The community member is a beginner looking for guidance on how to combine web-scraped data with their existing HTML and Markdown files in a stack they have set up using create-llama. They have successfully used Apify to crawl pages and generate a dataset, but are unsure how to incorporate this data into their existing setup. One of the comments mentions that the community member is not married to Apify and was just using it as the first tool they saw for URL scraping in the llama directory.
Hello all -- i'm a self-confessed n00b and am just looking for some direction on how to accomplish this please. I've used create-llama to get a stack running and have a working implementation with a combination of markdown docs and html files I added to the model. What I'd now like to do is add web-scraped data to the model. I installed apify and have used it to successfully crawl pages and generate a dataset. My question is... how can I combine web scraped data with my existing html & markdown files in the same stack I've already got set up with create-llama? Thank you!
