Fructose
AI
llm function calling library
SHOW HN2024
218points
99comments
#355of 3,515 in 2024
Top 11%of 2024 by points
How HN took it
CuriousMostly questions and neutral comments
4 positive, 22 neutral or asking, 1 mixed, 11 critical, out of 38 comments about the project. Thread score -0.16.
Idea: 2 for, 8 againstDesign: 2 for, 2 againstExecution: 0 for, 1 against
The thread, comment by comment
Each row is a top-level comment and its replies, in HN's order. Select a cell to open that comment on HN.
positive neutral or mixed critical about another commenter or something else the maker
What HN said
What people liked
Clean, neat aesthetics of the API
From 1 comment
This is much nicer than calling GPT in the middle of my code. Honestly the aesthetics of Fructose just make the code so much neater
AmanKishore on HN
Functional programming feel fits generative programming
From 2 comments
Yeah, functional programming and pure functions seem perfect for generative programming. Granted, I think they're perfect in general, but as long as human programmers are still…
ravenstine on HNyeah I had a moment working with fructose where I realized "oh this is more like functional programming than I expected"
edunteman on HN
Objections
Too similar to Marvin and other existing libraries
From 3 comments
> not unlike other packages such as marvin This feels pretty much identical to Marvin? Like the entire API? From a genuine place of curiosity: I get that your prompts are…
itfollowsthen on HNyeah this seems to be pretty much the same interface as `fn` from marvin, except w/o pydantic (see…
nate_nowack on HNWait. So why not just contribute to an existing open source project if you’re going to implement an identical API? If you run your own models as a part of it, surely you could…
lefttoreader on HN
Relies on prompt-and-parse JSON rather than native function calling or grammar constraints
From 2 comments
This approach may be too high-level "magic" to the point of being difficult to work with and iterate upon. Looking at the prompt templates…
minimaxir on HNBig proponent of guaranteed outputs for LLMs. I wrote a library awhile back (gpt-json) that did something similar by querying the OpenAI API. At the end of the day though while…
icyfox on HN
Output structure not guaranteed; parse failures throw exceptions
From 1 comment
It's not 100% yet. Route to that: 1. Clientside, retry strategy on failed parse. Not yet implemented, we throw an exception on parse fail right now, but soon to be implemented.…
edunteman on HN
Only works with OpenAI models despite LLM framing
From 1 comment
I find it grating that all of these types of things say "LLMs" when in fact they literally only work with OpenAI. There are hundreds of variations of LLM models. When it works…
ilaksh on HN
Requests
Support for local LLMs like Ollama and LocalAI
From 2 comments
I love the concept, but I'd really prefer being able to use it against local llms (localai, ollama, etc).
jsight on HNfyi: LM Studio can host a server that uses the OpenAI api to whatever model you are using locally So as long as this library can be directed to localhost or configured, it can…
yieldcrv on HN
Support for Claude, Llama2 and other models
From 1 comment
Are you planning to add other types like Claude or Llama2?
politelemon on HN
Pydantic support
From 1 comment
Very Cool! Would it work for Pydantic out of the box? Or that's something coming along?
jonathan-adly on HN
Questions
How does it compare to Instructor, Marvin, Outlines, LMQL, Guidance
From 3 comments
How does Fructose relate or compare to Instructor (https://github.com/jxnl/instructor)?
hedgehog on HNI've done a lot of work over the last year wrangling LLM outputs - both from the OpenAI API as well as local LLMs. What are the benefits of using Fructose over LMQL, Guidance or…
biddit on HNObvious question - how is this better than marvin, instructor, outlines.
justanotheratom on HN
Why not contribute to existing open source projects instead
From 2 comments
> not unlike other packages such as marvin This feels pretty much identical to Marvin? Like the entire API? From a genuine place of curiosity: I get that your prompts are…
itfollowsthen on HNWait. So why not just contribute to an existing open source project if you’re going to implement an identical API? If you run your own models as a part of it, surely you could…
lefttoreader on HN
Alternatives named
Instructor
From 2 comments
Good stuff. How does this compare to Instructor? I’ve been using this extensively https://jxnl.github.io/instructor/
mattew on HNHow does Fructose relate or compare to Instructor (https://github.com/jxnl/instructor)?
hedgehog on HN
Marvin
From 2 comments
> not unlike other packages such as marvin This feels pretty much identical to Marvin? Like the entire API? From a genuine place of curiosity: I get that your prompts are…
itfollowsthen on HNyeah this seems to be pretty much the same interface as `fn` from marvin, except w/o pydantic (see…
nate_nowack on HN
Outlines
From 1 comment
This approach may be too high-level "magic" to the point of being difficult to work with and iterate upon. Looking at the prompt templates…
minimaxir on HN
LMQL
From 1 comment
I've done a lot of work over the last year wrangling LLM outputs - both from the OpenAI API as well as local LLMs. What are the benefits of using Fructose over LMQL, Guidance or…
biddit on HN
Guidance
From 1 comment
TGI just integrated Guidance in 1.4.3, that by itself can support both grammar/JSON/Pydantic & tool invocation/function calling. Langchain & Llamaindex plus Fructose really need…
iAkashPaul on HN