knowledge-graph-construction
安装方式
先用 Prompt 核对来源,也可切换到安装命令或下载可用的安装包。
用 AI 助手安装
复制提示词,让助手先核对固定版本和依赖。
查看 Prompt收起 Prompt
先检查当前 Agent 是否已安装 SkillPI Skill Finder。如果尚未安装,请按官方仓库的说明安装并启用:https://github.com/Findskills/skillpi。然后使用 Skill Finder 打开此 SkillPI 详情页并定位 "knowledge-graph-construction":https://skillpi.com/zh/skills/deepskill-b4586e42be87608a3a1572793f9e165ce40dbfb41e46bf3024493cb29cf23e59。安装前核对上游来源和版本:https://github.com/brycewang-stanford/Auto-Empirical-Research-Skills/blob/bfa0a6e5a843babbf45a1ef1663fd5dc4f07c0ba/skills/43-wentorai-research-plugins/skills/tools/knowledge-graph/knowledge-graph-construction/SKILL.md。来源不一致时停止并说明差异。核对通过后,用 Skill Finder 安装目标 Skill,并报告安装路径和来源版本。
此命令从 GitHub 来源仓库获取指定技能。运行前请先查看源文件。
npx skills add https://github.com/brycewang-stanford/Auto-Empirical-Research-Skills/tree/bfa0a6e5a843babbf45a1ef1663fd5dc4f07c0ba/skills/43-wentorai-research-plugins/skills/tools/knowledge-graph/knowledge-graph-construction --skill knowledge-graph-construction来源与配置
查看 GitHub 源码brycewang-stanford/Auto-Empirical-Research-Skills固定提交 bfa0a6e5a843babbf45a1ef1663fd5dc4f07c0ba
配置方式待核实
请查看原始来源中的适用工具、依赖和权限要求。
安装实测待补充
本条目面向文献与学术工具场景,提供“knowledge-graph-construction”技能的目录入口。公开标签:learning、知识图谱、RAG、实体抽取。请通过固定上游版本核对实际功能、依赖与权限;此页为 Skillπ 独立编写的用途介绍和原站链接,不代表运行安全保证。原文与附件依各自许可开放。
文件浏览
---
name: knowledge-graph-construction
description: "Build research knowledge graphs for literature synthesis and RAG systems"
metadata:
openclaw:
emoji: "🗺"
category: "tools"
subcategory: "knowledge-graph"
keywords: ["knowledge graph", "knowledge modeling", "ontology", "RAG", "retrieval augmented generation"]
source: "N/A"
---
# Knowledge Graph Construction Guide
## Overview
Knowledge graphs (KGs) organize information as networks of entities and relationships, making them powerful tools for research synthesis, literature exploration, and AI-augmented retrieval. In academic contexts, knowledge graphs can represent relationships between papers, authors, methods, datasets, findings, and concepts -- enabling queries like "Which methods have been applied to dataset X?" or "What are the common limitations reported across studies of Y?"
This guide covers building knowledge graphs for research applications: defining schemas (ontologies), extracting entities and relations from text, storing and querying graph data, and integrating knowledge graphs with Retrieval Augmented Generation (RAG) systems for AI-powered research assistants.
Whether you are building a personal research knowledge base, constructing a domain-specific literature graph, or developing a RAG system for an academic chatbot, these patterns provide a solid foundation.
## Knowledge Graph Fundamentals
### Core Components
| Component | Definition | Research Example |
|-----------|-----------|-----------------|
| Entity (Node) | A distinct concept or object | Paper, Author, Method, Dataset |
| Relation (Edge) | A typed connection between entities | "cites", "uses_method", "evaluates_on" |
| Property | An attribute of an entity or relation | Paper.year, Author.affiliation |
| Ontology/Schema | Formal definition of entity and relation types | Research ontology defining valid types |
### Designing a Research Ontology
```yaml
# research_ontology.yaml
entities:
Paper:
properties: [title, year, doi, abstract, venue]
Author:
properties: [name, affiliation, orcid]
Method:
properties: [name, description, category]
Dataset:
properties: [name, domain, size, url]
Finding:
properties: [description, metric, value, significance]
Concept:
properties: [name, definition, domain]
relations:
CITES:
from: Paper
to: Paper
AUTHORED_BY:
from: Paper
to: Author
USES_METHOD:
from: Paper
to: Method
EVALUATES_ON:
from: Paper
to: Dataset
REPORTS_FINDING:
from: Paper
to: Finding
RELATED_TO:
from: Concept
to: Concept
INTRODUCES:
from: Paper
to: Method
```
## Entity and Relation Extraction
### LLM-Based Extraction
Using a large language model to extract structured knowledge from paper abstracts:
```python
import json
from openai import OpenAI
client = OpenAI()
EXTRACTION_PROMPT = """Extract entities and relationships from this research paper abstract.
Return JSON with:
- entities: list of {type, name, properties}
- relations: list of {source, relation, target}
Entity types: Paper, Method, Dataset, Finding, Concept
Relation types: USES_METHOD, EVALUATES_ON, REPORTS_FINDING, RELATED_TO, INTRODUCES
Abstract: {abstract}
Respond ONLY with valid JSON."""
def extract_from_abstract(abstract, paper_title):
response = client.chat.completions.create(
model="gpt-4o",
messages=[
{"role": "system", "content": "You are a research knowledge extraction system."},
{"role": "user", "content": EXTRACTION_PROMPT.format(abstract=abstract)}
],
response_format={"type": "json_object"},
temperature=0
)
result = json.loads(response.choices[0].message.content)
# Add the paper itself as an entity
result['entities'].insert(0, {
'type': 'Paper',
'name': paper_title,
'properties': {'abstract': abstract[:200]}
})
return result
```
### SpaCy + Custom NER for Domain-Specific Extraction
```python
import spacy
from spacy.tokens import Span
nlp = spacy.load("en_core_web_trf")
# Register custom entity types
@spacy.Language.component("research_entities")
def research_entity_component(doc):
# Pattern-based recognition for methods
method_patterns = [
"random forest", "gradient boosting", "neural network",
"transformer", "attention mechanism", "BERT", "GPT",
"convolutional", "recurrent", "GAN"
]
new_ents = list(doc.ents)
for token in doc:
for pattern in method_patterns:
if pattern.lower() in doc[token.i:token.i+3].text.lower():
span = doc.char_span(token.idx, token.idx + len(pattern),
label="METHOD")
if span and span not in new_ents:
new_ents.append(span)
doc.ents = spacy.util.filter_spans(new_ents)
return doc
nlp.add_pipe("research_entities", after="ner")
```
## Graph Storage and Querying
### Neo4j (Production)
```python
from neo4j import GraphDatabase
class ResearchGraph:
def __init__(self, uri, user, password):
self.driver = GraphDatabase.driver(uri, auth=(user, password))
def add_paper(self, paper):
with self.driver.session() as session:
session.run("""
MERGE (p:Paper {doi: $doi})
SET p.title = $title, p.year = $year, p.abstract = $abstract
""", **paper)
def add_citation(self, citing_doi, cited_doi):
with self.driver.session() as session:
session.run("""
MATCH (a:Paper {doi: $citing})
MATCH (b:Paper {doi: $cited})
MERGE (a)-[:CITES]->(b)
""", citing=citing_doi, cited=cited_doi)
def add_method_usage(self, paper_doi, method_name):
with self.driver.session() as session:
session.run("""
MATCH (p:Paper {doi: $doi})
MERGE (m:Method {name: $method})
MERGE (p)-[:USES_METHOD]->(m)
""", doi=paper_doi, method=method_name)
def find_papers_using_method(self, method_name):
with self.driver.session() as session:
result = session.run("""
MATCH (p:Paper)-[:USES_METHOD]->(m:Method {name: $method})
RETURN p.title AS title, p.year AS year, p.doi AS doi
ORDER BY p.year DESC
""", method=method_name)
return [dict(record) for record in result]
def find_common_methods(self, doi1, doi2):
with self.driver.session() as session:
result = session.run("""
MATCH (p1:Paper {doi: $doi1})-[:USES_METHOD]->(m:Method)
<-[:USES_METHOD]-(p2:Paper {doi: $doi2})
RETURN m.name AS method
""", doi1=doi1, doi2=doi2)
return [record['method'] for record in result]
```
### NetworkX (Lightweight / Prototyping)
```python
import networkx as nx
import json
def build_research_graph(extracted_data_list):
"""Build a NetworkX graph from extracted paper data."""
G = nx.MultiDiGraph()
for data in extracted_data_list:
for entity in data['entities']:
G.add_node(
entity['name'],
type=entity['type'],
**entity.get('properties', {})
)
for rel in data['relations']:
G.add_edge(
rel['source'],
rel['target'],
relation=rel['relation']
)
return G
# Query the graph
def get_method_landscape(G):
"""Find which methods are most used across papers."""
methods = [n for n, d in G.nodes(data=True) if d.get('type') == 'Method']
method_usage = {}
for method in methods:
papers = [n for n in G.predecessors(method)
if G.nodes[n].get('type') == 'Paper']
method_usage[method] = len(papers)
return sorted(method_usage.items(), key=lambda x: x[1], reverse=True)
```
## Knowledge Graph + RAG Integration
Combining knowledge graphs with retrieval augmented generation creates powerful research assistants:
```python
def kg_rag_query(question, graph, embedding_model, llm):
"""Answer a research question using KG-enhanced RAG."""
# Step 1: Extract entities from the question
question_entities = extract_entities(question)
# Step 2: Retrieve relevant subgraph
subgraph_nodes = set()
for entity in question_entities:
if entity in graph:
# Get 2-hop neighborhood
neighbors = nx.ego_graph(graph, entity, radius=2)
subgraph_nodes.update(neighbors.nodes())
# Step 3: Format context from subgraph
context_parts = []
for node in subgraph_nodes:
node_data = graph.nodes[node]
edges = list(graph.edges(node, data=True))
context_parts.append(
f"{node} ({node_data.get('type', 'Unknown')}): "
f"{', '.join(f'{e[2].get(\"relation\", \"related_to\")} {e[1]}' for e in edges[:5])}"
)
context = '\n'.join(context_parts[:20])
# Step 4: Generate answer with LLM
prompt = f"""Based on the following knowledge graph context, answer the question.
Context:
{context}
Question: {question}
Provide a detailed answer citing specific papers, methods, and findings from the context."""
return llm.generate(prompt)
```
## Best Practices
- **Start with a clear schema.** Define your entity types and relations before extracting data. A schema change later requires re-processing.
- **Use persistent identifiers.** DOIs for papers, ORCIDs for authors, and canonical names for methods prevent duplicate nodes.
- **Validate extracted triples.** LLM extraction is imperfect. Sample and manually verify 5-10% of extractions.
- **Enrich with external data.** Link your KG to OpenAlex, CrossRef, or Wikidata for additional metadata.
- **Version your graph.** Export snapshots regularly and track changes over time.
- **Design queries before building.** Know what questions you want to answer before deciding on the schema.
## References
- [Neo4j Documentation](https://neo4j.com/docs/) -- Graph database
- [NetworkX Documentation](https://networkx.org/) -- Python graph library
- [OpenAlex API](https://docs.openalex.org/) -- Open bibliographic data
- [LlamaIndex Knowledge Graph Guide](https://docs.llamaindex.ai/) -- KG-RAG integration
- [Graphiti](https://github.com/getzep/graphiti) -- Temporal knowledge graph library
版本历史
-
v2026.07
GitHub ↗
原版更新说明
## Highlights - **First tagged release.** Every gate is green: `make check` (validate + 183 unit tests + eval-harness + numeric benchmarks), validate-catalog, quality-evals, and OpenSSF Scorecard on `main`. - **Rigor double loop at 13 method families.** Each family closes taxonomy tag → eval scenario (does the agent avoid the method's known traps?) → deterministic numeric benchmark (does it recover the true effect?). New this cycle: heterogeneous treatment effects (CATE) and quantile treatment effects (QTE). - **Paper-WorkFlow flagship at 29/29 executable rigor gates**, now merged to its `main` with a drift-gated README badge — the credibility artifact is checked by CI, so it can never silently go stale ([RIGOR.md](https://github.com/brycewang-stanford/Paper-WorkFlow/blob/main/RIGOR.md)). - **1,150 vendored skills / 69 collections**, all license-audited, security-scanned, tracked in a machine-readable catalog with CI-enforced freshness, and importable as a single whole-repo router skill. - **Hardened weekly upstream syncs**: synced trees must pass the full gate before merge; this cycle both sync PRs were verified, patched (StatsPAI's SkillOpt execution-gate card restored), and merged. - **First-party plugin marketplace** (Python / R / Stata empirical-analysis plugins + guide) shipped in the previous cycle, now under a tagged version. ## Known Follow-Ups - Ecosystem benchmark comparison (AERS vs econometrics agents on the shared benchmark suite) — [PLAN-2026-07 week 3](https://github.com/brycewang-stanford/Auto-Empirical-Research-Skills/blob/main/docs/PLAN-2026-07.md). - Decomposition (Oaxaca–Blinder) and shift-share (Bartik) method families (weeks 3–4). - GitHub Pages catalog site, README demo screenshots, five-language README consistency script (week 4). ## Catalog - Top-level collections: **69** - `SKILL.md` files: **1150** - Cataloged agent tools: **335** ([`tools/CATALOG.md`](../tools/CATALOG.md)) ## Methodological rigor - Method families in the coverage map: **13** ([`RIGOR_COVERAGE.md`](RIGOR_COVERAGE.md)) - Eval scenarios: **26** (138 rubric items, 122 auto-checkable) ([`../eval-harness/`](../eval-harness/README.md)) - Benchmark tasks: **13** (70 gold checks, 58 required) ([`../benchmark/`](../benchmark/README.md)) ### Method families (skills tagged) - `iv`: 27 - `rdd`: 25 - `panel-fe`: 19 - `staggered-did`: 17 - `bayesian`: 13 - `did`: 10 - `event-study`: 10 - `matching`: 10 - `synthetic-control`: 10 - `cate`: 8 - `dml`: 8 - `survival`: 3 - `quantile`: 2 ### Eval scenarios by category - `causal-identification`: 14 - `citation-hygiene`: 1 - `reproducibility`: 2 - `research-integrity`: 1 - `runtime-safety`: 1 - `statistical-validity`: 2 - `writing-compliance`: 3 - `writing-style`: 2 ## License buckets - AGPL-3.0: 1 - Apache-2.0: 1 - CC-BY-NC-4.0 (non-commercial): 1 - CC-BY-SA-4.0: 1 - CC-BY-SA-4.0 (repository default): 4 - GPL-3.0: 1 - MIT: 35 - MIT Non-Commercial: 1 - Mixed (per-skill; see folder): 2 - UNKNOWN - check upstream: 22 ## Quality gates - `make check` — catalog/provenance/audit/eval freshness, repo hygiene, Paper-WorkFlow gates, stdlib unit tests, eval-harness lint + graded smoke, and the strict numeric benchmark (reference-gold drift fails the build). - External links and OpenSSF Scorecard run on their scheduled workflows.
当前收录版本
0.0.1
质量评测
满分 100。前四项来自 DeepSkill 收录的质量报告。
评分依据
面向学术研究的知识图谱构建,解决文献综述和RAG系统的核心痛点
评分依据
触发词覆盖全面:knowledge graph, ontology, RAG等关键词精准
评分依据
文档结构完整:从基础概念到具体实现再到最佳实践
评分依据
使用标准可靠的第三方库(OpenAI、SpaCy、Neo4j、NetworkX)
计算方式
取前四项原始分值的算术平均,四舍五入取整。可通过收录报告核对各项评分与说明,运行记录需单独查证。
权限与使用前检查
根据当前主文档自动整理,命中内容可能是示例或防护说明;不是实际权限声明,也未覆盖附件、外部依赖或运行行为。
未从主文档识别到上述常见操作,不能据此判断无需权限或没有风险。
文档引用的域名或地址
这些地址可能用于文档链接或示例,不是已批准的联网清单。使用前核对实际目的地及发送的数据。
- docs.llamaindex.ai
- docs.openalex.org
- github.com
- neo4j.com
- networkx.org
安全评级与访问范围
risk · 静态证据核验,不代表运行安全保证。
使用前请由宿主核对并授权实际文件读写、外部服务和联网目的地;本站的核验不会授予任何运行权限。
用户讨论
还没有已核实的点评。