Kor: a half-baked prototype that "helps" you extract structured data using LLMs
1–10 of 17 posts
Re: Kor: a half-baked prototype that "helps" you extract structured data using LLMs
#2Neat, I was just looking for something like this today, I think I'll give it a spin.
Does anybody here have experience with metadata extraction using LLMs? I've been thinking about it recently. and wonder if just making a big prompt and putting that into OpenGPT or even ChatGPT is really the way to go, or if there is a "cleverer" way. Maybe you could train specifically for certain fields, or use the LLM in a different way (like you can use the embeddings directly to do simularity search)?
Another idea was, if you have a lot of similar HTML documents, to not ask the LLM for the metadata, but to ask it for CSS selectors that contain the metadata fields - assuming it can deal with HTML and the data is verbatim in there. Then you should be able to get much more consistent results.
Re: Kor: a half-baked prototype that "helps" you extract structured data using LLMs
#3Have you tried this on HTML?
Re: Kor: a half-baked prototype that "helps" you extract structured data using LLMs
#4Does this take advantage of the new OpenAI functions api? From a quick look, I can't find any indication that it does. Although I find it tricky to disentangle the langchain abstractions, so I might be missing it. Kor's last release predates the announcement of OpenAI functions, so probably not.
Seems like this is now best done via functions, if you're using OpenAI's models? They call out "extracting structured data from text" as a key use case in their announcement.
https://openai.com/blog/function-calling-and-other-api-updat...
Re: Kor: a half-baked prototype that "helps" you extract structured data using LLMs
#5Another tool like this is Marvin. My experience this that these work pretty well, but the world of prompt “engineering” is a very squishy one and getting the exact output format you want is not guaranteed.
Re: Kor: a half-baked prototype that "helps" you extract structured data using LLMs
#6Does this take advantage of the new OpenAI functions api? From a quick look, I can't find any indication that it does. Although I find it tricky to disentangle the langchain abstractions, so I might be missing it. Kor's last release predates the announcement of OpenAI functions, so probably not. Seems like this is now best done via functions, if you're using OpenAI's models? They call out "extracting structured data…
No, it is not using openai functions. Since it is on top of langchain it uses the LLM abstraction of it and it can be used with other models as well.
Re: Kor: a half-baked prototype that "helps" you extract structured data using LLMs
#7Have you tried this on HTML?
Yes, tried it on HTML to get "metadata" that was not present in the HTML meta tags, such as author, publish date, etc. Works good.
Re: Kor: a half-baked prototype that "helps" you extract structured data using LLMs
#8Re: Kor: a half-baked prototype that "helps" you extract structured data using LLMs
#9Re: Kor: a half-baked prototype that "helps" you extract structured data using LLMs
#10Neat, I was just looking for something like this today, I think I'll give it a spin. Does anybody here have experience with metadata extraction using LLMs? I've been thinking about it recently. and wonder if just making a big prompt and putting that into OpenGPT or even ChatGPT is really the way to go, or if there is a "cleverer" way. Maybe you could train specifically for certain fields, or use the LLM in a differen…
I gave it some css paths extracted from devtools, and some sample elements with data that needed extraction and had it write a beautiful soup + regex routine to do the extractions. worked fine. Also thousands of times faster.