RasaGPT

Overview of RasaGPT

What it is

RasaGPT is a headless LLM chatbot platform built on top of Rasa and Langchain. It serves as boilerplate and a reference implementation of Rasa and Telegram using an LLM library like Langchain for indexing, retrieval and context injection. The project is open source and licensed under MIT.

Key features

• LLM learns on an arbitrary corpus of data using Langchain - Upload documents and train via FastAPI - Document versioning and automatic re-training on upload - Custom async endpoints and database models via FastAPI and SQLModel - Bot determines whether human handoff is necessary - Bot generates tags based on user questions and responses automatically - Full API documentation via Swagger and Redoc - Embedding similarity search via pgvector and Postgres functions - Multi-tenancy support, sessions, and metadata between Rasa and backend - Supports Telegram; can integrate Slack, WhatsApp, Line, SMS, etc.
• Extend agentic and memory capabilities with Langchain

Use cases

RasaGPT can be used for help desk, customer support, quizzes, e-learning, dungeon and dragons, and other conversational AI applications that require a headless LLM chatbot integrated with Rasa and Telegram.

Getting started

bash git clone https://github.com/paulpierre/RasaGPT.git cd RasaGPT cp .env-example .env # Edit your .env file and add all the necessary credentials make install

License and pricing

The project is open source under the MIT license. Pricing type is open_source.

Based on the project's public README and repository metadata.