🔥 Rankify: A Comprehensive Python Toolkit for Retrieval, Re-Ranking, and Retrieval-Augmented Generation 🔥. Our toolkit integrates 40 pre-retrieved benchmark datasets and supports 7+ retrieval techniques, 24+ state-of-the-art Reranking models, and multiple RAG methods.
active 2025-05-08 → 2025-08-28 (UTC)
Activity over time
Daily event counts in the loaded window
Line chart, 113 days from 2025-05-08 to 2025-08-28. Pushes: 52 total, peak 7 in a day. Pull requests: 0 total, peak 0 in a day. Issues: 48 total, peak 13 in a day. Comments: 7 total, peak 2 in a day. Stars: 0 total, peak 0 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 |
|---|---|---|---|---|
| aherzinger | 106 | 51 | 0 | 7 |
Recent activity
Latest issues, pull requests and releases
- Issue comment#29aherzinger2025-08-20 16:20Write documentation
- Issue comment#8aherzinger2025-08-16 19:54Implement Prompt Compression (Simple Version)
- Issue#8aherzinger2025-08-16 19:54Implement Prompt Compression (Simple Version)
- Issue#30aherzinger2025-08-16 19:53Test out React prompting
- Issue#31aherzinger2025-08-15 16:07Evaluate RAG methods
- Issue#30aherzinger2025-08-15 16:06Test out React prompting
- Issue#29aherzinger2025-08-15 16:05Write documentation
- Issue#27aherzinger2025-07-15 13:23Fix Self-consistency only returning lowercase answer in majority vote
- Issue comment#12aherzinger2025-07-15 13:14Consider which other metrics could be useful for given Method
- Issue#12aherzinger2025-07-15 13:14Consider which other metrics could be useful for given Method
- Issue#26aherzinger2025-07-10 11:12Fix Broken/not optimally working RAG methods
- Issue comment#14aherzinger2025-07-10 07:16Research about more prompting techniques which could be included
- Issue#14aherzinger2025-07-10 07:16Research about more prompting techniques which could be included
- Issue#25aherzinger2025-06-16 18:44Look into implementing ReACT
- Issue#17aherzinger2025-06-14 14:44Include mutliple examples for different kinds of RAG-methods with different models
- Issue#9aherzinger2025-06-14 14:42Implement Self-Consistency Sampling
- Issue#5aherzinger2025-06-14 11:44Implement Zero-Shot RAG
- Issue#6aherzinger2025-06-14 11:44Implement Naive RAG
- Issue#24aherzinger2025-06-13 11:01Enable user to use custom_prompts instead of template
- Issue#23aherzinger2025-06-13 09:34Flexible & Solid Prompt Templates for Different Model Types
- Issue#22aherzinger2025-06-10 12:11Create Setup for testing different prompts
- Issue#21aherzinger2025-05-28 12:35Update Readme
- Issue#21aherzinger2025-05-21 20:10Update Readme
- Issue#20aherzinger2025-05-17 13:31Include VLLM as a Backend
- Issue comment#19aherzinger2025-05-17 13:31Include liteLLM as a backend
Totals cover only the window loaded into ClickHouse and count events, not GitHub's lifetime totals — 0 stars here means stars gained during the window, not the repo's star count.