This project provides a minimalistic, offline-capable React UI for interacting with local Large Language Models (LLMs) via Ollama. It targets users who want an improved chatbot experience for local models, offering features like model toggling, conversation history, and prompt templating.

How It Works

The UI is built with React, Next.js, and Tailwind CSS for a modern frontend. It leverages LangchainJs and Ollama to connect to and manage local LLMs. Conversations and context are stored in memory for seamless model switching, and a local database persists chat history.

Quick Start & Requirements

• Install dependencies: npm install
• Run the UI: npm run dev
• Requires Node.js version 14.0.1 or higher.
• Ollama must be installed and running (defaulting to http://localhost:11434).
• Custom Ollama API base URL can be configured via .env.local.
• Official Docs: [Not explicitly linked, but project structure implies standard Next.js setup]

Highlighted Details

• Real-time chat with local LLMs.
• Seamless model toggling, even mid-conversation.
• Memory-based context storage for smooth interactions.
• Local database for saving and revisiting conversation history.
• Parameter-driven prompt templating for reusability.

Maintenance & Community

• No specific contributors, sponsorships, or community links (Discord/Slack) are mentioned in the README.

Licensing & Compatibility

• MIT License. Permissive for commercial use and closed-source linking.

Limitations & Caveats

The project is under active development with several features planned, including message editing, image uploads for multimodal models, conversation summarization, and desktop app conversion.