Improve Page Content when Fetching
Opened this issue · 1 comments
GuillemineA commented
For now the web page content is either polluted with html text, either a plain text (no tittle, links or anything).
To improve the quality of the results the goal is to manage to get a a web page content and format it in markdown. That way, OpenAI will have a better idea of what it's reading.
GuillemineA commented
#18
We now have a good function to convert the HTML content of the web page into markdown.