[holdenc137]

I don't get it (and I'd call this cumulative not incremental)

Why not at least wait until the key is complete - what's the use in a partial key?

[xg15]

Doesn't it do exactly that?

> As a consequence of 1 and 5, we only add a property to an object once we have the entire key and enough of the value to know that value's type.

[0x6c6f6c]

Their example in the README is extremely misleading then. It indicates your stream output is

name: A name: Al name: Ale name: Alex

Which would suggest you are getting unfinished strings out in the stream.

[__jonas]

How is it misleading? It shows that it gives back unfinished values but finished keys.

[rictic]

Cumulative is a good term too. I come from the browser world where it's typically called incremental parsing, e.g. when web browsers parse and render HTML as it streams in over the wire. I was doing the same thing with JSON from LLMs.

[simonw]

If you're building a UI that renders output from a streaming LLM you might get back something which looks like this:

  {"role": "assistant", "text": "Here's that Python code you aske

Incomplete parsing with incomplete strings is still useful in order to render that to your end user while it's still streaming in.

[trevor-e]

In this example the value is incomplete, not the key.

[cozzyd]

incomplete strings could be fun in certain cases

{"cleanup_cmd":"rm -rf /home/foo/.tmp" }

[stronglikedan]

If any part of that value actually made it, unchecked, to execution, then you have bigger problems than partial JSON keys/values.

[sublee]

Incremental JSON parsing is key for LLM apps, but safe progressive UIs also need to track incompleteness and per-chunk diffs. LangDiff [1] would help with that.

[1]: https://github.com/globalaiplatform/langdiff/tree/main/ts

[cozzyd]

Why not just chunk the json packets instead?

[xg15]

Only because you have access to the incomplete value doesn't mean you should treat it like the complete one...

[rictic]

Yeah, another fun one is string enums. Could tread "DeleteIfEmpty" as "Delete".

[Waterluvian]

I imagine if you reason about incomplete strings as a sort of “unparsed data” where you might store or transport or render it raw (like a string version of printing response.data instead of response.json()), but not act on it (compare, concat, etc), it’s a reasonably safe model?

I’m imagining it in my mental model as being typed “unknown”. Anything that prevents accidental use as if it were a whole string… I imagine a more complex type with an “isComplete” flag of sorts would be more powerful but a bit of a blunderbuss.