Hypergraph is more powerful. Transform unstructured text into structured knowledge with LLMs. Graphs, hypergraphs, and spatio-temporal extractions — with one command.
feat: Enhance graph templates with additional parameters and improved documentation for better extraction capabilities
yifanfeng97003d549b92fc
diff --git a/examples/auto_graph_demo.py b/examples/auto_graph_demo.pyindex 419691c..c8d0127 100644--- a/examples/auto_graph_demo.py+++ b/examples/auto_graph_demo.py@@ -411,7 +411,7 @@ def run_demo():chat_queries = ["请总结这个公会冲突的核心原因。","暗影刺客和小甜甜的行为对团队造成了什么影响?",- "从这个事件中,我们学到了什么关于公会管理的经验?"+ "从这个事件中,我们学到了什么关于公会管理的经验?",]for q in chat_queries:@@ -434,6 +434,11 @@ def run_demo():except Exception as e:print(f"⚠️ 保存失败: {e}")+ graph.show(+ node_label_extractor=lambda n: f"{n.name} ({n.category})",+ edge_label_extractor=lambda e: e.action_type,+ )+if __name__ == "__main__":run_demo()diff --git a/hyperextract/graphs/base.py b/hyperextract/graphs/base.pyindex 6c41e06..a5fe623 100644--- a/hyperextract/graphs/base.py+++ b/hyperextract/graphs/base.py@@ -22,6 +22,7 @@ from langchain_core.language_models.chat_models import BaseChatModelfrom langchain_core.prompts import ChatPromptTemplatefrom ontomem import OMemfrom ontomem.merger import MergeStrategy, create_merger, BaseMerger+from ontosight import view_graphfrom hyperextract.core import BaseAutoTypefrom hyperextract.utils.logging import logger@@ -69,7 +70,9 @@ DEFAULT_EDGE_PROMPT = (class AutoGraphSchema(BaseModel, Generic[NodeSchema, EdgeSchema]):"""Generic schema container for graph-based knowledge patterns."""- nodes: List[NodeSchema] = Field(default_factory=list, description="Graph nodes/entities")+ nodes: List[NodeSchema] = Field(+ default_factory=list, description="Graph nodes/entities"+ )edges: List[EdgeSchema] = Field(default_factory=list, description="Graph edges/relationships")@@ -93,7 +96,10 @@ class EdgeListSchema(BaseModel, Generic[EdgeSchema]):)-class AutoGraph(BaseAutoType[AutoGraphSchema[NodeSchema, EdgeSchema]], Generic[NodeSchema, EdgeSchema]):+class AutoGraph(+ BaseAutoType[AutoGraphSchema[NodeSchema, EdgeSchema]],+ Generic[NodeSchema, EdgeSchema],+):"""AutoGraph - extracts knowledge graphs with nodes and edges from text.This pattern extracts structured knowledge graphs consisting of entities (nodes) and@@ -388,7 +394,9 @@ class AutoGraph(BaseAutoType[AutoGraphSchema[NodeSchema, EdgeSchema]], Generic[Nself.clear_index()- def _update_data_state(self, incoming_data: AutoGraphSchema[NodeSchema, EdgeSchema]) -> None:+ def _update_data_state(+ self, incoming_data: AutoGraphSchema[NodeSchema, EdgeSchema]+ ) -> None:"""Merge incoming graph data into current state.Args:@@ -424,7 +432,9 @@ class AutoGraph(BaseAutoType[AutoGraphSchema[NodeSchema, EdgeSchema]], Generic[N# Prune dangling edges to ensure graph consistencyreturn self._prune_dangling_edges(raw_graph)- def _extract_data_by_one_stage(self, text: str) -> AutoGraphSchema[NodeSchema, EdgeSchema]:+ def _extract_data_by_one_stage(+ self, text: str+ ) -> AutoGraphSchema[NodeSchema, EdgeSchema]:"""Extract nodes and edges simultaneously using single LLM call.Args:@@ -454,7 +464,9 @@ class AutoGraph(BaseAutoType[AutoGraphSchema[NodeSchema, EdgeSchema]], Generic[N# Merge multiple graphsreturn self.merge_batch_data(graph_list)- def _extract_data_by_two_stage(self, text: str) -> AutoGraphSchema[NodeSchema, EdgeSchema]:+ def _extract_data_by_two_stage(+ self, text: str+ ) -> AutoGraphSchema[NodeSchema, EdgeSchema]:"""Extract nodes first, then edges with node context (batch processing).Process:@@ -491,7 +503,9 @@ class AutoGraph(BaseAutoType[AutoGraphSchema[NodeSchema, EdgeSchema]], Generic[N# 5. Global Merge (passes tuples to merge_batch_data)return self.merge_batch_data(partial_graphs)- def _extract_nodes_batch(self, chunks: List[str]) -> List[NodeListSchema[NodeSchema]]:+ def _extract_nodes_batch(+ self, chunks: List[str]+ ) -> List[NodeListSchema[NodeSchema]]:"""Batch extract nodes from multiple text chunks.Args:@@ -542,7 +556,9 @@ class AutoGraph(BaseAutoType[AutoGraphSchema[NodeSchema, EdgeSchema]], Generic[Nreturn llm_chain.batch(inputs, config={"max_concurrency": self.max_workers})- def _prune_dangling_edges(self, graph: AutoGraphSchema[NodeSchema, EdgeSchema]) -> AutoGraphSchema[NodeSchema, EdgeSchema]:+ def _prune_dangling_edges(+ self, graph: AutoGraphSchema[NodeSchema, EdgeSchema]+ ) -> AutoGraphSchema[NodeSchema, EdgeSchema]:"""Prune edges that connect to non-existent nodes (Consistency Check).Ensures graph consistency by removing any edges where either endpoint@@ -851,3 +867,49 @@ class AutoGraph(BaseAutoType[AutoGraphSchema[NodeSchema, EdgeSchema]], Generic[Nself._edge_memory.load_index(str(edge_index_path))except Exception as e:logger.warning(f"Failed to load edge index: {e}")++ def show(+ self,+ node_label_extractor: Callable[[NodeSchema], str],+ edge_label_extractor: Callable[[EdgeSchema], str],+ ) -> None:+ """Visualize the graph using OntoSight.++ Args:+ node_label_extractor: A function that takes a NodeSchema and returns a string label for visualization.+ edge_label_extractor: A function that takes an EdgeSchema and returns a string label for visualization.+ """++ if self._node_memory.has_index() and self._edge_memory.has_index():+ logger.info(+ "Visualizing graph with search and chat capabilities (indices detected)."+ )++ def search_callback(query: str) -> None:+ return self.search(query, top_k_nodes=3, top_k_edges=3)++ def chat_callback(question: str) -> None:+ response = self.chat(question, top_k_nodes=3, top_k_edges=3)+ content = response.content+ retrieved_nodes = response.additional_kwargs.get("retrieved_nodes", [])+ retrieved_edges = response.additional_kwargs.get("retrieved_edges", [])+ return content, (retrieved_nodes, retrieved_edges)+ else:+ logger.info(+ "Visualizing graph without search and chat capabilities (no indices detected)."+ )+ search_callback = None+ chat_callback = None++ view_graph(+ node_list=self.nodes,+ edge_list=self.edges,+ node_schema=self.node_schema,+ edge_schema=self.edge_schema,+ node_id_extractor=self.node_key_extractor,+ node_ids_in_edge_extractor=self.nodes_in_edge_extractor,+ node_label_extractor=node_label_extractor,+ edge_label_extractor=edge_label_extractor,+ on_search=search_callback,+ on_chat=chat_callback,+ )diff --git a/hyperextract/templates/en/general/concept_map.py b/hyperextract/templates/en/general/concept_map.pyindex 690d32e..d19fee9 100644--- a/hyperextract/templates/en/general/concept_map.py+++ b/hyperextract/templates/en/general/concept_map.py@@ -1,5 +1,7 @@-from typing import List, Optional+from typing import List, Optional, Anyfrom pydantic import BaseModel, Field+from langchain_core.language_models.chat_models import BaseChatModel+from langchain_core.embeddings import Embeddingsfrom hyperextract.graphs import AutoGraph# ==============================================================================@@ -52,16 +54,62 @@ CONCEPT_MAP_EDGE_PROMPT = (class ConceptMap(AutoGraph[Concept, ConceptRelation]):"""- A template for building conceptual graphs and taxonomies.- Ideal for technical documentation, educational materials, and glossaries.+ A template for building concept maps and taxonomies.++ Ideal for structured learning, technical documentation, and glossary extraction.+ It focuses on definitions, semantic categories, and hierarchical relationships.++ Example:+ >>> from langchain_openai import ChatOpenAI, OpenAIEmbeddings+ >>> llm = ChatOpenAI(model="gpt-4o")+ >>> embedder = OpenAIEmbeddings()+ >>> # Initialize the template+ >>> cm = ConceptMap(llm_client=llm, embedder=embedder)+ >>> # Extract taxonomy from text+ >>> text = "Machine Learning is a subset of Artificial Intelligence that uses data to learn."+ >>> cm.feed_text(text)+ >>> print(cm.edges) # Output shows: Machine Learning --(is a)--> Artificial Intelligence"""- def __init__(self, **kwargs):+ def __init__(+ self,+ llm_client: BaseChatModel,+ embedder: Embeddings,+ *,+ extraction_mode: str = "one_stage",+ chunk_size: int = 2048,+ chunk_overlap: int = 256,+ max_workers: int = 10,+ verbose: bool = False,+ **kwargs: Any+ ):+ """+ Initialize the ConceptMap template.++ Args:+ llm_client: The language model client used for extraction.+ embedder: The embedding model used for concept deduplication and indexing.+ extraction_mode: The strategy for extraction:+ - "one_stage": Extract nodes and edges simultaneously (faster).+ - "two_stage": Extract nodes first, then edges (higher accuracy).+ chunk_size: Maximum number of characters per text chunk.+ chunk_overlap: Number of characters to overlap between chunks.+ max_workers: Maximum number of parallel workers for processing.+ verbose: If True, prints detailed progress logs.+ **kwargs: Additional arguments passed to the AutoGraph constructor.+ """super().__init__(node_schema=Concept,edge_schema=ConceptRelation,node_key_extractor=lambda x: x.term.strip(),edge_key_extractor=lambda x: f"{x.source.strip()}--({x.relation_type.lower()})-->{x.target.strip()}",nodes_in_edge_extractor=lambda x: (x.source.strip(), x.target.strip()),+ 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=CONCEPT_MAP_PROMPT,prompt_for_node_extraction=CONCEPT_MAP_NODE_PROMPT,prompt_for_edge_extraction=CONCEPT_MAP_EDGE_PROMPT,diff --git a/hyperextract/templates/en/general/knowledge_graph.py b/hyperextract/templates/en/general/knowledge_graph.pyindex 3d3a3bd..6b6880c 100644--- a/hyperextract/templates/en/general/knowledge_graph.py+++ b/hyperextract/templates/en/general/knowledge_graph.py@@ -1,5 +1,7 @@-from typing import List, Optional+from typing import List, Optional, Anyfrom pydantic import BaseModel, Field+from langchain_core.language_models.chat_models import BaseChatModel+from langchain_core.embeddings import Embeddingsfrom hyperextract.graphs import AutoGraph# ==============================================================================@@ -55,15 +57,61 @@ KNOWLEDGE_GRAPH_EDGE_PROMPT = (class KnowledgeGraph(AutoGraph[Entity, Relation]):"""A foundational knowledge graph template for factual extraction.- Best for news, biographies, and descriptive encyclopedic content.++ This template is optimized for extracting entities (People, Places, Organizations)+ and their factual interactions from news articles, biographies, and encyclopedic texts.++ Example:+ >>> from langchain_openai import ChatOpenAI, OpenAIEmbeddings+ >>> llm = ChatOpenAI(model="gpt-4o")+ >>> embedder = OpenAIEmbeddings()+ >>> # Initialize the template+ >>> kg = KnowledgeGraph(llm_client=llm, embedder=embedder)+ >>> # Extract knowledge from text+ >>> text = "Steve Jobs co-founded Apple in Cupertino."+ >>> kg.feed_text(text)+ >>> print(kg.nodes) # Output: [Entity(name='Steve Jobs', ...), Entity(name='Apple', ...)]"""- def __init__(self, **kwargs):+ def __init__(+ self,+ llm_client: BaseChatModel,+ embedder: Embeddings,+ *,+ extraction_mode: str = "one_stage",+ chunk_size: int = 2048,+ chunk_overlap: int = 256,+ max_workers: int = 10,+ verbose: bool = False,+ **kwargs: Any+ ):+ """+ Initialize the KnowledgeGraph template.++ Args:+ llm_client: The language model client used for extraction.+ embedder: The embedding model used for entity deduplication and indexing.+ extraction_mode: The strategy for extraction:+ - "one_stage": Extract nodes and edges simultaneously (faster).+ - "two_stage": Extract nodes first, then edges (higher accuracy).+ chunk_size: Maximum number of characters per text chunk.+ chunk_overlap: Number of characters to overlap between chunks.+ max_workers: Maximum number of parallel workers for processing.+ verbose: If True, prints detailed progress logs.+ **kwargs: Additional arguments passed to the AutoGraph constructor.+ """super().__init__(node_schema=Entity,edge_schema=Relation,node_key_extractor=lambda x: x.name.strip(),edge_key_extractor=lambda x: f"{x.source.strip()}--[{x.relation.lower()}]-->{x.target.strip()}",nodes_in_edge_extractor=lambda x: (x.source.strip(), x.target.strip()),+ 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=KNOWLEDGE_GRAPH_PROMPT,prompt_for_node_extraction=KNOWLEDGE_GRAPH_NODE_PROMPT,prompt_for_edge_extraction=KNOWLEDGE_GRAPH_EDGE_PROMPT,diff --git a/hyperextract/templates/en/general/logic_graph.py b/hyperextract/templates/en/general/logic_graph.pyindex 56362ab..def0289 100644--- a/hyperextract/templates/en/general/logic_graph.py+++ b/hyperextract/templates/en/general/logic_graph.py@@ -1,5 +1,7 @@-from typing import List, Optional+from typing import List, Optional, Anyfrom pydantic import BaseModel, Field+from langchain_core.language_models.chat_models import BaseChatModel+from langchain_core.embeddings import Embeddingsfrom hyperextract.graphs import AutoGraph# ==============================================================================@@ -51,15 +53,62 @@ LOGIC_GRAPH_EDGE_PROMPT = (class LogicGraph(AutoGraph[LogicNode, LogicRelation]):"""A template for analyzing reasoning, arguments, and causal chains.- Ideal for analytical reports, debate transcripts, and scientific reasoning.++ This template is designed to map out the logical structure of analytical reports,+ scientific papers, or debate transcripts. It captures claims, evidence, and+ the logical links (Support/Contradict) between them.++ Example:+ >>> from langchain_openai import ChatOpenAI, OpenAIEmbeddings+ >>> llm = ChatOpenAI(model="gpt-4o")+ >>> embedder = OpenAIEmbeddings()+ >>> # Initialize the template+ >>> lg = LogicGraph(llm_client=llm, embedder=embedder)+ >>> # Extract logic from text+ >>> text = "The climate is warming because carbon levels are rising."+ >>> lg.feed_text(text)+ >>> print(lg.edges) # Output shows: Carbon levels rising --(Supports)--> Climate is warming"""- def __init__(self, **kwargs):+ def __init__(+ self,+ llm_client: BaseChatModel,+ embedder: Embeddings,+ *,+ extraction_mode: str = "one_stage",+ chunk_size: int = 2048,+ chunk_overlap: int = 256,+ max_workers: int = 10,+ verbose: bool = False,+ **kwargs: Any+ ):+ """+ Initialize the LogicGraph template.++ Args:+ llm_client: The language model client used for extraction.+ embedder: The embedding model used for logic point deduplication and indexing.+ extraction_mode: The strategy for extraction:+ - "one_stage": Extract nodes and edges simultaneously (faster).+ - "two_stage": Extract nodes first, then edges (higher accuracy).+ chunk_size: Maximum number of characters per text chunk.+ chunk_overlap: Number of characters to overlap between chunks.+ max_workers: Maximum number of parallel workers for processing.+ verbose: If True, prints detailed progress logs.+ **kwargs: Additional arguments passed to the AutoGraph constructor.+ """super().__init__(node_schema=LogicNode,edge_schema=LogicRelation,node_key_extractor=lambda x: x.statement.strip(),edge_key_extractor=lambda x: f"{x.source.strip()}--({x.inference.lower()})-->{x.target.strip()}",nodes_in_edge_extractor=lambda x: (x.source.strip(), x.target.strip()),+ 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=LOGIC_GRAPH_PROMPT,prompt_for_node_extraction=LOGIC_GRAPH_NODE_PROMPT,prompt_for_edge_extraction=LOGIC_GRAPH_EDGE_PROMPT,diff --git a/hyperextract/templates/zh/general/concept_map.py b/hyperextract/templates/zh/general/concept_map.pyindex af793dd..80209c7 100644--- a/hyperextract/templates/zh/general/concept_map.py+++ b/hyperextract/templates/zh/general/concept_map.py@@ -1,5 +1,7 @@-from typing import List, Optional+from typing import List, Optional, Anyfrom pydantic import BaseModel, Field+from langchain_core.language_models.chat_models import BaseChatModel+from langchain_core.embeddings import Embeddingsfrom hyperextract.graphs import AutoGraph# ==============================================================================@@ -49,16 +51,61 @@ CONCEPT_MAP_EDGE_PROMPT = (class ConceptMap(AutoGraph[Concept, ConceptRelation]):"""- 用于构建概念图谱和分类体系的模板。- 适用于技术文档、教育材料、术语表解析等场景。+ 用于构建概念图和分类体系的模板。++ 适用于结构化学习、技术文档和术语表提取。侧重于定义、语义类别和层级关系。++ 示例:+ >>> from langchain_openai import ChatOpenAI, OpenAIEmbeddings+ >>> llm = ChatOpenAI(model="gpt-4o")+ >>> embedder = OpenAIEmbeddings()+ >>> # 初始化模板+ >>> cm = ConceptMap(llm_client=llm, embedder=embedder)+ >>> # 从文本中提取分类体系+ >>> text = "机器学习是人工智能的一个子集,它利用数据进行学习。"+ >>> cm.feed_text(text)+ >>> print(cm.edges) # 输出显示:机器学习 --(是一种)--> 人工智能"""- def __init__(self, **kwargs):+ def __init__(+ self,+ llm_client: BaseChatModel,+ embedder: Embeddings,+ *,+ extraction_mode: str = "one_stage",+ chunk_size: int = 2048,+ chunk_overlap: int = 256,+ max_workers: int = 10,+ verbose: bool = False,+ **kwargs: Any+ ):+ """+ 初始化 ConceptMap 模板。++ Args:+ llm_client: 用于提取的语言模型客户端。+ embedder: 用于概念去重和索引的嵌入模型。+ extraction_mode: 提取策略:+ - "one_stage": 同时提取节点和边(速度更快)。+ - "two_stage": 先提取节点,再提取边(准确度更高)。+ chunk_size: 每个文本块的最大字符数。+ chunk_overlap: 文本块之间的重叠字符数。+ max_workers: 并行处理的最大线程数。+ verbose: 如果为 True,则打印详细的进度日志。+ **kwargs: 传给 AutoGraph 构造函数的其他参数。+ """super().__init__(node_schema=Concept,edge_schema=ConceptRelation,node_key_extractor=lambda x: x.term.strip(),edge_key_extractor=lambda x: f"{x.source.strip()}--({x.relation_type.lower()})-->{x.target.strip()}",nodes_in_edge_extractor=lambda x: (x.source.strip(), x.target.strip()),+ 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=CONCEPT_MAP_PROMPT,prompt_for_node_extraction=CONCEPT_MAP_NODE_PROMPT,prompt_for_edge_extraction=CONCEPT_MAP_EDGE_PROMPT,diff --git a/hyperextract/templates/zh/general/knowledge_graph.py b/hyperextract/templates/zh/general/knowledge_graph.pyindex f853d4c..32742b5 100644--- a/hyperextract/templates/zh/general/knowledge_graph.py+++ b/hyperextract/templates/zh/general/knowledge_graph.py@@ -1,5 +1,7 @@-from typing import List, Optional+from typing import List, Optional, Anyfrom pydantic import BaseModel, Field+from langchain_core.language_models.chat_models import BaseChatModel+from langchain_core.embeddings import Embeddingsfrom hyperextract.graphs import AutoGraph# ==============================================================================@@ -52,15 +54,61 @@ KNOWLEDGE_GRAPH_EDGE_PROMPT = (class KnowledgeGraph(AutoGraph[Entity, Relation]):"""- 通用事实知识图谱模板,适用于新闻报道、百科条目及传记。+ 用于事实提取的基础知识图谱模板。++ 该模板经过优化,适用于从新闻文章、传记和百科文本中提取实体(人物、地点、组织)及其事实交互。++ 示例:+ >>> from langchain_openai import ChatOpenAI, OpenAIEmbeddings+ >>> llm = ChatOpenAI(model="gpt-4o")+ >>> embedder = OpenAIEmbeddings()+ >>> # 初始化模板+ >>> kg = KnowledgeGraph(llm_client=llm, embedder=embedder)+ >>> # 从文本中提取知识+ >>> text = "苏轼出生于眉州眉山,是北宋著名的文学家。"+ >>> kg.feed_text(text)+ >>> print(kg.nodes) # 输出: [Entity(name='苏轼', ...), Entity(name='眉州眉山', ...)]"""- def __init__(self, **kwargs):+ def __init__(+ self,+ llm_client: BaseChatModel,+ embedder: Embeddings,+ *,+ extraction_mode: str = "one_stage",+ chunk_size: int = 2048,+ chunk_overlap: int = 256,+ max_workers: int = 10,+ verbose: bool = False,+ **kwargs: Any+ ):+ """+ 初始化 KnowledgeGraph 模板。++ Args:+ llm_client: 用于提取的语言模型客户端。+ embedder: 用于实体去重和索引的嵌入模型。+ extraction_mode: 提取策略:+ - "one_stage": 同时提取节点和边(速度更快)。+ - "two_stage": 先提取节点,再提取边(准确度更高)。+ chunk_size: 每个文本块的最大字符数。+ chunk_overlap: 文本块之间的重叠字符数。+ max_workers: 并行处理的最大线程数。+ verbose: 如果为 True,则打印详细的进度日志。+ **kwargs: 传给 AutoGraph 构造函数的其他参数。+ """super().__init__(node_schema=Entity,edge_schema=Relation,node_key_extractor=lambda x: x.name.strip(),edge_key_extractor=lambda x: f"{x.source.strip()}--[{x.relation.lower()}]-->{x.target.strip()}",nodes_in_edge_extractor=lambda x: (x.source.strip(), x.target.strip()),+ 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=KNOWLEDGE_GRAPH_PROMPT,prompt_for_node_extraction=KNOWLEDGE_GRAPH_NODE_PROMPT,prompt_for_edge_extraction=KNOWLEDGE_GRAPH_EDGE_PROMPT,diff --git a/hyperextract/templates/zh/general/logic_graph.py b/hyperextract/templates/zh/general/logic_graph.pyindex 85718a7..c992d4c 100644--- a/hyperextract/templates/zh/general/logic_graph.py+++ b/hyperextract/templates/zh/general/logic_graph.py@@ -1,5 +1,7 @@-from typing import List, Optional+from typing import List, Optional, Anyfrom pydantic import BaseModel, Field+from langchain_core.language_models.chat_models import BaseChatModel+from langchain_core.embeddings import Embeddingsfrom hyperextract.graphs import AutoGraph# ==============================================================================@@ -48,16 +50,61 @@ LOGIC_GRAPH_EDGE_PROMPT = (class LogicGraph(AutoGraph[LogicNode, LogicRelation]):"""- 用于分析论文推理、论证和因果链的模板。- 适用于分析报告、辩论内容、科研推理及逻辑分析。+ 用于分析推理、论证和因果链的模板。++ 该模板旨在映射分析报告、科学论文或辩论记录的逻辑结构。它捕捉主张、证据以及它们之间的逻辑链接(支持/反驳)。++ 示例:+ >>> from langchain_openai import ChatOpenAI, OpenAIEmbeddings+ >>> llm = ChatOpenAI(model="gpt-4o")+ >>> embedder = OpenAIEmbeddings()+ >>> # 初始化模板+ >>> lg = LogicGraph(llm_client=llm, embedder=embedder)+ >>> # 从文本中提取逻辑+ >>> text = "由于碳含量上升,气候正在变暖。"+ >>> lg.feed_text(text)+ >>> print(lg.edges) # 输出显示:碳含量上升 --(支持)--> 气候正在变暖"""- def __init__(self, **kwargs):+ def __init__(+ self,+ llm_client: BaseChatModel,+ embedder: Embeddings,+ *,+ extraction_mode: str = "one_stage",+ chunk_size: int = 2048,+ chunk_overlap: int = 256,+ max_workers: int = 10,+ verbose: bool = False,+ **kwargs: Any+ ):+ """+ 初始化 LogicGraph 模板。++ Args:+ llm_client: 用于提取的语言模型客户端。+ embedder: 用于逻辑点去重和索引的嵌入模型。+ extraction_mode: 提取策略:+ - "one_stage": 同时提取节点和边(速度更快)。+ - "two_stage": 先提取节点,再提取边(准确度更高)。+ chunk_size: 每个文本块的最大字符数。+ chunk_overlap: 文本块之间的重叠字符数。+ max_workers: 并行处理的最大线程数。+ verbose: 如果为 True,则打印详细的进度日志。+ **kwargs: 传给 AutoGraph 构造函数的其他参数。+ """super().__init__(node_schema=LogicNode,edge_schema=LogicRelation,node_key_extractor=lambda x: x.statement.strip(),edge_key_extractor=lambda x: f"{x.source.strip()}--({x.inference.lower()})-->{x.target.strip()}",nodes_in_edge_extractor=lambda x: (x.source.strip(), x.target.strip()),+ 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=LOGIC_GRAPH_PROMPT,prompt_for_node_extraction=LOGIC_GRAPH_NODE_PROMPT,prompt_for_edge_extraction=LOGIC_GRAPH_EDGE_PROMPT,