文档提取-85%价值率-将 PDF 等复杂文档转换为适合大模型处理的 Markdown/JSON 格式，以适配你的智能体工作流。Transforms complex documents like PDFs into LLM-ready markdown/JSON for your Agentic workflows.
Python · active 2025-04-06 → 2026-08-07 (UTC)
Activity over time
Daily event counts in the loaded window
Line chart, 489 days from 2025-04-06 to 2026-08-07. Pushes: 764 total, peak 26 in a day. Pull requests: 843 total, peak 33 in a day. Issues: 864 total, peak 34 in a day. Comments: 1,631 total, peak 35 in a day. Stars: 13,918 total, peak 376 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 |
|---|---|---|---|---|
| myhloli | 1.6K | 416 | 514 | 384 |
| dosubot[bot] | 421 | 0 | 195 | 216 |
| github-actions[bot] | 368 | 306 | 0 | 62 |
| Copilot | 324 | 0 | 3 | 213 |
| zhongguogu | 18 | 0 | 0 | 9 |
| Sidney233 | 16 | 0 | 16 | 0 |
| chatgpt-codex-connector[bot] | 16 | 0 | 0 | 10 |
| YamiZhao123 | 13 | 0 | 0 | 6 |
| Doge2077 | 12 | 0 | 2 | 4 |
| johnking0099 | 11 | 11 | 0 | 0 |
| Simonqujian78 | 10 | 0 | 0 | 8 |
| lc345 | 10 | 0 | 0 | 10 |
| lovetian1991 | 10 | 0 | 0 | 8 |
| LittleNoob2333 | 10 | 0 | 0 | 9 |
| zzk2021 | 9 | 0 | 0 | 5 |
| chaoStart | 9 | 0 | 0 | 5 |
| gaoxumustwin | 9 | 0 | 0 | 1 |
| userGuo-o | 9 | 0 | 0 | 4 |
| wakeup404 | 8 | 0 | 0 | 8 |
| seedclaimer | 8 | 0 | 0 | 5 |
Recent activity
Latest issues, pull requests and releases
- Issue comment#5369github-actions[bot]2026-08-07 17:31Fix docx page detection: also split on manual page breaks and pageBreakBefore
- Pull request#5369dosubot[bot]2026-08-07 17:31
- Pull request#5369AfroDeivid2026-08-07 17:31
- Issue comment#5335github-actions[bot]2026-07-28 03:07Trim process heap after document analysis
- Issue comment#5198xmuwenxiang2026-06-30 07:00Fix skewed PDF text backfill
- Issue#5199chaoStart2026-06-30 06:37解析一个大文件，中途想取消解析，不想等待，请问是否有相应的命令行或者函数
- Issue comment#5196myhloli2026-06-30 02:48Next with 3.3.1
- Issue comment#5197sun66762026-06-30 01:39feat: add async parse pause resume support
- Pull request#5197sun66762026-06-30 01:31
- Issue#5178zhou05522026-06-25 03:23识别时部分内容丢失
- Issue#5160myhloli2026-06-21 08:10pdf中的部分希腊字母没有识别出来，识别成了？？？
- Issue comment#4839975897132026-06-17 03:18升级到最新版之后，信息分块效果差了点
- Pull request#5134myhloli2026-06-17 03:12
- Issue comment#4839myhloli2026-06-17 03:06升级到最新版之后，信息分块效果差了点
- Issue comment#5120star202452026-06-17 00:40使用 k8s 在昇腾 910B3 上部署mineru 服务时，服务无法运行在指定卡 id 上
- Issue comment#5134myhloli2026-06-16 20:06Integrate PP-OCRv6 model and enhance OCR language handling
- Issue#5120xsj123-rgb2026-06-12 01:42使用 k8s 在昇腾 910B3 上部署mineru 服务时，服务无法运行在指定卡 id 上
- Issue comment#5100eastyu2026-06-09 14:47海光k100 使用hybrid-auto-engine解析后端，显存不释放
- Issue#5093dosubot[bot]2026-06-08 01:49Task 006: Artifact-First Result Contract
- Issue#5093ErixWong2026-06-08 01:47Task 006: Artifact-First Result Contract
- Issue#5074myhloli2026-06-04 03:09vllm 推理表格任务，会切分的很乱，但是transformers是正常的
- Issue comment#5052github-actions[bot]2026-05-31 21:29feat: add optional external VLM visual details enrichment
- Pull request#5052dosubot[bot]2026-05-31 21:29
- Issue comment#5045zeweihan2026-05-30 08:58exited with code 139 段错误
- Issue comment#5045dosubot[bot]2026-05-30 08:17exited with code 139 段错误
Totals cover only the window loaded into ClickHouse and count events, not GitHub's lifetime totals — 13,918 stars here means stars gained during the window, not the repo's star count.