cdqa-suite/cdQA
⛔ [NOT MAINTAINED] An End-To-End Closed Domain Question Answering System.
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⛔ [NOT MAINTAINED] An End-To-End Closed Domain Question Answering System.
AgentSearch is a framework for powering search agents and enabling customizable local search.
OCR, Archive, Index and Search: Implementation agnostic OCR framework.
🔥 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.
Adaptive Chunking: automatically select the best chunking method per document for RAG. Accepted at LREC 2026.
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
Data from GitHub · snapshot Nov 9, 2026