Skip to content

Hypergraph is more powerful. Transform unstructured text into structured knowledge with LLMs. Graphs, hypergraphs, and spatio-temporal extractions — with one command.

1.8 KB
Raw Blame
"""
通用领域模板示例

Usage:
    python examples/templates/general_template.py
"""

from pathlib import Path

import dotenv
from langchain_openai import ChatOpenAI, OpenAIEmbeddings

from hyperextract import Template

project_root = Path(__file__).resolve().parent.parent.parent.parent

dotenv.load_dotenv()

# ==================== 测试用例(取消注释选择要测试的用例) ====================

# // test for 基础知识图谱
test_data_file = "arbitrary_tech_news.md"
template_name = "general/graph"

# // test for 基础超图
# test_data_file = "encyclopedia_machine_learning.md"
# template_name = "general/base_hypergraph"

# // test for 基础列表
# test_data_file = "regulation_company_policy.md"
# template_name = "general/list"

# // test for 传记图谱
# test_data_file = "biography_scientist.md"
# template_name = "general/biography_graph"

# // test for 概念图谱
# test_data_file = "encyclopedia_machine_learning.md"
# template_name = "general/concept_graph"

# ==================== 主函数 ====================

def main():
    test_data_dir = project_root / "tests" / "test_data" / "zh" / "general"
    input_file = test_data_dir / test_data_file
    
    with open(input_file, "r", encoding="utf-8") as f:
        text = f.read()
    
    print("=" * 80)
    print(f"🧪 测试模板: {template_name}")
    print(f"📂 测试数据: {input_file}")
    print("=" * 80)

    llm = ChatOpenAI(model="gpt-4o-mini", temperature=0)
    embedder = OpenAIEmbeddings(model="text-embedding-3-small")

    extractor = Template.create(
        template_name,
        language="zh",
        llm_client=llm,
        embedder=embedder,
    )

    print("\n📥 正在提取知识摘要...")
    extractor.feed_text(text)
    print("✅ 提取完成!\n")

    extractor.show()


if __name__ == "__main__":
    main()