# NVIDIA/ChatRTX

A developer reference project for creating Retrieval Augmented Generation (RAG) chatbots on Windows using TensorRT-LLM

Repository: https://github.com/NVIDIA/ChatRTX
Canonical: https://ross.abutalabs.com/products/chatrtx
Language: Python
License: NOASSERTION
License Family: other
Archived: true
Last push: 2026-01-21T07:16:58+00:00

## Health v2 (maintenance only)
Score: 10/100 (v2, computed 2026-09-02T17:46:02.011165+00:00)
- activity 63, release rhythm 35, longevity 75
- inputs: {"age_days": 1050, "days_push": 224, "days_rel": null, "gap_med": null, "n_releases_24m": 0}
- flags: no_releases, archived, no_license
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 3121, forks 430 (observed 2026-08-28T04:07:44.286777+00:00)

## What it is
ChatRTX is a Windows demo application for building personalized RAG chatbots on local RTX GPUs using TensorRT-LLM, NVIDIA NIM, and LlamaIndex. It lets users query their own documents (text, PDF, DOCX, images) with LLMs and supports voice input via Whisper or Riva Parakeet.

## Use cases
- chat with my own documents locally on windows
- build a rag chatbot on an rtx gpu
- query pdfs and notes with a local llm
- run tensorrt-llm inference on personal files
- voice-query a local ai assistant
- search images and docs with clip and llm

## When to choose
- you want a reference implementation of RAG on Windows with TensorRT-LLM
- you have a supported NVIDIA RTX GPU and want fully local, private document Q&A
- you want to study how to integrate NIM, LlamaIndex, and FAISS into a chatbot pipeline

## When to avoid
- you need a maintained or production-ready product - the project was deprecated in January 2026
- you don't have a compatible NVIDIA RTX GPU
- you need Linux, macOS, or cloud deployment
- you want multi-user or server-side RAG rather than a local demo

## Facets
- artifact type: application
- maturity: abandoned
- function: rag, llm-inference, chatbot, speech-recognition, search-engine
- domain: large-language-models, chatbots, artificial-intelligence, windows
- platform: windows, python
- tags: tensorrt-llm, nvidia-nim, llamaindex, faiss, local-llm, deprecated, rtx, voice-input, demo-app, retrieval-augmented-generation, gpu, desktop

## Member repositories
- NVIDIA/ChatRTX (main) score 10

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:07:44.286777+00:00.
- Health v2: computed from the inputs above; adoption is never an input.
- Inferred fields (summary, facets, guidance): AI-extracted, prompt v1, taxonomy v1, on 2026-08-30T07:26:36.827266+00:00, confidence not recorded.
  - readme: https://github.com/NVIDIA/ChatRTX (fetched 2026-08-28T04:07:44.286777+00:00, sha 7ac903b3c979)
- Data as of 2026-08-30T08:39:29.467469+00:00.