HtmlRAG: HTML is Better Than Plain Text for Modeling Retrieval Results in RAG Systems (WWW 2025)
active 2024-11-05 → 2026-04-18 (UTC)
Activity over time
Daily event counts in the loaded window
Line chart, 530 days from 2024-11-05 to 2026-04-18. Pushes: 29 total, peak 4 in a day. Pull requests: 0 total, peak 0 in a day. Issues: 47 total, peak 5 in a day. Comments: 62 total, peak 6 in a day. Stars: 418 total, peak 61 in a day.
- Pushes
- Pull requests
- Issues
- Comments
- Stars
Stars, PRs, issues and forks are under-captured in the later part of this window. GH Archive progressively stopped capturing non-push events during 2026 — −95% or worse by the end of the window. Every series here except Pushes fades for that reason, so a decline above reflects the archive, not this repository. Pushes stay reliable throughout, so read them, and the contributor counts derived from them, as the real signal. Data health has the measurements.
Top contributors
Pushes, PRs, issues, reviews and comments — stars and forks excluded, so this is contribution rather than popularity
| Contributor | Contributions | Pushes | PRs | Comments |
|---|---|---|---|---|
| plageon | 87 | 29 | 0 | 37 |
| Morning-Z | 13 | 0 | 0 | 6 |
| LinXin04 | 12 | 0 | 0 | 9 |
| oreo34567 | 6 | 0 | 0 | 3 |
| dev-wenjie | 4 | 0 | 0 | 3 |
| jesenzhang | 4 | 0 | 0 | 2 |
| andygoosh | 3 | 0 | 0 | 1 |
| zhimin-z | 2 | 0 | 0 | 1 |
| sliontc | 1 | 0 | 0 | 0 |
| heyikou | 1 | 0 | 0 | 0 |
| Fujiaoji | 1 | 0 | 0 | 0 |
| wzy-2020 | 1 | 0 | 0 | 0 |
| metoto | 1 | 0 | 0 | 0 |
| JarvisUSTC | 1 | 0 | 0 | 0 |
| ChantalMP | 1 | 0 | 0 | 0 |
Recent activity
Latest issues, pull requests and releases
- Issue comment#23plageon2025-09-11 07:37作为HTML翻译任务的可能性
- Issue#22Fujiaoji2025-07-08 19:16Do you remove the logo from the HTML during cleaning?
- Issue comment#21plageon2025-05-20 02:42基于生成模型的剪枝需要训练吗？
- Issue#21plageon2025-05-20 02:42基于生成模型的剪枝需要训练吗？
- Issue comment#20plageon2025-05-20 02:41htmlRAG可以仅仅只用于创建知识库么？
- Issue#20plageon2025-05-20 02:41htmlRAG可以仅仅只用于创建知识库么？
- Issue#21LinXin042025-05-19 13:51基于生成模型的剪枝需要训练吗？
- Issue#20metoto2025-04-18 07:25htmlRAG可以仅仅只用于创建知识库么？
- Issue comment#19oreo345672025-04-11 07:06can't run tree_rerank_tree_gen.py
- Issue comment#19plageon2025-04-11 06:04can't run tree_rerank_tree_gen.py
- Issue comment#19oreo345672025-04-11 05:49can't run tree_rerank_tree_gen.py
- Issue comment#19plageon2025-04-11 05:47can't run tree_rerank_tree_gen.py
- Issue#19oreo345672025-04-11 05:08can't run tree_rerank_tree_gen.py
- Releaseplageon2025-01-16 08:57v0.1.1
- Issue comment#18plageon2025-01-14 09:41How to parse url into html text?
- Issue#18heyikou2025-01-14 09:31How to parse url into html text?
- Issue#17plageon2025-01-04 10:53cannot install the package due to dependency conflict...
- Releaseplageon2025-01-02 06:57v0.0.6
- Issue comment#17plageon2024-12-30 15:06cannot install the package due to dependency conflict...
- Issue comment#17zhimin-z2024-12-30 11:07cannot install the package due to dependency conflict...
- Issue#17plageon2024-12-30 02:55cannot install the package due to dependency conflict...
- Issue comment#17plageon2024-12-30 02:55cannot install the package due to dependency conflict...
- Issue#17plageon2024-12-30 02:55cannot install the package due to dependency conflict...
- Issue#17zhimin-z2024-12-27 13:56cannot install the package due to dependency conflict...
- Issue#16oreo345672024-12-26 06:44can't calculate block rankings with Generative model
Totals cover only the window loaded into ClickHouse and count events, not GitHub's lifetime totals — 418 stars here means stars gained during the window, not the repo's star count.