i agree. perhaps you're confused on the intent. the only flag being planted is for folks using rasa looking for a reference implementation just like i was a week ago. not sure if you're being intentionally cynical but trying is good thing. why? bc most ppl don't try. you make 0 of the shots you never take. and of course, if you're not intentionally being cynical -- gucci. if you are i encourage you to make your next comment substantial or encouraging :)
well to be fair, when you're scaling it does matter. i would want my techlead or seniors to care and know when/where to make specific trade-offs bc cloud costs are not forgiving.
i think that's where folks that make those comments are coming from.
that's a somewhat cynical interpretation. what if i just care about aesthetics and want to raise the bar.
my primary motivation was to get users of Rasa out of a directional hole bc that's where i was.
of course i like stars. it's a video game and i like winning. it was actually created in a few days all by me. no ulterior motive, literally indexing a solution to my problem from ~a week ago.
my bg is eng + product so i do these things as reflex and have a love for good UX.
We are all crafters, and I admire the attention to these presentation points of OP. This is clear in the documentation and explanations at the repository too.
That said, I don't think the questioning of GP was malicious, just a natural curiosity. Yes, a little suspicious, but, well, we are in the internet after all. In the least, it's good to point when someone does the extra work to make a great presentation.
Sorry, I didn't mean to imply any nefarious ulterior motives here.
I'm more just intellectually curious about the dynamics of Github and marketing on it these days, whether it's for attracting contributors to non-commercial OSS projects or more commercial objectives where rapid growth leads to userbase, funding, etc.
The project looks quite interesting and I agree we need a way to bridge the gap between traditional bot creation frameworks and the more LLM-centric approaches of late.
my objective falls into neither bucket. i want rasa users to find it so i optimize for search (GH tags, clear description), ease of use (video, addt'l MD files) and perception (logos) but i'll be honest, for my intention it has a diminishing rate of return.
at minimum i find canonical README sections like quick start, installation, how it works is necessary if you want to be helpful. helpfulness is difficult to measure outside of inbound emails thanking you / forks w/ actual commits.
hope that gives some kind of insight. just make everything awesome :)
The sad truth is that it's the average README that's hilariously bad, not that you did something strange or wrong. As you say - whenever something is trying to be useful to anyone other than the author, the author should in turn try to be helpful. Unfortunately, programmers always had a love-hate relationship with documentation (love it when you need it and others wrote it for you, hate the guts of it if it's you who need to write it), but I think it got progressively worse in the last decade.
At work, I have to often seriously fight for there to even be a README. Lack of docs and docstrings, lack of meaningful comments in the code, utter lack of visualization was the norm in the 90s, then it got better for a while, and now we've done a full circle and are back with undocumented spaghetti everywhere.
It's really strange, and I don't understand why it's like this. I tell people who nominally are way past being juniors to read their code before making a PR - to see how easy to understand it is - and they look like they just got enlightened. Like, isn't this (reading your own code) the most basic of all ways of working with code? Same for READMEs, I tell them to put all the information needed for a new person to set the project up, and am met with blank stares - why would they, programmers, bother with writing down plain English and managing the information surrounding what they do? Have these guys never thought about what the "I" in "IT" means?
Sorry, that's a possibly unwarranted rant, but when I see posts like GP's that seem to assume that writing a helpful README is somehow strange and a waste of effort unless it translates into clicks, it just blows my mind, it a pretty negative way.
you're not alone my dude. i have a similar challenge w/ my engineers. my best lead is an artisan and its proud of what he authors, and like me sees their code as part of the product UX / funnel (1%). the others (99%) i have to get a bit draconian or simply create company templates they must adhere to or PRs get rejected and they hear from me on their 1:1s.
you either love it or you don't. and if you don't, follow the rules like a big boy or get called out.
ultimately you have to set a culture for it even if it is pulling teeth because you net net it impacts the PnL.
I really appreciate your work on this--we have been building on rasa and looking into alt ways to use new LLM models. The question is, do we even need Rasa anymore, does it make sense given that RasaX is behind a very expensive paywall.
the next best platform I could find for my friend I was helping was google's dialog flow. again, it was managed, closed-source opinionated and not as flexible. and most importantly design considerations were for a pre-LLM world.
i personally think there is an acute opportunity for creating a bare bones rasa built with LLMs in mind. the core concepts behind rasa are useful (domains, intents, actions, etc.) but the underlying NLU technology and assumptions around the platform are obsolete so 70% of the footprint is unnecessary.
it solves how to integrate LLMs (Langchain) an application API pipeline with Rasa... of which I could not find an out-of-the-box public example on github. and so here we are :)
in short and as mentioned in the README.md this is absolutely vulnerable to prompt injection. I think this is not a fully solved issue but some interesting community research has been done to help address these things in production
I'm not sure it solves the problem of restricting the information it uses though. For example, as a proof of concept for a customer, I tried providing information from a vector database as context, but GPT would still answer questions that were not provided in that context. It would base its answers on information that was already crawled from the customer website and in the model. That is concerning because the website might get updated but you can't update the model yourself (among other reasons).
- Reduce bloat, make packages optional e.g. pip install langchain[all]
- Reduce opinionated implementation of vector stores, I want my own schema
- Don't unnaturally force the chain abstraction
- Invest more in document retrieval
i agree. perhaps you're confused on the intent. the only flag being planted is for folks using rasa looking for a reference implementation just like i was a week ago. not sure if you're being intentionally cynical but trying is good thing. why? bc most ppl don't try. you make 0 of the shots you never take. and of course, if you're not intentionally being cynical -- gucci. if you are i encourage you to make your next comment substantial or encouraging :)