[riter]

Unfortunately there were not a whole lot of end-to-end examples of integrating Rasa with OpenAI nor functional boilerplates on github so I put a working prototype together in a few days and thus RasaGPT was bron.

RasaGPT is a python-based boilerplate and reference implementation of Rasa and Telegram utilizing an LLM library like Langchain for indexing, retrieval and context injection. FastAPI end-points are made available for you to build your application on top of. Features include:

- Automated hand-off to human if queries are out of bounds - "Training" pipeline done via API - Multi-tenant support - Generate category labels from questions - Works right out of the box with docker-compose - Ngrok reverse tunnel and dummy data included - Multiple use cases and a great starting point

Hope you like it, more @ rasagpt.dev

[contravariant]

I haven't worked with Rasa so I was wondering if I understood things correctly.

Are you using a language model to look up the correct reply to a particular response inside Rasa? Where Rasa presumably connects to some kind of backend to retrieve information or 'do stuff'?

[riter]

thanks for asking.

this implementation leverages Rasa and stands up a FastAPI server where it receives the user response webhook first and gets processed by (or bypasses) Rasa.

The LLM queries a set of documents indexed by Langchain. Dummy data has been included (Pepe Corp.)

Rasa has support for a "fallback" mechanism whereby if a user's response scores low on your pre-configured Rasa intents (like Greet) you can have it route directly to the LLM as well. But for now RasaGPT capture and routes the Telegram response to the FastAPI webhook endpoint.

the LLM itself and prompts I configured provides a boolean on whether the response should be escalated to a human or not, based on LLM+Langchain not knowing the answer to the user's query from the indexed documents.

I hope that answers your question, if not happy to follow-up!