冗长的 DDL 输入在现实应用程序中很常见。为了解决这个问题，一种有效的方法是实施一个预处理模块，该模块根据自然语言问题提取最相关的表和列。该技术可以显着减少输入序列的总长度，从而提高效率。 结合 sqlcoder-7b-2
active 2023-08-28 → 2026-03-07 (UTC)
Activity over time
Daily event counts in the loaded window
Line chart, 923 days from 2023-08-28 to 2026-03-07. Pushes: 15 total, peak 3 in a day. Pull requests: 0 total, peak 0 in a day. Issues: 63 total, peak 6 in a day. Comments: 82 total, peak 8 in a day. Stars: 194 total, peak 5 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 |
|---|---|---|---|---|
| lihaoyang-ruc | 82 | 15 | 0 | 44 |
| dshwei | 17 | 0 | 0 | 8 |
| steph730 | 8 | 0 | 0 | 5 |
| shellhuang1227 | 5 | 0 | 0 | 4 |
| kanseaveg | 5 | 0 | 0 | 3 |
| zzkzzkjsw | 4 | 0 | 0 | 2 |
| LJHzju | 3 | 0 | 0 | 2 |
| Saraaqzs | 3 | 0 | 0 | 1 |
| lwmlyy | 3 | 0 | 0 | 1 |
| Kaimary | 3 | 0 | 0 | 1 |
| ddingwang12 | 3 | 0 | 0 | 1 |
| ChinaStark | 3 | 0 | 0 | 2 |
| CycloneBoy | 2 | 0 | 0 | 2 |
| ruilinWho | 2 | 0 | 0 | 0 |
| MainSuper | 2 | 0 | 0 | 1 |
| Mucalinda2436 | 2 | 0 | 0 | 1 |
| Yhw109 | 2 | 0 | 0 | 1 |
| lazyfuzzyguy | 2 | 0 | 0 | 0 |
| binz98 | 1 | 0 | 0 | 0 |
| ArthurChen189 | 1 | 0 | 0 | 0 |
Recent activity
Latest issues, pull requests and releases
Totals cover only the window loaded into ClickHouse and count events, not GitHub's lifetime totals — 194 stars here means stars gained during the window, not the repo's star count.