Bolnee-Chat is a newly released self-hosted RAG (Retrieval Augmented Generation) chatbot platform designed for business website integration. The platform allows users to deploy and manage chatbots on their own infrastructure, offering control over data and operations.
The system enables chatbots to answer questions based on specific knowledge sources, including website content and uploaded PDF documents. It supports integration with various OpenAI-compatible large language model (LLM) providers such as OpenAI, OpenRouter, Groq, Ollama, and vLLM, allowing users to choose their preferred model.
Bolnee-Chat stores all data, including visitor chats and knowledge chunks, in a local SQLite database. Provider API keys are encrypted using AES-256-GCM. Integration into a website is achieved by embedding a two-line JavaScript snippet. The platform also includes features like knowledge management, avatar file storage, and a dark-mode console for administration.
Installation involves cloning the GitHub repository, configuring environment variables, and running npm commands for setup. Users can add knowledge sources by providing website URLs or uploading documents like PDFs, TXT, MD, DOCX, or FAQ files. Chatbot configuration includes selecting an LLM provider and model, with encrypted key storage ensuring security.
✨ This summary was generated by AI from the outlets' reporting listed below. It is not independently verified and may contain errors — check the original sources. How BrevFeed works →
One email each morning: the day's tech stories, clustered across outlets and summarized. No account needed.
One email a day. Unsubscribe in one click, any time.
Spend a few minutes, get the whole day. Every topic's top stories in one hands-free rundown — listen, watch, or read the transcript.
▶ Play today's briefNew every morning, and the back catalogue is archived by date.
Bolnee-Chat is a new self-hosted RAG chatbot platform that allows businesses to integrate AI chatbots into their websites using their own infrastructure. It enables grounding answers in provided sources like websites and PDFs, and supports various OpenAI-compatible LLM providers.