Hypergraph is more powerful. Transform unstructured text into structured knowledge with LLMs. Graphs, hypergraphs, and spatio-temporal extractions — with one command.
refactor: 更新示例文件和显示解析器配置
yifanfeng976f7e0f90bac0
diff --git a/examples/template_demo.py b/examples/template_demo.pyindex 0a7a6db..4cf7d46 100644--- a/examples/template_demo.py+++ b/examples/template_demo.py@@ -21,16 +21,22 @@ from hyperextract import Templatefrom langchain_openai import ChatOpenAI, OpenAIEmbeddings+# INPUT_FILE = (+# Path(__file__).parent.parent+# / "tests"+# / "test_data"+# / "templates"+# / "biography_scientist.md"+# )+INPUT_FILE = (Path(__file__).parent.parent/ "tests"- / "test_data"- / "templates"- / "biography_scientist.md"+ / "kg.md")-name = "general/life_event_timeline"-# name = "general/knowledge_graph"+# name = "general/life_event_timeline"+name = "general/knowledge_graph"def main():diff --git a/hyperextract/utils/template_engine/parsers/display.py b/hyperextract/utils/template_engine/parsers/display.pyindex b0984eb..aa76feb 100644--- a/hyperextract/utils/template_engine/parsers/display.py+++ b/hyperextract/utils/template_engine/parsers/display.py@@ -11,9 +11,9 @@ from .identifiers import _extractordef parse_display(- display: NaiveDisplaySchema | GraphDisplaySchema | None,+ display: NaiveDisplaySchema | GraphDisplaySchema,autotype: VALID_AUTOTYPES,-) -> Callable[[Any], str] | tuple[Callable[[Any], str], Callable[[Any], str]] | None:+) -> Callable[[Any], str] | tuple[Callable[[Any], str], Callable[[Any], str]]:"""Parse display config and return label extractors.Args:@@ -24,9 +24,6 @@ def parse_display(- For model/list/set: label_extractor- For graph types: (entity_label_extractor, relation_label_extractor)"""- if not display:- return None-if autotype in ("model", "list", "set"):return _extractor(display.label)