Building a helpdesk chatbot with the Rasa ecosystem

Rasa Studio is very useful for no-code usage, but somewhat lagging behind Rasa Pro in features, which makes it hard to use it for development cycle of more complex chatbots (rating 7).

Rasa Pro and Rasa SDK provide quite transparent pro-code usage possibilities (rating 9), but there are some dependencies in the message processing, where we had to look for custom code/workarounds.
Rasa analytics could be more flexible, i.e. built without any dependency on Kafka event broker. That's why have built our own analytics, because we've had a custom SQL event broker. I'd give the Rasa ecosystem an overall rating of 8.

Rasa Pro is well suited for corporate use and for chatbots which require backend connections. Smaller chatbots with a few flows might be better served with a simple dialogue engine and custom AI agents, or Rasa Open Source. Rasa does not come with its own complex vector database, just in-memory FAISS and connectors to external vector DB's such as Milvus and Qdrant. It provides only a basic document parser and embedder for FAISS. If you need to build a RAG focused chatbot around a large knowledge base with complex documents, e.g. lots of MS Word or PDF files, you'll have to build a separate document parser and embedder, as well as your own semantic search engine.

Rasa support has been very responsive, trying to fix any reported issues ASAP. They've also listened to many requests for improvement. The Rasa features and changelog are well documented.