🏆 #2,845 overall#347 of 407 in Search & Retrieval🔥 active this week

salikhussain71-code /PAKGOV-RAG-project

Research project on bilingual Urdu-English retrieval-augmented generation for Pakistani government and legal documents, with OCR, hybrid retrieval, citation grounding, and evaluation.

$ git clone https://github.com/salikhussain71-code/PAKGOV-RAG-project.git
GitHub social preview for salikhussain71-code/PAKGOV-RAG-project
Stars
130
130
Forks
7
7
Language
Python
License
MIT
Created
Sep 17, 2026
0.1 years old
Last push
Nov 7, 2026
🔥 this week

Categories

GitHub topics

More in Search & Retrieval

Search & Retrieval

cdqa-suite/cdQA

⛔ [NOT MAINTAINED] An End-To-End Closed Domain Question Answering System.

🧠 Natural Language Processing❓ Question Answering
PythonApache-2.0updated Apr 30, 2020
GitHub ↗★ 615⑂ 189
Search & Retrieval

SciPhi-AI/agent-search

AgentSearch is a framework for powering search agents and enabling customizable local search.

PythonApache-2.0updated Apr 22, 2024
GitHub ↗★ 566⑂ 55
Search & Retrieval

maxent-ai/ocrpy

OCR, Archive, Index and Search: Implementation agnostic OCR framework.

📄 OCR & Documents🧠 Natural Language Processing
Jupyter NotebookMITupdated Nov 3, 2023
GitHub ↗★ 225⑂ 11
Search & Retrieval

DataScienceUIBK/Rankify

🔥 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.

❓ Question Answering🧠 Natural Language Processing
Pythonno licenseupdated Sep 7, 2026
GitHub ↗★ 683⑂ 71
Search & Retrieval

ekimetrics/adaptive-chunking

Adaptive Chunking: automatically select the best chunking method per document for RAG. Accepted at LREC 2026.

🧠 Natural Language Processing
PythonMITupdated Jul 6, 2026
GitHub ↗★ 401⑂ 44
Search & Retrieval

UKPLab/gpl

Powerful unsupervised domain adaptation method for dense retrieval. Requires only unlabeled corpus and yields massive improvement: "GPL: Generative Pseudo Labeling for Unsupervised Domain Adaptation of Dense Retrieval" https://arxiv.org/abs/2112.07577

🧠 Natural Language Processing
PythonApache-2.0updated Jul 6, 2023
GitHub ↗★ 344⑂ 38

Data from GitHub · snapshot Nov 9, 2026