tools:chat
Translate:

RTI Wiki AI — Free, Private, Open Source

Tool not loading? Open directly at /tools/chat-app.html.

What this is

An RTI Wiki AI — chat about the RTI Act, 2005 that runs entirely in your browser. Ask questions in plain English — fees, timelines, grounds for refusal, case law, appeal procedure, state-specific rules, DPDP amendments — and the chatbot answers. Free as of now. No sign-up. No API key. No data leaves your device.

How it works

  1. You pick an open-source model size (330 MB fastest, 720 MB balanced, 1.8 GB best).
  2. First use downloads the model once (cached in your browser).
  3. You type a question.
  4. The model runs on your device's GPU via WebGPU and streams an answer.
  5. The chat remembers the last few turns for context.

The model is primed with the RTI Act framework — all 10 grounds of rejection, §19 appeals, §20 penalties, key sections, post-DPDP-2025 amendments, and 10+ landmark Supreme Court / High Court cases — before your question ever reaches it.

What it is NOT

  • Not legal advice. A 1-3 billion parameter model can be wrong. Cross-check with statutory text and the curated pages.
  • Not up-to-the-minute. The model's prior knowledge is from its training date; for the latest rules, check our blog.
  • Not a document-aware assistant yet. Phase 2 (coming) will add retrieval-augmented generation over all 300+ pages of this site.

Requirements

  • WebGPU — Chrome 113+, Edge, or any WebGPU-capable browser. Safari / Firefox support is experimental.
  • First run download — 330 MB to 1.8 GB depending on model choice. One-time; cached thereafter.

Privacy

  • The question you type never leaves your browser.
  • The model weights come from a public CDN (HuggingFace via WebLLM), but only once — cached afterwards.
  • No tracking, no analytics, no logging of your questions on our side.

Attribution

Sources

  • Right to Information Act, 2005 (as amended 2019, 2023)
  • Digital Personal Data Protection Act, 2023 — §44(3)
  • Meta Llama 3.2 community licence; Alibaba Qwen 2.5; MLC AI; WebLLM (Apache-2.0)

Last reviewed: 21 April 2026.

Discussion

Enter your comment:
 
Share this article
Was this helpful? views
tools/chat.txt · Last modified: by 127.0.0.1