Add chat-llama-nemotron example as a regular directory

community/README.md

@@ -82,4 +82,8 @@ Community examples are sample code and deployments for RAG pipelines that are no
 
 * [AI Podcast Assistant](./ai-podcast-assistant/)
 
-  This example demonstrates a comprehensive workflow for processing podcast audio using the Phi-4-Multimodal LLM through NVIDIA NIM Microservices. It includes functionality for generating detailed notes from audio content, creating concise summaries, and translating both transcriptions and summaries into different languages. The implementation handles long audio files by automatically chunking them for efficient processing and preserves formatting during translation.
+  This example demonstrates a comprehensive workflow for processing podcast audio using the Phi-4-Multimodal LLM through NVIDIA NIM Microservices. It includes functionality for generating detailed notes from audio content, creating concise summaries, and translating both transcriptions and summaries into different languages. The implementation handles long audio files by automatically chunking them for efficient processing and preserves formatting during translation.
+
+* [Chat with LLM Llama 3.1 Nemotron Nano 4B](./chat-llama-nemotron/)
+
+  This is a React-based conversational UI designed for interacting with a powerful local LLM. It incorporates RAG to enhance contextual understanding and is backed by an NVIDIA Dynamo inference server running the NVIDIA Llama-3.1-Nemotron-Nano-4B-v1.1 model. The setup enables low-latency, cloud-free AI assistant capabilities, with live document search and reasoning, all deployable on local or edge infrastructure.

community/chat-llama-nemotron/.gitignore

@@ -0,0 +1,156 @@
+# Dependencies
+node_modules/
+.pnp/
+.pnp.js
+package-lock.json
+yarn.lock
+
+# Testing
+coverage/
+.nyc_output/
+test-results/
+junit.xml
+
+# Production
+build/
+dist/
+out/
+.next/
+.nuxt/
+.cache/
+.output/
+
+# Environment files
+.env
+.env.*
+!.env.example
+.env.local
+.env.development.local
+.env.test.local
+.env.production.local
+.env*.local
+*.env
+
+# Logs
+npm-debug.log*
+yarn-debug.log*
+yarn-error.log*
+logs/
+*.log
+debug.log
+error.log
+
+# IDE
+.idea/
+.vscode/
+*.swp
+*.swo
+*.sublime-workspace
+*.sublime-project
+.project
+.classpath
+.settings/
+*.code-workspace
+
+# OS
+.DS_Store
+Thumbs.db
+desktop.ini
+$RECYCLE.BIN/
+*.lnk
+
+# Python
+__pycache__/
+*.py[cod]
+*$py.class
+*.so
+.Python
+env/
+venv/
+ENV/
+.env/
+.venv/
+pip-log.txt
+pip-delete-this-directory.txt
+.tox/
+.coverage
+.coverage.*
+.cache
+nosetests.xml
+coverage.xml
+*.cover
+*.py,cover
+.hypothesis/
+.pytest_cache/
+.python-version
+*.egg-info/
+.installed.cfg
+*.egg
+MANIFEST
+dist/
+build/
+eggs/
+parts/
+bin/
+var/
+sdist/
+develop-eggs/
+.installed.cfg
+lib/
+lib64/
+
+# RAG specific
+data/
+embeddings/
+*.faiss
+*.pkl
+*.bin
+*.vec
+*.model
+*.index
+chunks/
+documents/
+vectors/
+corpus/
+indexes/
+
+# Temporary files
+*.tmp
+*.temp
+*.bak
+*.swp
+*~
+*.swx
+*.swo
+*.swn
+*.bak
+*.orig
+*.rej
+*.patch
+*.diff
+
+# Build artifacts
+*.min.js
+*.min.css
+*.map
+*.gz
+*.br
+*.zip
+*.tar
+*.tar.gz
+*.tgz
+*.rar
+*.7z
+
+# Debug
+.debug/
+debug/
+debug.log
+npm-debug.log*
+yarn-debug.log*
+yarn-error.log*
+
+# Local development
+.local/
+local/
+local.* 

community/chat-llama-nemotron/README.md

@@ -0,0 +1,135 @@
+# Chat with Llama-3.1-Nemotron-Nano-4B-v1.1
+
+A React-based chat interface for interacting with an LLM, featuring RAG (Retrieval-Augmented Generation) capabilities and NVIDIA Dynamo backend serving NVIDIA Llama-3.1-Nemotron-Nano-4B-v1.1.
+
+## Project Structure
+
+```
+.
+├── frontend/           # React frontend application
+├── backend-rag/        # RAG service backend
+└── backend-dynamo/     # NVIDIA Dynamo backend service
+    └── llm-proxy/      # Proxy server for NVIDIA Dynamo
+```
+
+## Prerequisites
+
+- Node.js 18 or higher
+- Python 3.8 or higher
+- NVIDIA GPU with CUDA support (for LLM serving with NVIDIA Dynamo)
+- Docker (optional, for containerized deployment)
+- Git
+
+## Configuration
+
+### Frontend
+
+The frontend configuration is managed through YAML files in `frontend/public/config/`:
+
+- `app_config.yaml`: Main application configuration:
+  - API endpoints
+  - UI settings
+  - File upload settings
+
+See [frontend/README.md](frontend/README.md)
+
+### Backend
+
+Each service has its own configuration files:
+
+- RAG backend: see [backend-rag/README.md](backend-rag/README.md)
+- LLM Proxy: see [backend-dynamo/llm-proxy/README.md](backend-dynamo/llm-proxy/README.md)
+- DynamoDB backend: see [backend-dynamo/README.md](backend-dynamo/README.md)
+
+
+## Setup
+
+### Llama-3.1-Nemotron-Nano-4B-v1.1 running on a GPU Server
+
+This step should be performed on a machine with a GPU.
+
+Set NVIDIA Dynamo backend running Llama-3.1-Nemotron-Nano-4B-v1.1 following the instruction [backend-dynamo/README.md](backend-dynamo/README.md).
+
+### Local client with a local RAG database
+
+These steps can be performed locally and don't require a GPU.
+
+1. Clone the repository:
+   ```bash
+   git clone <this-repository-url>
+   cd react-llama-client
+   ```
+
+2. Install frontend dependencies:
+   ```bash
+   cd frontend
+   npm install
+   ```
+
+3. Set up backend services:
+
+   For Unix/macOS:
+   ```bash
+   # RAG Backend
+   cd backend-rag
+   python -m venv venv
+   source venv/bin/activate
+   pip install -r requirements.txt
+
+   # LLM Proxy
+   cd backend-dynamo/llm-proxy
+   python -m venv venv
+   source venv/bin/activate
+   pip install -r requirements.txt
+   ```
+
+   For Windows:
+   ```bash
+   # RAG Backend
+   cd backend-rag
+   python -m venv venv
+   .\venv\Scripts\activate
+   pip install -r requirements.txt
+
+   # LLM Proxy
+   cd backend-dynamo\llm-proxy
+   python -m venv venv
+   .\venv\Scripts\activate
+   pip install -r requirements.txt
+   ```
+
+4. Start the services (each in a new terminal):
+
+   For Unix/macOS:
+   ```bash
+   # Start frontend (in frontend directory)
+   cd frontend
+   npm start
+
+   # Start RAG backend (in backend-rag directory)
+   cd backend-rag
+   source venv/bin/activate
+   python src/app.py
+
+   # Start LLM proxy (in backend-dynamo/llm-proxy directory)
+   cd backend-dynamo/llm-proxy
+   source venv/bin/activate
+   python proxy.py
+   ```
+
+   For Windows:
+   ```bash
+   # Start frontend (in frontend directory)
+   cd frontend
+   npm start
+
+   # Start RAG backend (in backend-rag directory)
+   cd backend-rag
+   .\venv\Scripts\activate
+   python src\app.py
+
+   # Start LLM proxy (in backend-dynamo\llm-proxy directory)
+   cd backend-dynamo\llm-proxy
+   .\venv\Scripts\activate
+   python proxy.py
+   ```

community/chat-llama-nemotron/backend-dynamo/.gitignore

@@ -0,0 +1,43 @@
+# Python
+__pycache__/
+*.py[cod]
+*$py.class
+*.so
+.Python
+env/
+venv/
+ENV/
+.env/
+.venv/
+pip-log.txt
+pip-delete-this-directory.txt
+.tox/
+.coverage
+.coverage.*
+.cache
+nosetests.xml
+coverage.xml
+*.cover
+*.py,cover
+.hypothesis/
+.pytest_cache/
+
+# Logs
+logs/
+*.log
+
+# IDE
+.idea/
+.vscode/
+*.swp
+*.swo
+
+# Environment variables
+.env
+.env.local
+.env.*.local
+
+# AWS
+.aws/
+aws.json
+credentials.json