Hacker News Board Hacker News, browsed like a classic message board
Live data from Hacker News

DSPy: Framework for programming with foundation models

github.com

Post reply on HN
Print view View original

51–56 of 56 posts

Re: DSPy: Framework for programming with foundation models

#51

Post by apstls »

okhat wrote: post #46
apstls wrote: post #45

Earlier quoted context omitted.

I'm trying to wrap my head around this project too, since it does seem interesting. Similar to what OP wrote, the sense I got from poking around (and of course from reading the bit in the README that basically says exactly this) was that there are two distinct pieces here, the first being a nice, clean library for working directly with LLMs that refreshingly lacks the assumptions and brittle abstractions found in man…

Thanks! Lots to discuss from your excellent response, but I'll address the easy part first: DSPy is v2 of DSP (demonstrate-search-predict). The DSPy paper hasn't been released yet. DSPy is a completely different thing from DSP. It's a superset. (We actually implemented DSPy _using_ DSPv1. Talk about bootstrapping!) Reading the DSPv1 paper is still useful to understand the history of these ideas, but it's not a comple…

Ah, gotcha! Do you have a rough idea of when the DSPy paper will be released? I'll keep an eye out.

Re: DSPy: Framework for programming with foundation models

#52

Post by okhat »

apstls wrote: post #51
okhat wrote: post #46

Earlier quoted context omitted.

Thanks! Lots to discuss from your excellent response, but I'll address the easy part first: DSPy is v2 of DSP (demonstrate-search-predict). The DSPy paper hasn't been released yet. DSPy is a completely different thing from DSP. It's a superset. (We actually implemented DSPy _using_ DSPv1. Talk about bootstrapping!) Reading the DSPv1 paper is still useful to understand the history of these ideas, but it's not a comple…

Ah, gotcha! Do you have a rough idea of when the DSPy paper will be released? I'll keep an eye out.

Writing right now. This month :-)

Re: DSPy: Framework for programming with foundation models

#53

Post by data_maan »

Difwif wrote: post #22

Looks interesting and seems to not make some of the mistakes that other frameworks make (langchain, llamaindex, etc.) I was pretty apprehensive when I looked at your short hand signature API. I'm really not a fan of these custom mini languages, but it looks like it's fairly constrained at the moment and has an expanded form with a sane Python API. My only concern is that the short hand signatures spiral out of contro…

> seems to not make some of the mistakes that other frameworks make (langchain, llamaindex, etc.)

Which mistakes, specifically, do you mean they make?

Re: DSPy: Framework for programming with foundation models

#54

Post by two_in_one »

tevon wrote: post #49
gabereiser wrote: post #13

Earlier quoted context omitted.

I welcome programming English++ with open arms so long as I can scold it when it makes mistakes and it doesn’t require move semantics. I’m joking of course but I do think LLM’s will become part of the programming language lexer of some kind. If not already being looked into.

Introducing non-deterministic inputs into programs is already wild. I think once we get past "make the LLM generate #$%!#@ JSON" we will start seeing a lot more of this, since we will then be able to constrain the code-paths that are followed. I could absolutely see LLM-powered operators being introduced at some point, that we use just like an if statement. Imagine "if(input like LLM(greeting))" or while(LLM(input) l…

Why not the other way around? LLM interfaced with a controller which recognizes commands in text stream and can insert data.

If it's too dark call 'HAL.lights_on' with the current room as a parameter.

"Tell me how old Napoleon would be today." "Today Napoleon, assuming he is alive, would be calc(today - data.Napoleon.birthdate).year"

Re: DSPy: Framework for programming with foundation models

#55

Post by sandGorgon »

grandma_tea wrote: post #30

This is really cool! It took me a bit to understand what this thing is for so allow me to summarize: For simple LLM tasks, don't bother using this tool. It won't do much for you. If you have a more complicated task (eg. knowledge database lookups, chain of thought reasoning, multi-hop lookups...) then DSPy offers 2 things: a clean class-based representation of your workflow, and a way to *solve* for the best prompt s…

would love your thoughts on this as well - https://github.com/arakoodev/edgechains

got frustrated in the same way with "Black Box Prompting - every library hides prompts/chains in layers of libraries...while it should have been declarative.

EdgeChains - allows u to specify ur prompt and chain in jsonnet. This why i think Generative AI needs declarative orchestration and not previous generations. https://github.com/arakoodev/edgechains#why-do-you-need-decl...

Post reply on HN