rasa

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...

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.

Totally. Rasa (https://github.com/RasaHQ/rasa) is an open source chatbot platform. It allows you to setup "Input Channels" e.g. slack telegram, and has an intents and response pipeline. It leverages pre-LLM NLU models (NLTK, BERT, etc.) to score intents and based on that intent it will automate a pre-configured response. My implementation allows you directly route (or fallback to) to GPT-3 or GPT-4 via Langchain document retrieval. So essentially this is an example of a knowledgebase customer support bot. I hope that makes sense, let me know if not!

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

Flex [1] is a transpiler that converts a series of statements in natural language to either Python, Java or C++, and is trained using Rasa NLU [2], an open-source framework usually used for training chatbots and voice assistants. Flex is a project I made in college in 2018 along with two of my classmates, Gourav and Sanjay. The initial idea was to create a voice assistant you could speak to that wrote code for you, similar to GitHub's upcoming (and a lot more advanced) project "Hey, Github" [3]. We then had to reduce the project's scope to complete it in a single semester while writing exams, preparing for job interviews and submitting reports and assignments. So we settled on creating a Python program that takes a file containing statements written in natural language as input and transpiles them to a valid Python/Java/C++ program. The p

Hi, How do statups go about when building a tech product that would bring an idea to life? I would like to know if there are some startups that open-source their entire stack. I would like to see building blocks for their web/mobile applications. I have checked https://stackshare.io/, but it is high-level for me, I'd love to how people put code together. Some (Small) startups I came across: - RASA: https://github.com/RasaHQ/rasa - MapZen: https://github.com/mapzen/ Could you please share some links of an open source stack (for a product).

Hello, I am working on a product and I would like to get a glimpse on how do teams structure their code, and how do they organize their thoughts with respect to code/stack/production pipeline (e.g. [RASA](https://github.com/RasaHQ/rasa)). Sinece we are two engineers developing a product, with humbled experience, we would love to see more eye-opening examples that help acquire best practices. Examples can be e-commerce application, preferably a running pipeline in production.