knowledge-graph-kit 0.1.0__py3-none-any.whl

knowledge_graph_kit/schema.txt

@@ -0,0 +1,38 @@
+# ========== 节点类型定义 ==========
+节点类型:
+  # 1. 知识节点（核心骨架）
+  - Topic:             # 知识主题
+      属性: [name, level(认知层次), difficulty, estimatedTime]
+  - Concept:           # 原子概念（如“多态”），Topic的子类
+  - Skill:             # 可操作技能（如“调试”），Topic的子类
+
+  # 2. 资源节点（知识载体）
+  - Video:             # MOOC视频片段
+      属性: [title, url, duration, startTime, endTime]
+  - TextSegment:       # 教材/讲义段落
+      属性: [content, pageNum]
+  - CodeExample:       # 代码示例
+      属性: [codeSnippet, language]
+
+   # 3. 教学节点（智能应用）
+  - Question:          # 题目（预设或生成）
+      属性: [stem(题干), type(选择/填空/简答), correctAnswer, difficulty]
+
+# ========== 关系类型定义（部分） ==========
+关系类型:
+  # ---- 知识-知识关系 ----
+  hasPrerequisite:     # 知识A是B的前置
+      domain: Topic, range: Topic
+  isA:                 # 概念上下位
+      domain: Topic, range: Topic
+  commonlyConfusedWith:# 易混淆
+      domain: Topic, range: Topic
+
+  # ---- 知识-资源关系 ----
+  teaches:             # 视频讲解知识点
+      domain: Video, range: Topic
+  hasExample:          # 知识点有代码示例
+      domain: Topic, range: CodeExample
+  assessedBy:          # 知识点被题目考查
+      domain: Topic, range: Question
+

knowledge_graph_kit-0.1.0.dist-info/METADATA

@@ -0,0 +1,120 @@
+Metadata-Version: 2.4
+Name: knowledge-graph-kit
+Version: 0.1.0
+Summary: 知识图谱构建管线：文本分块、LLM抽取、实体解析、Neo4j写入
+Author-email: hbue_jerry <lovecpp@foxmail.com>
+License: MIT
+Project-URL: Homepage, https://github.com/jerryhbue/property-graph
+Project-URL: Source, https://github.com/jerryhbue/property-graph
+Project-URL: Tracker, https://github.com/jerryhbue/property-graph/issues
+Classifier: Development Status :: 3 - Alpha
+Classifier: Intended Audience :: Developers
+Classifier: License :: OSI Approved :: MIT License
+Classifier: Programming Language :: Python :: 3
+Classifier: Programming Language :: Python :: 3.10
+Classifier: Programming Language :: Python :: 3.11
+Classifier: Programming Language :: Python :: 3.12
+Classifier: Topic :: Scientific/Engineering :: Artificial Intelligence
+Requires-Python: >=3.10
+Description-Content-Type: text/markdown
+License-File: LICENSE
+Requires-Dist: python-dotenv>=1.0.0
+Requires-Dist: openai>=1.0.0
+Requires-Dist: pydantic>=2.0.0
+Requires-Dist: neo4j>=5.0.0
+Requires-Dist: httpx>=0.28.0
+Dynamic: license-file
+
+# knowledge-graph-kit
+
+知识图谱构建管线：从教材文本中抽取实体和关系，写入 Neo4j 图数据库。
+
+## 安装
+
+```bash
+pip install knowledge-graph-kit
+```
+
+## 环境变量
+
+| 变量 | 说明 | 默认值 |
+|---|---|---|
+| `OPENAI_API_KEY` | OpenAI API 密钥 | — |
+| `OPENAI_BASE_URL` | OpenAI API 地址（可换兼容 API） | — |
+| `LLM_MODEL_NAME` | 模型名称 | `gpt-4o-mini` |
+| `NEO4J_URI` | Neo4j 连接地址 | `bolt://localhost:7687` |
+| `NEO4J_USERNAME` | Neo4j 用户名 | `neo4j` |
+| `NEO4J_PASSWORD` | Neo4j 密码 | `12345678` |
+
+在项目根目录创建 `.env` 文件即可自动加载，或直接在 shell 中设置。
+
+## CLI 命令
+
+安装后提供 4 个命令行工具：
+
+### 1. 文本分块
+
+```bash
+kg-chunker <txt_path>
+```
+
+按章节标题将教材文本拆分为语义块。
+
+### 2. 实体关系抽取
+
+```bash
+kg-extractor <txt_path>
+```
+
+基于本体 schema 引导 LLM 抽取实体和关系，输出 `extraction_result.json`。
+
+可通过 `KG_SCHEMA_PATH` 环境变量指定自定义 ontology 文件。
+
+### 3. 实体解析去重
+
+```bash
+kg-resolver <input.json>
+```
+
+精确/模糊去重实体，清理属性，更新关系引用，输出 `extraction_result_clean.json`。
+
+### 4. 写入 Neo4j
+
+```bash
+kg-neo4j-writer [input.json]
+```
+
+将清洗后的结果写入 Neo4j 图数据库。默认尝试读取 `extraction_result_clean.json` 或 `extraction_result.json`。
+
+## 程序化使用
+
+```python
+from knowledge_graph_kit import chunk_file, Neo4jWriter
+
+# 文本分块
+chunks = chunk_file("教材.txt")
+
+# 配置 OpenAI
+from knowledge_graph_kit.extractor import configure
+configure(api_key="sk-xxx", model="gpt-4o")
+
+# 写入 Neo4j
+writer = Neo4jWriter(
+    uri="bolt://localhost:7687",
+    user="neo4j",
+    password="your-password",
+)
+writer.write_entities(entities)
+writer.write_relations(relations)
+writer.close()
+```
+
+## 管线流程
+
+```
+txt 文件 → 分块(chunker) → LLM抽取(extractor) → 实体解析(resolver) → Neo4j写入(writer)
+```
+
+## License
+
+MIT

knowledge_graph_kit-0.1.0.dist-info/RECORD

@@ -0,0 +1,12 @@
+knowledge_graph_kit/__init__.py,sha256=kdwMYns2WDXC7eAh8nwEmkys7XYRm2lrhU8kP-pwggQ,833
+knowledge_graph_kit/chunker.py,sha256=Dr61Sast26clUGsMuHDdbNUZ85pA6w3IjnG5RB8QS8o,8944
+knowledge_graph_kit/entity_resolver.py,sha256=dWxdMHZGlr8eJpduXEZUjLYyHbMN0Q6MzQ3ups0Zcmg,15610
+knowledge_graph_kit/extractor.py,sha256=Q49tKvVUDmkJYJ7Wds20bVwev1R69U-cqelpDCfuBMc,18491
+knowledge_graph_kit/neo4j_writer.py,sha256=arMZHJijGSNgSGzCroc55Jvd5OYsziosGCKPY_FZWxw,10498
+knowledge_graph_kit/schema.txt,sha256=T7Xi1Xm51BeP6jSyxZKa_OWemwR8UUzpvxfymLFsYdk,1486
+knowledge_graph_kit-0.1.0.dist-info/licenses/LICENSE,sha256=Btzdu2kIoMbdSp6OyCLupB1aRgpTCJ_szMimgEnpkkE,1056
+knowledge_graph_kit-0.1.0.dist-info/METADATA,sha256=4zcwC2P15OFzP2VvtX2QQTkU1teqMLarTUggqO74oek,3241
+knowledge_graph_kit-0.1.0.dist-info/WHEEL,sha256=aeYiig01lYGDzBgS8HxWXOg3uV61G9ijOsup-k9o1sk,91
+knowledge_graph_kit-0.1.0.dist-info/entry_points.txt,sha256=BV0DCAgUuMpft7BFpPNQO8p_U-zgvlAq2V-iND7MX_4,225
+knowledge_graph_kit-0.1.0.dist-info/top_level.txt,sha256=BsnPVDjVwMYIa2GI1KLziv6eKZtsr917YIF8g78qTHY,20
+knowledge_graph_kit-0.1.0.dist-info/RECORD,,

knowledge_graph_kit-0.1.0.dist-info/WHEEL

@@ -0,0 +1,5 @@
+Wheel-Version: 1.0
+Generator: setuptools (82.0.1)
+Root-Is-Purelib: true
+Tag: py3-none-any
+

knowledge_graph_kit-0.1.0.dist-info/entry_points.txt

@@ -0,0 +1,5 @@
+[console_scripts]
+kg-chunker = knowledge_graph_kit.chunker:main
+kg-extractor = knowledge_graph_kit.extractor:main
+kg-neo4j-writer = knowledge_graph_kit.neo4j_writer:main
+kg-resolver = knowledge_graph_kit.entity_resolver:main

knowledge_graph_kit-0.1.0.dist-info/licenses/LICENSE

@@ -0,0 +1,21 @@
+MIT License
+
+Copyright (c) 2025
+
+Permission is hereby granted, free of charge, to any person obtaining a copy
+of this software and associated documentation files (the "Software"), to deal
+in the Software without restriction, including without limitation the rights
+to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
+copies of the Software, and to permit persons to whom the Software is
+furnished to do so, subject to the following conditions:
+
+The above copyright notice and this permission notice shall be included in all
+copies or substantial portions of the Software.
+
+THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
+AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
+LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
+OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
+SOFTWARE.

knowledge_graph_kit-0.1.0.dist-info/top_level.txt

@@ -0,0 +1 @@
+knowledge_graph_kit