[cheesyFishes]

The output is either text or markdown, and from there you can handle it however you need.

In LlamaIndex for example, there are a a few markdown-specific classes that work well with this.

You can find an example over in the repo -- https://github.com/run-llama/llama_parse/blob/main/examples/...

[lolpanda]

I was hoping to get structured data. For example, parsing an voice will give results like {"title"... "line_items": [...], "date":...}