RasaGPT is a headless chatbot platform that combines Rasa with modern LLM tooling such as Langchain and LlamaIndex. It serves as a reference implementation and boilerplate for building conversational AI systems with retrieval and context injection. RasaGPT includes a FastAPI backend for creating custom bot endpoints, along with document ingestion and a training pipeline. It simplifies integration challenges between Rasa and LLM libraries, including metadata handling and library conflicts. RasaGPT supports multi-tenant deployments, session management, and custom schemas using pgvector. It also enables Telegram bot integration and remote access via ngrok. Docker support allows easier setup and deployment, particularly on macOS environments. While designed as a working prototype, it provides a practical foundation for developers building LLM-powered chatbot applications with extensible architecture and preconfigured components.
Features
- Headless chatbot framework combining Rasa with LLM tools
- FastAPI backend for custom bot endpoints and APIs
- Built-in document ingestion and training pipeline
- Integration with Langchain, LlamaIndex, and pgvector
- Multi-tenancy, session handling, and metadata support
- Dockerized setup with Telegram and ngrok integration