AutoGraph[HistoricalPersonNode, PersonRelationEdgembedder: Embeddings,*,extraction_mode: str = "two_stage",+ chunk_size: int = 512,+ chunk_overlap: int = 64,max_workers: int = 10,verbose: bool = False,**kwargs: Any,@@ -120,6 +122,8 @@ class HistoricalKnowledgeGraph(AutoGraph[HistoricalPersonNode, PersonRelationEdgembedder: 嵌入模型,用于语义检索extraction_mode: 提取模式,可选 "one_stage"(同时提取节点和边)或 "two_stage"(先提取节点,再提取边),默认为 "two_stage"+ chunk_size: 每个分块的最大字符数,默认为 512(历史文本信息量大,需较小分块)+ chunk_overlap: 分块之间的重叠字符数,默认为 64max_workers: 最大工作线程数,默认为 10verbose: 是否输出详细日志,默认为 False**kwargs: 其他技术参数,传递给基类@@ -138,6 +142,8 @@ class HistoricalKnowledgeGraph(AutoGraph[HistoricalPersonNode, PersonRelationEdgprompt=_PROMPT,prompt_for_node_extraction=_NODE_PROMPT,prompt_for_edge_extraction=_EDGE_PROMPT,+ chunk_size=chunk_size,+ chunk_overlap=chunk_overlap,**kwargs,)diff --git a/hyperextract/templates/zh/history/memory_flashback_list.py b/hyperextract/templates/zh/history/memory_flashback_list.pyindex d3538b1..2b0586a 100644--- a/hyperextract/templates/zh/history/memory_flashback_list.py+++ b/hyperextract/templates/zh/history/memory_flashback_list.py@@ -58,6 +58,8 @@ class MemoryFlashbackList(AutoList[MemoryFragment]):llm_client: BaseChatModel,embedder: Embeddings,*,+ chunk_size: int = 512,+ chunk_overlap: int = 64,max_workers: int = 10,verbose: bool = False,**kwargs: Any,@@ -68,6 +70,8 @@ class MemoryFlashbackList(AutoList[MemoryFragment]):Args:llm_client: LLM 客户端,用于知识提取embedder: 嵌入模型,用于语义检索+ chunk_size: 每个分块的最大字符数,默认为 512(历史文本信息量大,需较小分块)+ chunk_overlap: 分块之间的重叠字符数,默认为 64max_workers: 最大工作线程数,默认为 10verbose: 是否输出详细日志,默认为 False**kwargs: 其他技术参数,传递给基类@@ -79,6 +83,8 @@ class MemoryFlashbackList(AutoList[MemoryFragment]):max_workers=max_workers,verbose=verbose,prompt=_PROMPT,+ chunk_size=chunk_size,+ chunk_overlap=chunk_overlap,**kwargs,)diff --git a/hyperextract/templates/zh/history/multi_participant_event_map.py b/hyperextract/templates/zh/history/multi_participant_event_map.pyindex 9c3d920..73ac64f 100644--- a/hyperextract/templates/zh/history/multi_participant_event_map.py+++ b/hyperextract/templates/zh/history/multi_participant_event_map.py@@ -113,6 +113,8 @@ class MultiParticipantEventMap(AutoHypergraph[EventParticipantNode, EventHyperedembedder: Embeddings,*,extraction_mode: str = "two_stage",+ chunk_size: int = 512,+ chunk_overlap: int = 64,max_workers: int = 10,verbose: bool = False,**kwargs: Any,@@ -125,6 +127,8 @@ class MultiParticipantEventMap(AutoHypergraph[EventParticipantNode, EventHyperedembedder: 嵌入模型,用于语义检索extraction_mode: 提取模式,可选 "one_stage"(同时提取节点和边)或 "two_stage"(先提取节点,再提取边),默认为 "two_stage"+ chunk_size: 每个分块的最大字符数,默认为 512(历史文本信息量大,需较小分块)+ chunk_overlap: 分块之间的重叠字符数,默认为 64max_workers: 最大工作线程数,默认为 10verbose: 是否输出详细日志,默认为 False**kwargs: 其他技术参数,传递给基类@@ -146,6 +150,8 @@ class MultiParticipantEventMap(AutoHypergraph[EventParticipantNode, EventHyperedprompt=_PROMPT,prompt_for_node_extraction=_NODE_PROMPT,prompt_for_edge_extraction=_EDGE_PROMPT,+ chunk_size=chunk_size,+ chunk_overlap=chunk_overlap,**kwargs,)diff --git a/hyperextract/templates/zh/history/narrative_relation_graph.py b/hyperextract/templates/zh/history/narrative_relation_graph.pyindex 726e223..bb10f9e 100644--- a/hyperextract/templates/zh/history/narrative_relation_graph.py+++ b/hyperextract/templates/zh/history/narrative_relation_graph.py@@ -109,6 +109,8 @@ class NarrativeRelationGraph(AutoGraph[NarrativeCharacterNode, NarrativeInteractembedder: Embeddings,*,extraction_mode: str = "two_stage",+ chunk_size: int = 512,+ chunk_overlap: int = 64,max_workers: int = 10,verbose: bool = False,**kwargs: Any,@@ -121,6 +123,8 @@ class NarrativeRelationGraph(AutoGraph[NarrativeCharacterNode, NarrativeInteractembedder: 嵌入模型,用于语义检索extraction_mode: 提取模式,可选 "one_stage"(同时提取节点和边)或 "two_stage"(先提取节点,再提取边),默认为 "two_stage"+ chunk_size: 每个分块的最大字符数,默认为 512(历史文本信息量大,需较小分块)+ chunk_overlap: 分块之间的重叠字符数,默认为 64max_workers: 最大工作线程数,默认为 10verbose: 是否输出详细日志,默认为 False**kwargs: 其他技术参数,传递给基类@@ -139,6 +143,8 @@ class NarrativeRelationGraph(AutoGraph[NarrativeCharacterNode, NarrativeInteractprompt=_PROMPT,prompt_for_node_extraction=_NODE_PROMPT,prompt_for_edge_extraction=_EDGE_PROMPT,+ chunk_size=chunk_size,+ chunk_overlap=chunk_overlap,**kwargs,)diff --git a/hyperextract/templates/zh/history/personal_trajectory_hypergraph.py b/hyperextract/templates/zh/history/personal_trajectory_hypergraph.pyindex ac5a1ba..0f0b591 100644--- a/hyperextract/templates/zh/history/personal_trajectory_hypergraph.py+++ b/hyperextract/templates/zh/history/personal_trajectory_hypergraph.py@@ -113,6 +113,8 @@ class PersonalTrajectoryHypergraph(AutoHypergraph[PersonNode, LifePhaseHyperedgeembedder: Embeddings,*,extraction_mode: str = "two_stage",+ chunk_size: int = 512,+ chunk_overlap: int = 64,max_workers: int = 10,verbose: bool = False,**kwargs: Any,@@ -125,6 +127,8 @@ class PersonalTrajectoryHypergraph(AutoHypergraph[PersonNode, LifePhaseHyperedgeembedder: 嵌入模型,用于语义检索extraction_mode: 提取模式,可选 "one_stage"(同时提取节点和边)或 "two_stage"(先提取节点,再提取边),默认为 "two_stage"+ chunk_size: 每个分块的最大字符数,默认为 512(历史文本信息量大,需较小分块)+ chunk_overlap: 分块之间的重叠字符数,默认为 64max_workers: 最大工作线程数,默认为 10verbose: 是否输出详细日志,默认为 False**kwargs: 其他技术参数,传递给基类@@ -146,6 +150,8 @@ class PersonalTrajectoryHypergraph(AutoHypergraph[PersonNode, LifePhaseHyperedgeprompt=_PROMPT,prompt_for_node_extraction=_NODE_PROMPT,prompt_for_edge_extraction=_EDGE_PROMPT,+ chunk_size=chunk_size,+ chunk_overlap=chunk_overlap,**kwargs,)diff --git a/hyperextract/templates/zh/history/political_struggle_hypergraph.py b/hyperextract/templates/zh/history/political_struggle_hypergraph.pyindex 35113e2..c2d6aeb 100644--- a/hyperextract/templates/zh/history/political_struggle_hypergraph.py+++ b/hyperextract/templates/zh/history/political_struggle_hypergraph.py@@ -120,6 +120,8 @@ class PoliticalStruggleHypergraph(AutoHypergraph[PoliticalActorNode, StruggleHypembedder: Embeddings,*,extraction_mode: str = "two_stage",+ chunk_size: int = 512,+ chunk_overlap: int = 64,max_workers: int = 10,verbose: bool = False,**kwargs: Any,@@ -132,6 +134,8 @@ class PoliticalStruggleHypergraph(AutoHypergraph[PoliticalActorNode, StruggleHypembedder: 嵌入模型,用于语义检索extraction_mode: 提取模式,可选 "one_stage"(同时提取节点和边)或 "two_stage"(先提取节点,再提取边),默认为 "two_stage"+ chunk_size: 每个分块的最大字符数,默认为 512(历史文本信息量大,需较小分块)+ chunk_overlap: 分块之间的重叠字符数,默认为 64max_workers: 最大工作线程数,默认为 10verbose: 是否输出详细日志,默认为 False**kwargs: 其他技术参数,传递给基类@@ -158,6 +162,8 @@ class PoliticalStruggleHypergraph(AutoHypergraph[PoliticalActorNode, StruggleHypprompt=_PROMPT,prompt_for_node_extraction=_NODE_PROMPT,prompt_for_edge_extraction=_EDGE_PROMPT,+ chunk_size=chunk_size,+ chunk_overlap=chunk_overlap,**kwargs,)diff --git a/hyperextract/templates/zh/tcm/acupoint_location_map.py b/hyperextract/templates/zh/tcm/acupoint_location_map.pyindex 7885905..62c5141 100644--- a/hyperextract/templates/zh/tcm/acupoint_location_map.py+++ b/hyperextract/templates/zh/tcm/acupoint_location_map.py@@ -99,6 +99,8 @@ class AcupointLocationMap(AutoGraph[AcupointNode, LocationRelation]):embedder: Embeddings,*,extraction_mode: str = "two_stage",+ chunk_size: int = 512,+ chunk_overlap: int = 64,max_workers: int = 10,verbose: bool = False,**kwargs: Any,@@ -111,6 +113,8 @@ class AcupointLocationMap(AutoGraph[AcupointNode, LocationRelation]):embedder: 嵌入模型,用于语义检索extraction_mode: 提取模式,可选 "one_stage"(同时提取节点和边)或 "two_stage"(先提取节点,再提取边),默认为 "two_stage"+ chunk_size: 每个分块的最大字符数,默认为 512(中医文本信息量大,需较小分块)+ chunk_overlap: 分块之间的重叠字符数,默认为 64max_workers: 最大工作线程数,默认为 10verbose: 是否输出详细日志,默认为 False**kwargs: 其他技术参数,传递给基类@@ -124,6 +128,8 @@ class AcupointLocationMap(AutoGraph[AcupointNode, LocationRelation]):llm_client=llm_client,embedder=embedder,extraction_mode=extraction_mode,+ chunk_size=chunk_size,+ chunk_overlap=chunk_overlap,max_workers=max_workers,verbose=verbose,prompt=_PROMPT,diff --git a/hyperextract/templates/zh/tcm/compatibility_net.py b/hyperextract/templates/zh/tcm/compatibility_net.pyindex 2456b0a..1ee91dc 100644--- a/hyperextract/templates/zh/tcm/compatibility_net.py+++ b/hyperextract/templates/zh/tcm/compatibility_net.py@@ -94,6 +94,8 @@ class CompatibilityNet(AutoGraph[HerbEntity, CompatibilityRelation]):embedder: Embeddings,*,extraction_mode: str = "two_stage",+ chunk_size: int = 512,+ chunk_overlap: int = 64,max_workers: int = 10,verbose: bool = False,**kwargs: Any,@@ -106,6 +108,8 @@ class CompatibilityNet(AutoGraph[HerbEntity, CompatibilityRelation]):embedder: 嵌入模型,用于语义检索extraction_mode: 提取模式,可选 "one_stage"(同时提取节点和边)或 "two_stage"(先提取节点,再提取边),默认为 "two_stage"+ chunk_size: 每个分块的最大字符数,默认为 512(中医文本信息量大,需较小分块)+ chunk_overlap: 分块之间的重叠字符数,默认为 64max_workers: 最大工作线程数,默认为 10verbose: 是否输出详细日志,默认为 False**kwargs: 其他技术参数,传递给基类@@ -119,6 +123,8 @@ class CompatibilityNet(AutoGraph[HerbEntity, CompatibilityRelation]):llm_client=llm_client,embedder=embedder,extraction_mode=extraction_mode,+ chunk_size=chunk_size,+ chunk_overlap=chunk_overlap,max_workers=max_workers,verbose=verbose,prompt=_PROMPT,diff --git a/hyperextract/templates/zh/tcm/formula_composition.py b/hyperextract/templates/zh/tcm/formula_composition.pyindex df7a456..4e6f262 100644--- a/hyperextract/templates/zh/tcm/formula_composition.py+++ b/hyperextract/templates/zh/tcm/formula_composition.py@@ -122,6 +122,8 @@ class FormulaComposition(AutoHypergraph[HerbNode, FormulaHyperedge]):embedder: Embeddings,*,extraction_mode: str = "two_stage",+ chunk_size: int = 512,+ chunk_overlap: int = 64,max_workers: int = 10,verbose: bool = False,**kwargs: Any,@@ -134,6 +136,8 @@ class FormulaComposition(AutoHypergraph[HerbNode, FormulaHyperedge]):embedder: 嵌入模型,用于语义检索extraction_mode: 提取模式,可选 "one_stage"(同时提取节点和边)或 "two_stage"(先提取节点,再提取边),默认为 "two_stage"+ chunk_size: 每个分块的最大字符数,默认为 512(中医文本信息量大,需较小分块)+ chunk_overlap: 分块之间的重叠字符数,默认为 64max_workers: 最大工作线程数,默认为 10verbose: 是否输出详细日志,默认为 False**kwargs: 其他技术参数,传递给基类@@ -160,6 +164,8 @@ class FormulaComposition(AutoHypergraph[HerbNode, FormulaHyperedge]):llm_client=llm_client,embedder=embedder,extraction_mode=extraction_mode,+ chunk_size=chunk_size,+ chunk_overlap=chunk_overlap,max_workers=max_workers,verbose=verbose,prompt=_PROMPT,diff --git a/hyperextract/templates/zh/tcm/function_indication_map.py b/hyperextract/templates/zh/tcm/function_indication_map.pyindex 29bf69b..857207b 100644--- a/hyperextract/templates/zh/tcm/function_indication_map.py+++ b/hyperextract/templates/zh/tcm/function_indication_map.py@@ -100,6 +100,8 @@ class FunctionIndicationMap(AutoGraph[GeneralEntity, GeneralRelation]):embedder: Embeddings,*,extraction_mode: str = "two_stage",+ chunk_size: int = 512,+ chunk_overlap: int = 64,max_workers: int = 10,verbose: bool = False,**kwargs: Any,@@ -112,6 +114,8 @@ class FunctionIndicationMap(AutoGraph[GeneralEntity, GeneralRelation]):embedder: 嵌入模型,用于语义检索extraction_mode: 提取模式,可选 "one_stage"(同时提取节点和边)或 "two_stage"(先提取节点,再提取边),默认为 "two_stage"+ chunk_size: 每个分块的最大字符数,默认为 512(中医文本信息量大,需较小分块)+ chunk_overlap: 分块之间的重叠字符数,默认为 64max_workers: 最大工作线程数,默认为 10verbose: 是否输出详细日志,默认为 False**kwargs: 其他技术参数,传递给基类@@ -125,6 +129,8 @@ class FunctionIndicationMap(AutoGraph[GeneralEntity, GeneralRelation]):llm_client=llm_client,embedder=embedder,extraction_mode=extraction_mode,+ chunk_size=chunk_size,+ chunk_overlap=chunk_overlap,max_workers=max_workers,verbose=verbose,prompt=_PROMPT,diff --git a/hyperextract/templates/zh/tcm/herb_property_model.py b/hyperextract/templates/zh/tcm/herb_property_model.pyindex 4963f12..ecce677 100644--- a/hyperextract/templates/zh/tcm/herb_property_model.py+++ b/hyperextract/templates/zh/tcm/herb_property_model.py@@ -28,9 +28,6 @@ class HerbProperty(BaseModel):_PROMPT = """## 角色与任务你是一位专业的中药学家,请从文本中提取单味药的性味归经、毒性及推荐剂量等信息。-## 核心概念定义-- **对象 (Object)**:从文本中提取的单一结构化对象,包含药物的性味归经信息-## 提取规则### 核心约束1. 识别文本的核心药物主体@@ -72,6 +69,8 @@ class HerbPropertyModel(AutoModel[HerbProperty]):llm_client: BaseChatModel,embedder: Embeddings,*,+ chunk_size: int = 512,+ chunk_overlap: int = 64,max_workers: int = 10,verbose: bool = False,**kwargs: Any,@@ -82,6 +81,8 @@ class HerbPropertyModel(AutoModel[HerbProperty]):Args:llm_client: LLM 客户端,用于知识提取embedder: 嵌入模型,用于语义检索+ chunk_size: 每个分块的最大字符数,默认为 512(中医文本信息量大,需较小分块)+ chunk_overlap: 分块之间的重叠字符数,默认为 64max_workers: 最大工作线程数,默认为 10verbose: 是否输出详细日志,默认为 False**kwargs: 其他技术参数,传递给基类@@ -91,6 +92,8 @@ class HerbPropertyModel(AutoModel[HerbProperty]):llm_client=llm_client,embedder=embedder,prompt=_PROMPT,+ chunk_size=chunk_size,+ chunk_overlap=chunk_overlap,max_workers=max_workers,verbose=verbose,**kwargs,diff --git a/hyperextract/templates/zh/tcm/meridian_flow_graph.py b/hyperextract/templates/zh/tcm/meridian_flow_graph.pyindex d661b2a..3ab446f 100644--- a/hyperextract/templates/zh/tcm/meridian_flow_graph.py+++ b/hyperextract/templates/zh/tcm/meridian_flow_graph.py@@ -100,6 +100,8 @@ class MeridianFlowGraph(AutoGraph[MeridianNode, MeridianFlowRelation]):embedder: Embeddings,*,extraction_mode: str = "two_stage",+ chunk_size: int = 512,+ chunk_overlap: int = 64,max_workers: int = 10,verbose: bool = False,**kwargs: Any,@@ -112,6 +114,8 @@ class MeridianFlowGraph(AutoGraph[MeridianNode, MeridianFlowRelation]):embedder: 嵌入模型,用于语义检索extraction_mode: 提取模式,可选 "one_stage"(同时提取节点和边)或 "two_stage"(先提取节点,再提取边),默认为 "two_stage"+ chunk_size: 每个分块的最大字符数,默认为 512(中医文本信息量大,需较小分块)+ chunk_overlap: 分块之间的重叠字符数,默认为 64max_workers: 最大工作线程数,默认为 10verbose: 是否输出详细日志,默认为 False**kwargs: 其他技术参数,传递给基类@@ -125,6 +129,8 @@ class MeridianFlowGraph(AutoGraph[MeridianNode, MeridianFlowRelation]):llm_client=llm_client,embedder=embedder,extraction_mode=extraction_mode,+ chunk_size=chunk_size,+ chunk_overlap=chunk_overlap,max_workers=max_workers,verbose=verbose,prompt=_PROMPT,diff --git a/hyperextract/templates/zh/tcm/prescription_modification.py b/hyperextract/templates/zh/tcm/prescription_modification.pyindex 73aa36a..b12ec77 100644--- a/hyperextract/templates/zh/tcm/prescription_modification.py+++ b/hyperextract/templates/zh/tcm/prescription_modification.py@@ -112,6 +112,8 @@ class PrescriptionModification(AutoHypergraph[PrescriptionNode, ModificationHypeembedder: Embeddings,*,extraction_mode: str = "two_stage",+ chunk_size: int = 512,+ chunk_overlap: int = 64,max_workers: int = 10,verbose: bool = False,**kwargs: Any,@@ -124,6 +126,8 @@ class PrescriptionModification(AutoHypergraph[PrescriptionNode, ModificationHypeembedder: 嵌入模型,用于语义检索extraction_mode: 提取模式,可选 "one_stage"(同时提取节点和边)或 "two_stage"(先提取节点,再提取边),默认为 "two_stage"+ chunk_size: 每个分块的最大字符数,默认为 512(中医文本信息量大,需较小分块)+ chunk_overlap: 分块之间的重叠字符数,默认为 64max_workers: 最大工作线程数,默认为 10verbose: 是否输出详细日志,默认为 False**kwargs: 其他技术参数,传递给基类@@ -147,6 +151,8 @@ class PrescriptionModification(AutoHypergraph[PrescriptionNode, ModificationHypellm_client=llm_client,embedder=embedder,extraction_mode=extraction_mode,+ chunk_size=chunk_size,+ chunk_overlap=chunk_overlap,max_workers=max_workers,verbose=verbose,prompt=_PROMPT,diff --git a/hyperextract/templates/zh/tcm/processing_method.py b/hyperextract/templates/zh/tcm/processing_method.pyindex efef896..65ca9ec 100644--- a/hyperextract/templates/zh/tcm/processing_method.py+++ b/hyperextract/templates/zh/tcm/processing_method.py@@ -59,6 +59,8 @@ class ProcessingMethod(AutoList[ProcessingMethodItem]):llm_client: BaseChatModel,embedder: Embeddings,*,+ chunk_size: int = 512,+ chunk_overlap: int = 64,max_workers: int = 10,verbose: bool = False,**kwargs: Any,@@ -69,6 +71,8 @@ class ProcessingMethod(AutoList[ProcessingMethodItem]):Args:llm_client: LLM 客户端,用于知识提取embedder: 嵌入模型,用于语义检索+ chunk_size: 每个分块的最大字符数,默认为 512(中医文本信息量大,需较小分块)+ chunk_overlap: 分块之间的重叠字符数,默认为 64max_workers: 最大工作线程数,默认为 10verbose: 是否输出详细日志,默认为 False**kwargs: 其他技术参数,传递给基类@@ -78,6 +82,8 @@ class ProcessingMethod(AutoList[ProcessingMethodItem]):llm_client=llm_client,embedder=embedder,prompt=_PROMPT,+ chunk_size=chunk_size,+ chunk_overlap=chunk_overlap,max_workers=max_workers,verbose=verbose,**kwargs,diff --git a/hyperextract/templates/zh/tcm/pulse_tongue_record.py b/hyperextract/templates/zh/tcm/pulse_tongue_record.pyindex 5a8a9f0..4e847f2 100644--- a/hyperextract/templates/zh/tcm/pulse_tongue_record.py+++ b/hyperextract/templates/zh/tcm/pulse_tongue_record.py@@ -61,6 +61,8 @@ class PulseTongueRecord(AutoList[PulseTongueItem]):llm_client: BaseChatModel,embedder: Embeddings,*,+ chunk_size: int = 512,+ chunk_overlap: int = 64,max_workers: int = 10,verbose: bool = False,**kwargs: Any,@@ -71,6 +73,8 @@ class PulseTongueRecord(AutoList[PulseTongueItem]):Args:llm_client: LLM 客户端,用于知识提取embedder: 嵌入模型,用于语义检索+ chunk_size: 每个分块的最大字符数,默认为 512(中医文本信息量大,需较小分块)+ chunk_overlap: 分块之间的重叠字符数,默认为 64max_workers: 最大工作线程数,默认为 10verbose: 是否输出详细日志,默认为 False**kwargs: 其他技术参数,传递给基类@@ -79,6 +83,8 @@ class PulseTongueRecord(AutoList[PulseTongueItem]):item_schema=PulseTongueItem,llm_client=llm_client,embedder=embedder,+ chunk_size=chunk_size,+ chunk_overlap=chunk_overlap,max_workers=max_workers,verbose=verbose,prompt=_PROMPT,diff --git a/hyperextract/templates/zh/tcm/syndrome_reasoning_graph.py b/hyperextract/templates/zh/tcm/syndrome_reasoning_graph.pyindex bde886a..90780d3 100644--- a/hyperextract/templates/zh/tcm/syndrome_reasoning_graph.py+++ b/hyperextract/templates/zh/tcm/syndrome_reasoning_graph.py@@ -114,6 +114,8 @@ class SyndromeReasoningGraph(AutoHypergraph[TCMEntity, SyndromeReasoningEdge]):embedder: Embeddings,*,extraction_mode: str = "two_stage",+ chunk_size: int = 512,+ chunk_overlap: int = 64,max_workers: int = 10,verbose: bool = False,**kwargs: Any,@@ -126,6 +128,8 @@ class SyndromeReasoningGraph(AutoHypergraph[TCMEntity, SyndromeReasoningEdge]):embedder: 嵌入模型,用于语义检索extraction_mode: 提取模式,可选 "one_stage"(同时提取节点和边)或 "two_stage"(先提取节点,再提取边),默认为 "two_stage"+ chunk_size: 每个分块的最大字符数,默认为 512(中医文本信息量大,需较小分块)+ chunk_overlap: 分块之间的重叠字符数,默认为 64max_workers: 最大工作线程数,默认为 10verbose: 是否输出详细日志,默认为 False**kwargs: 其他技术参数,传递给基类@@ -139,6 +143,8 @@ class SyndromeReasoningGraph(AutoHypergraph[TCMEntity, SyndromeReasoningEdge]):llm_client=llm_client,embedder=embedder,extraction_mode=extraction_mode,+ chunk_size=chunk_size,+ chunk_overlap=chunk_overlap,max_workers=max_workers,verbose=verbose,prompt=_PROMPT,