└── README.md


/README.md:
--------------------------------------------------------------------------------
 1 | # Tree-KG
 2 | 
 3 | **Tree-KG** is an expandable framework for constructing and iteratively expanding knowledge graphs (KGs) in knowledge-intensive domains.
 4 | 
 5 | ## Example Usage
 6 | 
 7 | ### 1. Submit a Task
 8 | 
 9 | ```bash
10 | curl -X POST https://pacman.cs.tsinghua.edu.cn/api/treekg/submit_task \
11 |   -F "user_config.json=@path/to/user_config.json" \
12 |   -F "file_dir=@path/to/input_file"
13 | ````
14 | 
15 | Example book:
16 | *《大学物理学（第4版）电磁学、光学、量子物理》*
17 | 张三慧 编著 安宇 阮东 李岩松 修订
18 | 清华大学出版社
19 | 
20 | Example `user_config.json`:
21 | 
22 | ```json
23 | {
24 |     "course_name": "Physics",
25 |     "material_name": "Electromagnetic_Optics_Quantum_Physics.pdf",
26 |     "book_start_page": 1,
27 |     "book_end_page": 507,
28 |     "cover_start_page": 1,
29 |     "cover_end_page": 1,
30 |     "toc_start_page": 2,
31 |     "toc_end_page": 9,
32 |     "text_start_page": 10,
33 |     "text_end_page": 479,
34 |     "appendix_start_page": 480,
35 |     "appendix_end_page": 507,
36 |     "toc_max_level": 3,
37 |     "toc_re_expression": [
38 |       "(第\\d+篇.*\\n\\n)",
39 |       "(第\\d+章.*\\n\\n|.*物理趣闻.*\\n\\n|.*元素周期表.*\\n\\n|.*数值表.*\\n\\n|.*部分习题答案.*\\n\\n|.*索引.*\\n\\n)",
40 |       "(\\*?\\d+\\.\\d+.*\\n\\n|.+?\\n\\n)"
41 |     ]
42 | }
43 | ```
44 | 
45 | #### Field Descriptions
46 | 
47 | * **course\_name**: e.g., `"Physics"`
48 | * **material\_name**: e.g., `"Electromagnetic_Optics_Quantum_Physics.pdf"`
49 | * **Page ranges** [book, cover, TOC (table of contents), text, appendix]: counted from the first file page, not internal book numbering.
50 | * **toc\_max\_level**: maximum TOC depth (starts from 1).
51 | * **toc\_re\_expression**: regular expressions to match TOC levels.
52 | 
53 | 
54 | ### 2. Check Task Status
55 | 
56 | ```bash
57 | curl https://pacman.cs.tsinghua.edu.cn/api/treekg/task_status/${task_id}
58 | ```
59 | 
60 | Example response:
61 | 
62 | ```json
63 | {
64 |   "task_id": "uuid-string",
65 |   "status": "processing",
66 |   "progress": 60,
67 |   "current_step": "augmentation",
68 |   "created_at": "2025-05-30T12:00:00",
69 |   "updated_at": "2025-05-30T12:05:00"
70 | }
71 | ```
72 | 
73 | ### 3. Retrieve Task Results
74 | 
75 | ```bash
76 | curl -O https://pacman.cs.tsinghua.edu.cn/api/treekg/task_result/${task_id}
77 | ```


--------------------------------------------------------------------------------