import jsonimport loggingimport timefrom pathlib import Path
import spacyimport networkx as nximport matplotlib.pyplot as plt
from docling.datamodel.base_models import InputFormatfrom docling.datamodel.pipeline_options import (AcceleratorDevice,AcceleratorOptions,PdfPipelineOptions,)from docling.document_converter import DocumentConverter, PdfFormatOption
# Load a spaCy language modelnlp = spacy.load("en_core_web_sm")
def extract_text_from_docling_document(docling_document):"""Extracts text content from a Docling Document object."""text = docling_document.export_to_text()return text
def build_knowledge_graph(text):doc = nlp(text)graph = nx.Graph()
# Extract entitiesfor ent in doc.ents:graph.add_node(ent.text, label=ent.label_)
# Simple relationship extraction (can be improved)for sent in doc.sents:for i, token in enumerate(sent):if token.dep_ in ["nsubj", "dobj"]:subject = [w for w in token.head.lefts if w.dep_ == "nsubj"]object_ = [w for w in token.head.rights if w.dep_ == "dobj"]if subject and object_:graph.add_edge(subject[0].text, object_[0].text, relation=token.head.lemma_)elif subject and token.head.lemma_ in ["be", "have"]:right_children = [child for child in token.head.rights if child.dep_ in ["attr", "acomp"]]if right_children:graph.add_edge(subject[0].text, right_children[0].text, relation=token.head.lemma_)return graph
def visualize_knowledge_graph(graph):"""Visualizes the knowledge graph."""pos = nx.spring_layout(graph)nx.draw(graph, pos, with_labels=True, node_size=3000, node_color="skyblue", font_size=10, font_weight="bold")edge_labels = nx.get_edge_attributes(graph, 'relation')nx.draw_networkx_edge_labels(graph, pos, edge_labels=edge_labels)plt.title("Knowledge Graph from Document")plt.show()
def main():logging.basicConfig(level=logging.INFO)_log = logging.getLogger(__name__) # Initialize the logger here#nlp = spacy.load("en_core_web_sm") # Load spacy # Removed from here#input_doc_path = Path("./input/2503.11576v1.pdf")input_doc_path = Path("./inp

巴黎市位于法国，以其标志性的埃菲尔铁塔而闻名。它是一处热门旅游目的地。这座铁塔由古斯塔夫・埃菲尔设计。著名科学家玛丽・居里出生于巴黎，她为放射学领域做出了重大贡献。她曾在镭研究所工作。塞纳河流经巴黎。
说明其适用性的原因：该文本包含多个实体和关系，这些实体和关系可被轻松提取并在知识图谱中呈现：・实体：巴黎、法国、埃菲尔铁塔、古斯塔夫・埃菲尔、玛丽・居里、镭研究所、塞纳河・关系：巴黎位于法国。巴黎因埃菲尔铁塔而闻名。埃菲尔铁塔由古斯塔夫・埃菲尔设计。玛丽・居里出生于巴黎。玛丽・居里是一位科学家。玛丽・居里为放射学领域做出了贡献。玛丽・居里曾在镭研究所工作。塞纳河流经巴黎。
根据该文本构建的知识图谱会将这些实体表示为节点，将关系表示为边，从而提供信息的结构化呈现。

INFO:__main__:Document converted in 8.63 seconds.WARNING:docling_core.types.doc.document:Parameter `strict_text` has been deprecated and will be ignored.Number of nodes: 23Number of edges: 72025-04-23 21:33:52.828 python3[73966:691115] The class 'NSSavePanel' overrides the method identifier. This method is implemented by class 'NSWindow'
Nodes: [('Paris', {'label': 'GPE'}), ('France', {'label': 'GPE'}), ('Eiffel Tower', {'label': 'FAC'}), ('Gustave Eiffel', {'label': 'PERSON'}), ('Marie Curie', {'label': 'PERSON'}), ('the Radium Institute', {'label': 'FAC'}), ('Seine River', {'label': 'LOC'}), ('## Explanation', {'label': 'MONEY'}), ('Radium Institute', {'label': 'ORG'}), ('the Eiffel Tower', {'label': 'LOC'}), ('The Eiffel Tower', {'label': 'LOC'}), ('city', {}), ('renowned', {}), ('It', {}), ('destination', {}), ('Explanation', {}), ('entities', {}), ('this', {}), ('suitable', {}), ('Curie', {}), ('scientist', {}), ('contributions', {}), ('graph', {})]
Edges: [('city', 'renowned', {'relation': 'be'}), ('It', 'destination', {'relation': 'be'}), ('Explanation', 'entities', {'relation': 'contain'}), ('entities', 'graph', {'relation': 'represent'}), ('this', 'suitable', {'relation': 'be'}), ('Curie', 'scientist', {'relation': 'be'}), ('Curie', 'contributions', {'relation': 'make'})]