使用 LangChain 从文本数据构建知识图

pip install -q langchain openai pyvis gradio==3.39.0

from langchain.prompts import PromptTemplatefrom langchain.llms.openai import OpenAIfrom langchain.chains import LLMChainfrom langchain.graphs.networkx_graph import KG_TRIPLE_DELIMITERfrom pprint import pprintfrom pyvis.network import Networkimport networkx as nximport gradio as gr

from google.colab import userdataOPENAI_API_KEY = userdata.get('OPENAI_API_KEY')

# 用于知识三元组提取的提示模板_DEFAULT_KNOWLEDGE_TRIPLE_EXTRACTION_TEMPLATE = ("You are a networked intelligence helping a human track knowledge triples"" about all relevant people, things, concepts, etc. and integrating"" them with your knowledge stored within your weights"" as well as that stored in a knowledge graph."" Extract all of the knowledge triples from the text."" A knowledge triple is a clause that contains a subject, a predicate,"" and an object. The subject is the entity being described,"" the predicate is the property of the subject that is being"" described, and the object is the value of the property.\\n\\n""EXAMPLE\\n""It's a state in the US. It's also the number 1 producer of gold in the US.\\n\\n"f"Output: (Nevada, is a, state){KG_TRIPLE_DELIMITER}(Nevada, is in, US)"f"{KG_TRIPLE_DELIMITER}(Nevada, is the number 1 producer of, gold)\\n""END OF EXAMPLE\\n\\n""EXAMPLE\\n""I'm going to the store.\\n\\n""Output: NONE\\n""END OF EXAMPLE\\n\\n""EXAMPLE\\n""Oh huh. I know Descartes likes to drive antique scooters and play the mandolin.\\n"f"Output: (Descartes, likes to drive, antique scooters){KG_TRIPLE_DELIMITER}(Descartes, plays, mandolin)\\n""END OF EXAMPLE\\n\\n""EXAMPLE\\n""{text}""Output:")
KNOWLEDGE_TRIPLE_EXTRACTION_PROMPT = PromptTemplate(input_variables=["text"],template=_DEFAULT_KNOWLEDGE_TRIPLE_EXTRACTION_TEMPLATE,)

llm = OpenAI(api_key=OPENAI_API_KEY,temperature=0.9)
# 使用知识三元组提取提示创建一个LLMChainchain = LLMChain(llm=llm, prompt=KNOWLEDGE_TRIPLE_EXTRACTION_PROMPT)

# Run the chain with the specified texttext = "The city of Paris is the capital and most populous city of France. The Eiffel Tower is a famous landmark in Paris."triples = chain.invoke({'text' : text}).get('text')

def parse_triples(response, delimiter=KG_TRIPLE_DELIMITER):if not response:return []return response.split(delimiter)
triples_list = parse_triples(triples)
pprint(triples_list)

[' (Paris, is the capital of, France)', '(Paris, is the most populous city in, France)', '(Eiffel Tower, is a, famous landmark)', '(Eiffel Tower, is in, Paris)']

def create_graph_from_triplets(triplets):G = nx.DiGraph()for triplet in triplets:subject, predicate, obj = triplet.strip().split(',')G.add_edge(subject.strip(), obj.strip(), label=predicate.strip())return G
def nx_to_pyvis(networkx_graph):pyvis_graph = Network(notebook=True, cdn_resources='remote')for node in networkx_graph.nodes():pyvis_graph.add_node(node)for edge in networkx_graph.edges(data=True):pyvis_graph.add_edge(edge[0], edge[1], label=edge[2]["label"])return pyvis_graph
def generateGraph():triplets = [t.strip() for t in triples_list if t.strip()]graph = create_graph_from_triplets(triplets)pyvis_network = nx_to_pyvis(graph)
pyvis_network.toggle_hide_edges_on_drag(True)pyvis_network.toggle_physics(False)pyvis_network.set_edge_smooth('discrete')
html = pyvis_network.generate_html()html = html.replace("'", "\\"")
return f"""<iframe style="width: 100%; height: 600px;margin:0 auto" name="result" allow="midi; geolocation; microphone; camera;display-capture; encrypted-media;" sandbox="allow-modals allow-formsallow-scripts allow-same-origin allow-popupsallow-top-navigation-by-user-activation allow-downloads" allowfullscreen=""allowpaymentrequest="" frameborder="0" srcdoc='{html}'></iframe>"""

demo = gr.Interface( generateGraph, inputs= None , outputs=gr.outputs.HTML(), title= “知识图谱” , allow_flagging= 'never' , live= True , ) 
demo.launch( height= 800 , width= “100%”）