xatkit VS pydantic

While we wait for these tools to pop up, any tech question on the internals of Xatkit you'd like to know? And if you want to read more about the technologies we have listed above, this twitter thread gives some pointers to good tutorials for them:

(obviously) Create your own chatbots (pairing it up with Xatkit or any other chatbot platform for all the front-end and behaviour processing components)

The easiest part is to create the chatbot. We'll obviously use Xatkit for this. The bot can have as many intents as you wish. The only part that we care about here is the default fallback state. Here, instead of saying something useless, e.g. "sorry I didn't get your question, can you rephrase it and try again?", we will ask Haystack to find us a solution.

Take a look at Xatkit (https://github.com/xatkit-bot-platform/xatkit). It's an open source chatbot development platform and very easy to deploy on your own premises as the bot is compiled into a single .jar.

But, IMHO, many business owners do not really want to create a bot by themselves, no matter how easy is the chatbot development interface. They want to give you the data (whatever type of data they already have, e.g. an excel file with collected questions) and get a bot out of it. This is way at Xatkit we're now providing this type of "chatbot automatic generation services"

There are ML libraries available for every language. So there is always a way to execute/train your neural networks outside the python world. For instance, in Xatkit, we reuse Stanfords' Core NLP models in some of our language processors. And, if needed, there is always the option to wrap the ML models code in a Python server (I like the simplicity of Flask for this) and consume them via API calls to this server.

We have recently launched Xatkit, a pretrained chatbot for eCommerce. The reception so far has been lukewarm and we wonder whether:

Interested to give it a try? For FREE during the next two months? Visit: https://xatkit.com/ (and pls redistribute to your colleagues if you know anybody that could be interested, thanks!)

But this doesn't mean your no-code tool needs to stick to one specific category. As we do in Xatkit, you can offer different interfaces/importers on top of the same engine. You can even offer a low-code version for advanced users willing to use your tool's API to complement the result of the no-code approach.

First, note the method prefix_allowed_tokens_fn. This method applies a Pydantic model to constrain/guide how the LLM generates tokens. Next, see how that constrain can be applied to txtai's LLM pipeline.

utype is a concise alternative of pydantic with simplified parameters and usages, supporting both sync/async functions and generators parsing, and capable of using native logic operators to define logical types like AND/OR/NOT, also provides custom type parsing by register mechanism that supports libraries like pydantic, attrs and dataclasses

I like some of the changes from v1 to v2. But then you have something like this [0] removed from the library without proper documentation or replacement, resulting in ugly workarounds in the link that wont' work properly.

[0]: https://github.com/pydantic/pydantic/discussions/6337

The easiest implementation I found was to use a PyDantic class for my target schema — and use that as a parameter for the method call to “ChatCompletion.create()”. Here’s a fragment of the GinAI Python classes used.

Also, FastStream uses Pydantic to parse input JSON-encoded data into Python objects, making it easy to work with structured data in your applications, so you can serialize your input messages just using type annotations.

Pydantic Validation: Leverage Pydantic's validation capabilities to serialize and validate incoming messages

Not sure if it is exactly related, but there is an open issue on Github for that exact message.

Well the performance increase is so huge because pydantic1 is really really slow. And for using rust, I'd have expected more tbh…

I've been benchmarking pydantic v2 against typedload (which I write) and despite the rust, it still manages to be slower than pure python in some benchmarks.

The ones on the website are still about comparing to v1 because v2 was not out yet at the time of the last release.

pydantic's author will refuse to benchmark any library that is faster (https://github.com/pydantic/pydantic/pull/3264 https://github.com/pydantic/pydantic/pull/1525 https://github.com/pydantic/pydantic/pull/1810) and keep boasting about amazing performances.

On pypy, v2 beta was really really really slow.