Official repo for "LongRAG: Enhancing Retrieval-Augmented Generation with Long-context LLMs".
active 2024-06-20 → 2026-04-10 (UTC)
Activity over time
Daily event counts in the loaded window
Line chart, 660 days from 2024-06-20 to 2026-04-10. Pushes: 84 total, peak 63 in a day. Pull requests: 2 total, peak 2 in a day. Issues: 8 total, peak 1 in a day. Comments: 11 total, peak 5 in a day. Stars: 232 total, peak 35 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 |
|---|---|---|---|---|
| XMHZZ2018 | 92 | 83 | 0 | 7 |
| gw16 | 5 | 0 | 0 | 2 |
| tyu008 | 3 | 0 | 0 | 2 |
| wenhuchen | 2 | 1 | 1 | 0 |
| acphile | 1 | 0 | 0 | 0 |
| zhoumengbo | 1 | 0 | 0 | 0 |
| AgainstEntropy | 1 | 0 | 1 | 0 |
Recent activity
Latest issues, pull requests and releases
- Issue#7zhoumengbo2024-12-11 05:14Does it support testing a single PDF file?
- Issue#6acphile2024-11-20 01:23Bad performance for running run_retrieve_tevatron.sh
- Issue comment#4XMHZZ20182024-08-29 23:27Question about process_wiki_page.py
- Pull request#5wenhuchen2024-08-25 20:33
- Pull request#5AgainstEntropy2024-08-25 04:15
- Issue#4gw162024-08-16 06:56Question about process_wiki_page.py
- Issue comment#3tyu0082024-08-10 16:58Could not reproduce the answer recall for NQ dataset
- Issue comment#3XMHZZ20182024-08-10 06:41Could not reproduce the answer recall for NQ dataset
- Issue#2XMHZZ20182024-08-10 03:35Question for retrieve_tevatron.sh.
- Issue comment#3tyu0082024-08-10 03:29Could not reproduce the answer recall for NQ dataset
- Issue comment#2XMHZZ20182024-08-10 02:56Question for retrieve_tevatron.sh.
- Issue comment#3XMHZZ20182024-08-10 02:51Could not reproduce the answer recall for NQ dataset
- Issue#3tyu0082024-08-09 23:10Could not reproduce the answer recall for NQ dataset
- Issue#2gw162024-07-16 09:23Question for retrieve_tevatron.sh.
- Issue#1XMHZZ20182024-07-09 18:32what is corpus_title_set in preprocess/process_wiki_page.py ?
- Issue comment#1XMHZZ20182024-07-09 00:49what is corpus_title_set in preprocess/process_wiki_page.py ?
- Issue comment#1gw162024-07-09 00:36what is corpus_title_set in preprocess/process_wiki_page.py ?
- Issue comment#1XMHZZ20182024-07-08 23:57what is corpus_title_set in preprocess/process_wiki_page.py ?
- Issue comment#1gw162024-07-08 23:42what is corpus_title_set in preprocess/process_wiki_page.py ?
- Issue comment#1XMHZZ20182024-07-08 14:20what is corpus_title_set in preprocess/process_wiki_page.py ?
- Issue#1gw162024-07-08 07:33what is corpus_title_set in preprocess/process_wiki_page.py ?
Totals cover only the window loaded into ClickHouse and count events, not GitHub's lifetime totals — 232 stars here means stars gained during the window, not the repo's star count.