Kor: Extract structured data using LLMs

Re:Kor: Extract structured data using LLMs by dennisy on Monday June 26, 2023 @03:44PM (#36484765)

Have you tried this on HTML?

[ Parent | on HN ]

Re:Kor: Extract structured data using LLMs by BorisWilhelms on Monday June 26, 2023 @04:12PM (#36485173)

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.

[ Parent | on HN ]

Re:Kor: Extract structured data using LLMs by BorisWilhelms on Monday June 26, 2023 @04:14PM (#36485191)

Actually not on raw HTML, but with the WebBaseLoader from Langchain which strips away HTML tags.

[ Parent | on HN ]

Re:Kor: Extract structured data using LLMs by dennisy on Monday June 26, 2023 @04:24PM (#36485337)

Ahh cool thank you!

[ Parent | on HN ]