RDFLib

RDFLib 是一个纯 Python 包，用于处理 RDF。RDFLib 包含了处理 RDF 所需的大部分内容，包括：

RDF/XML、N3、NTriples、N-Quads、Turtle、TriX、Trig 和 JSON-LD 的解析器和序列化器

一个图形接口，可以由多种存储实现中的任何一种支持

存储实现，包括内存中、磁盘上的持久化（Berkeley DB）和远程SPARQL端点

一个SPARQL 1.1实现 - 支持SPARQL 1.1查询和更新语句

SPARQL 函数扩展机制

图数据库是基于网络模型的应用程序的绝佳选择。为了标准化此类图的语法和语义，W3C推荐使用语义网技术，参见语义网。

SPARQL 作为一种查询语言，类似于这些图的 SQL 或 Cypher。本笔记本展示了通过生成 SPARQL 将 LLMs 作为自然语言接口应用于图数据库的示例。

免责声明： 迄今为止，通过LLMs生成SPARQL查询仍然有些不稳定。特别是对于会改变图形的UPDATE查询要格外小心。

设置

我们需要安装一个python库：

!pip install rdflib

有几种来源可以运行查询，包括网络上的文件、本地可用的文件、SPARQL端点，例如Wikidata和三元组存储。

from langchain.chains import GraphSparqlQAChain
from langchain_community.graphs import RdfGraph
from langchain_openai import ChatOpenAI

API Reference:GraphSparqlQAChain | RdfGraph | ChatOpenAI

graph = RdfGraph(
    source_file="http://www.w3.org/People/Berners-Lee/card",
    standard="rdf",
    local_copy="test.ttl",
)

请注意，如果源是只读的，提供local_file是必要的，以便在本地存储更改。

刷新图模式信息

如果数据库的模式发生变化，您可以刷新生成SPARQL查询所需的模式信息。

graph.load_schema()

graph.get_schema

In the following, each IRI is followed by the local name and optionally its description in parentheses. 
The RDF graph supports the following node types:
<http://xmlns.com/foaf/0.1/PersonalProfileDocument> (PersonalProfileDocument, None), <http://www.w3.org/ns/auth/cert#RSAPublicKey> (RSAPublicKey, None), <http://www.w3.org/2000/10/swap/pim/contact#Male> (Male, None), <http://xmlns.com/foaf/0.1/Person> (Person, None), <http://www.w3.org/2006/vcard/ns#Work> (Work, None)
The RDF graph supports the following relationships:
<http://www.w3.org/2000/01/rdf-schema#seeAlso> (seeAlso, None), <http://purl.org/dc/elements/1.1/title> (title, None), <http://xmlns.com/foaf/0.1/mbox_sha1sum> (mbox_sha1sum, None), <http://xmlns.com/foaf/0.1/maker> (maker, None), <http://www.w3.org/ns/solid/terms#oidcIssuer> (oidcIssuer, None), <http://www.w3.org/2000/10/swap/pim/contact#publicHomePage> (publicHomePage, None), <http://xmlns.com/foaf/0.1/openid> (openid, None), <http://www.w3.org/ns/pim/space#storage> (storage, None), <http://xmlns.com/foaf/0.1/name> (name, None), <http://www.w3.org/2000/10/swap/pim/contact#country> (country, None), <http://www.w3.org/1999/02/22-rdf-syntax-ns#type> (type, None), <http://www.w3.org/ns/solid/terms#profileHighlightColor> (profileHighlightColor, None), <http://www.w3.org/ns/pim/space#preferencesFile> (preferencesFile, None), <http://www.w3.org/2000/01/rdf-schema#label> (label, None), <http://www.w3.org/ns/auth/cert#modulus> (modulus, None), <http://www.w3.org/2000/10/swap/pim/contact#participant> (participant, None), <http://www.w3.org/2000/10/swap/pim/contact#street2> (street2, None), <http://www.w3.org/2006/vcard/ns#locality> (locality, None), <http://xmlns.com/foaf/0.1/nick> (nick, None), <http://xmlns.com/foaf/0.1/homepage> (homepage, None), <http://creativecommons.org/ns#license> (license, None), <http://xmlns.com/foaf/0.1/givenname> (givenname, None), <http://www.w3.org/2006/vcard/ns#street-address> (street-address, None), <http://www.w3.org/2006/vcard/ns#postal-code> (postal-code, None), <http://www.w3.org/2000/10/swap/pim/contact#street> (street, None), <http://www.w3.org/2003/01/geo/wgs84_pos#lat> (lat, None), <http://xmlns.com/foaf/0.1/primaryTopic> (primaryTopic, None), <http://www.w3.org/2006/vcard/ns#fn> (fn, None), <http://www.w3.org/2003/01/geo/wgs84_pos#location> (location, None), <http://usefulinc.com/ns/doap#developer> (developer, None), <http://www.w3.org/2000/10/swap/pim/contact#city> (city, None), <http://www.w3.org/2006/vcard/ns#region> (region, None), <http://xmlns.com/foaf/0.1/member> (member, None), <http://www.w3.org/2003/01/geo/wgs84_pos#long> (long, None), <http://www.w3.org/2000/10/swap/pim/contact#address> (address, None), <http://xmlns.com/foaf/0.1/family_name> (family_name, None), <http://xmlns.com/foaf/0.1/account> (account, None), <http://xmlns.com/foaf/0.1/workplaceHomepage> (workplaceHomepage, None), <http://purl.org/dc/terms/title> (title, None), <http://www.w3.org/ns/solid/terms#publicTypeIndex> (publicTypeIndex, None), <http://www.w3.org/2000/10/swap/pim/contact#office> (office, None), <http://www.w3.org/2000/10/swap/pim/contact#homePage> (homePage, None), <http://xmlns.com/foaf/0.1/mbox> (mbox, None), <http://www.w3.org/2000/10/swap/pim/contact#preferredURI> (preferredURI, None), <http://www.w3.org/ns/solid/terms#profileBackgroundColor> (profileBackgroundColor, None), <http://schema.org/owns> (owns, None), <http://xmlns.com/foaf/0.1/based_near> (based_near, None), <http://www.w3.org/2006/vcard/ns#hasAddress> (hasAddress, None), <http://xmlns.com/foaf/0.1/img> (img, None), <http://www.w3.org/2000/10/swap/pim/contact#assistant> (assistant, None), <http://xmlns.com/foaf/0.1/title> (title, None), <http://www.w3.org/ns/auth/cert#key> (key, None), <http://www.w3.org/ns/ldp#inbox> (inbox, None), <http://www.w3.org/ns/solid/terms#editableProfile> (editableProfile, None), <http://www.w3.org/2000/10/swap/pim/contact#postalCode> (postalCode, None), <http://xmlns.com/foaf/0.1/weblog> (weblog, None), <http://www.w3.org/ns/auth/cert#exponent> (exponent, None), <http://rdfs.org/sioc/ns#avatar> (avatar, None)

查询图

现在，您可以使用图形SPARQL问答链来询问有关图形的问题。

chain = GraphSparqlQAChain.from_llm(
    ChatOpenAI(temperature=0), graph=graph, verbose=True
)

chain.run("What is Tim Berners-Lee's work homepage?")

[1m> Entering new GraphSparqlQAChain chain...[0m
Identified intent:
[32;1m[1;3mSELECT[0m
Generated SPARQL:
[32;1m[1;3mPREFIX foaf: <http://xmlns.com/foaf/0.1/>
SELECT ?homepage
WHERE {
    ?person foaf:name "Tim Berners-Lee" .
    ?person foaf:workplaceHomepage ?homepage .
}[0m
Full Context:
[32;1m[1;3m[][0m

[1m> Finished chain.[0m

"Tim Berners-Lee's work homepage is http://www.w3.org/People/Berners-Lee/."

更新图表

类似地，您可以使用自然语言更新图表，即插入三元组。

chain.run(
    "Save that the person with the name 'Timothy Berners-Lee' has a work homepage at 'http://www.w3.org/foo/bar/'"
)

[1m> Entering new GraphSparqlQAChain chain...[0m
Identified intent:
[32;1m[1;3mUPDATE[0m
Generated SPARQL:
[32;1m[1;3mPREFIX foaf: <http://xmlns.com/foaf/0.1/>
INSERT {
    ?person foaf:workplaceHomepage <http://www.w3.org/foo/bar/> .
}
WHERE {
    ?person foaf:name "Timothy Berners-Lee" .
}[0m

[1m> Finished chain.[0m

'Successfully inserted triples into the graph.'

让我们验证结果：

query = (
    """PREFIX foaf: <http://xmlns.com/foaf/0.1/>\n"""
    """SELECT ?hp\n"""
    """WHERE {\n"""
    """    ?person foaf:name "Timothy Berners-Lee" . \n"""
    """    ?person foaf:workplaceHomepage ?hp .\n"""
    """}"""
)
graph.query(query)

[(rdflib.term.URIRef('https://www.w3.org/'),),
 (rdflib.term.URIRef('http://www.w3.org/foo/bar/'),)]

返回 SPARQL 查询

你可以使用return_sparql_query参数从Sparql QA Chain返回SPARQL查询步骤

chain = GraphSparqlQAChain.from_llm(
    ChatOpenAI(temperature=0), graph=graph, verbose=True, return_sparql_query=True
)

result = chain("What is Tim Berners-Lee's work homepage?")
print(f"SPARQL query: {result['sparql_query']}")
print(f"Final answer: {result['result']}")

[1m> Entering new GraphSparqlQAChain chain...[0m
Identified intent:
[32;1m[1;3mSELECT[0m
Generated SPARQL:
[32;1m[1;3mPREFIX foaf: <http://xmlns.com/foaf/0.1/>
SELECT ?workHomepage
WHERE {
    ?person foaf:name "Tim Berners-Lee" .
    ?person foaf:workplaceHomepage ?workHomepage .
}[0m
Full Context:
[32;1m[1;3m[][0m

[1m> Finished chain.[0m
SPARQL query: PREFIX foaf: <http://xmlns.com/foaf/0.1/>
SELECT ?workHomepage
WHERE {
    ?person foaf:name "Tim Berners-Lee" .
    ?person foaf:workplaceHomepage ?workHomepage .
}
Final answer: Tim Berners-Lee's work homepage is http://www.w3.org/People/Berners-Lee/.

print(result["sparql_query"])

PREFIX foaf: <http://xmlns.com/foaf/0.1/>
SELECT ?workHomepage
WHERE {
    ?person foaf:name "Tim Berners-Lee" .
    ?person foaf:workplaceHomepage ?workHomepage .
}

设置​

刷新图模式信息​

查询图​

更新图表​

返回 SPARQL 查询​

这个页面有帮助吗？

设置

刷新图模式信息

查询图

更新图表

返回 SPARQL 查询