SI_KG_2026_PlanningLaw/dofile/graphrag_pipeline/USAGE_EXAMPLES.md

使用示例

示例1: 从单个文档提取实体

from src.preprocessing.document_parser import DocumentParser
from src.extraction.ner import NERExtractor
from src.utils.config import load_config

# 加载配置
config = load_config()

# 解析文档
parser = DocumentParser()
doc = parser.parse_docx("../data/1法律/3-中华人民共和国城乡规划法.docx")

# 提取实体
ner_extractor = NERExtractor(config=config)
entities = ner_extractor.extract(doc["text"])

print(f"识别到 {sum(len(v) for v in entities.values())} 个实体")

示例2: 构建知识图谱

from src.preprocessing.document_parser import DocumentParser
from src.kg_builder.indexer import GraphIndexer
from src.utils.config import load_config

# 加载配置
config = load_config()

# 解析文档
parser = DocumentParser()
docs = parser.parse_directory("../data/1法律")

# 切分为TextUnit
all_textunits = []
for doc in docs[:3]:  # 只处理前3个文档
    textunits = parser.split_into_textunits(doc, max_length=500)
    all_textunits.extend(textunits)

# 构建知识图谱
indexer = GraphIndexer(config=config)
kg = indexer.index(all_textunits)

print(f"图谱包含 {kg.number_of_nodes()} 个节点，{kg.number_of_edges()} 条边")

示例3: 查询知识图谱

from src.kg_builder.graph import KnowledgeGraph
from src.query.global_search import GlobalSearcher
from src.query.local_search import LocalSearcher

# 加载图谱
kg = KnowledgeGraph()
kg.load("output/kg.json")

# 全局搜索
global_searcher = GlobalSearcher(kg.graph, communities={})
result = global_searcher.search("城市更新的法规要求")
print(result["answer"])

# 局部搜索
local_searcher = LocalSearcher(kg.graph)
result = local_searcher.search("城乡规划", depth=2)
print(f"找到 {result['subgraph']['num_nodes']} 个相关节点")

示例4: 法理结构提取

from src.analysis.legal_structure import LegalStructureExtractor

extractor = LegalStructureExtractor()

# 提取四要素
text = "为了促进城市可持续发展，应当坚持生态优先、绿色发展原则..."
elements = extractor.extract_four_elements(text)
print(elements)

# 提取跨法规引用
references = extractor.extract_cross_references(text)
print(references)

示例5: 三元组评估

from src.extraction.evaluator import TripletEvaluator

evaluator = TripletEvaluator()

# 评估多个模型的结果
peer_groups = {
    "model_1": [{"head": "A", "relation": "管控", "tail": "B"}],
    "model_2": [{"head": "A", "relation": "涉及", "tail": "B"}],
}

result = evaluator.evaluate_peer_groups(
    peer_groups,
    source_text="原始文本..."
)

print(f"最佳模型: {result['best_group']}")
print(f"评分: {result['scores']}")