RAGChecker: A Fine-grained Framework For Diagnosing RAG
active 2024-06-26 → 2026-04-22 (UTC)
Activity over time
Daily event counts in the loaded window
Line chart, 666 days from 2024-06-26 to 2026-04-22. Pushes: 33 total, peak 6 in a day. Pull requests: 13 total, peak 2 in a day. Issues: 36 total, peak 3 in a day. Comments: 51 total, peak 6 in a day. Stars: 936 total, peak 41 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 |
|---|---|---|---|---|
| HuXiangkun | 42 | 22 | 5 | 13 |
| rudongyu | 22 | 11 | 2 | 6 |
| FRAMEEE17 | 5 | 0 | 0 | 3 |
| xiezhuojin | 5 | 0 | 0 | 1 |
| ss8319 | 5 | 0 | 0 | 2 |
| Impavidity | 3 | 0 | 0 | 2 |
| Martyniqo | 3 | 0 | 1 | 1 |
| alexlorenzo | 3 | 0 | 0 | 3 |
| liwan14x | 3 | 0 | 0 | 1 |
| leekum2018 | 2 | 0 | 0 | 1 |
| hoahoa1808 | 2 | 0 | 0 | 2 |
| yidasanqian | 2 | 0 | 0 | 0 |
| renesteeman | 2 | 0 | 0 | 0 |
| zhimin-z | 2 | 0 | 0 | 1 |
| qpwo2468 | 2 | 0 | 0 | 2 |
| Juanpa0128j | 2 | 0 | 0 | 2 |
| ytxmobile98 | 1 | 0 | 1 | 0 |
| shahules786 | 1 | 0 | 0 | 0 |
| SeanShi23333 | 1 | 0 | 0 | 0 |
| ulan-yisaev | 1 | 0 | 0 | 0 |
Recent activity
Latest issues, pull requests and releases
- Issue#37cventus2025-06-11 07:06CLI fails with Bedrock models unless
- Issue#36xiezhuojin2025-06-03 09:18I got different relevant noise sensitivity and irrelevant noise sensitivity result between ragchecker result and paper's formula.
- Issue#36xiezhuojin2025-05-30 04:22I got different relevant noise sensitivity and irrelevant noise sensitivity result between ragchecker result and paper's formula.
- Issue#35xiezhuojin2025-05-30 03:24import error on a docker python:3.12-slim image
- Issue comment#35xiezhuojin2025-05-20 03:01import error on a docker python:3.12-slim image
- Issue comment#34smatsumt2025-05-19 11:23Deprecation issue with the latest Transformers
- Issue comment#35AnoOoooo2025-05-16 00:30import error on a docker python:3.12-slim image
- Issue#35xiezhuojin2025-05-15 08:41import error on a docker python:3.12-slim image
- Issue#34AbhilashPal2025-05-09 12:14Deprecation issue with the latest Transformers
- Issue#33leekum20182025-05-05 16:27What are the backbone models used in the output file without suffix "llama3"in meta_evalutation?
- Issue comment#10leekum20182025-04-26 19:37Integration with OpenAI
- Issue#32SeanShi233332025-04-16 03:07pip install ragchecker fails with Python 3.13 – works with Python 3.12
- Issue#30jacky681475272025-03-28 09:17Better with LLM
- Issue#29RyosukeSakaguchi2025-03-24 03:29RAGChecker Metric Input Requirements and Missing Data Handling
- Issue#28renesteeman2025-03-20 13:34Dataclasses-json version restrictions leads to Flyte incompatibility
- Issue#28renesteeman2025-03-20 13:32Dataclasses-json version restrictions leads to Flyte incompatibility
- Issue comment#244715663422025-03-04 06:06scores for metrics is Different when executed multiple times
- Issue#26dropberry2025-02-21 11:24Differences in faithfulness metric
- Pull request#25ytxmobile982025-01-16 02:43
- Issue comment#20HuXiangkun2024-12-16 05:17Which metrics are adopted in meta-evaluation by ragchecker?
- Issue comment#24HuXiangkun2024-12-16 05:15scores for metrics is Different when executed multiple times
- Issue#24daiDai-study2024-12-16 03:00scores for metrics is Different when executed multiple times
- Pull request#22HuXiangkun2024-12-09 04:56
- Issue comment#22HuXiangkun2024-12-09 04:56bug: update generator metrics in tutorial
- Pull request#23HuXiangkun2024-12-09 02:25
Totals cover only the window loaded into ClickHouse and count events, not GitHub's lifetime totals — 936 stars here means stars gained during the window, not the repo's star count.