rasa VS botman

Right before LLMs broke into the scene we had a few techniques I was aware of:

* Personality Forge uses a rules-based scripting approach [0]. This is basically ELIZA extended to take advantage of modern processing power.

* Rasa [1] used traditional NLP/NLU techniques and small-model ML to match intents and parse user requests. This is the same kind of tooling that Google/Alexa historically used, just without the voice layer and with more effort to keep the context in mind.

Rasa is actually open source [2], so you can poke around the internals to see how it's implemented. It doesn't look like it's changed architecture substantially since the pre-LLM days. Rhasspy [3] (also open source) uses similar techniques but in the voice assistant space rather than as a full chatbot.

[0] https://www.personalityforge.com/developers/how-to-build-cha...

[1] https://web.archive.org/web/20200801000000*/https://rasa.com... (old link because Rasa's marketing today is ambiguous about whether they're adding LLMs now).

[2] https://github.com/RasaHQ/rasa

[3] https://rhasspy.readthedocs.io/en/latest/

Rasa GitHub Repository

GitHub - Rasa

Support Rasa on GitHub ⭐

It itself is not a GPT. It is a a framework of a framework project built on top of Rasa (https://github.com/RasaHQ/rasa) and Langchain which by default uses gpt3.5-turbo (change it in the .env file) or any foundation model you wish.

There was already a GitHub issue https://github.com/RasaHQ/rasa/issues/11084 but it seems like there was no solution provided.

Rasa - also an open source platform. You can use it to build chatbots that are more in line with customer service and sales. Reading that, it’s kind of a big yikes for people under this kind of job knowing you can automate a part of their job via a chatbot. I think they also have a Pro version which is an extension that has additional analytics and probably more security features. I probably will check out the Open source one first and maybe ask about what the Pro version is.

At the moment it can recognise the type of statements in the training data set [1] and transpile them to Python, Java or C++ using the mappings defined here [2].

This is very different from how Codex/Autopilot work as it is trained using an NLU framework [3] which is usually used for training chatbots.

[1]: https://github.com/Flex-lang/transpiler/tree/master/transpil...

[2]: https://github.com/Flex-lang/transpiler/tree/master/transpil...

[3]: https://github.com/RasaHQ/rasa

Check out Rasa

5. BotMan

GitHub - BotMan

https://course.buildachatbot.io/ https://botman.io/

The open-source chatbot development framework for cross platform chat- and voice-applications. https://botman.io/