BNS Law RAG DB: Text Corpus for New Indian Criminal Laws

Hrutik2003/Bns_Law_Rag_DB is a cleaned and processed text corpus extracted from new Indian criminal laws introduced in 2023, including the Bharatiya Nyaya Sanhita (BNS), Bharatiya Nagarik Suraksha Sanhita (BNSS), and Bharatiya Sakshya Adhiniyam (BSA), as well as older laws like the Indian Penal Code (IPC) and Code of Criminal Procedure (CrPC). The dataset was created by author Hrutik2003 and was last updated on November 13, 2025. Its primary purpose is to serve as a knowledge base for Retrieval-Augmented Generation (RAG) systems.

Use Cases

• Building legal question-answering systems based on the text corpus of new Indian criminal laws.
• Training or fine-tuning language models for legal document understanding based on the processed IPC and CrPC text.
• Developing comparative analysis tools for legal changes based on the inclusion of both new 2023 laws and older statutes.
• Creating information retrieval systems for legal professionals based on the structured text corpus.

Strengths

• Focuses on a specific and timely domain: the new Indian criminal laws enacted in 2023.
• Includes both new legislation (BNS, BNSS, BSA) and foundational older laws (IPC, CrPC) for context.
• Text has been cleaned and processed specifically for RAG system compatibility.

Limitations

• Column-level documentation is absent; field semantics must be inferred after download.
• Row count, file formats, and dataset size are unknown, which may limit suitability assessment.
• License information is unknown, which could restrict commercial or research use.

Provenance

Source

Text extracted from official Indian criminal laws.

Collection Method

Cleaned and processed text extraction, method details unspecified.

Time Range

Laws introduced in 2023, alongside older statutes.

Freshness

Last updated 2025-11-13 16:18:23; freshness should be verified.

Geography

India