Alex Yang
Alex Yang
I think I should close this, I double tested on stackbliz that now it's should working. LlamaParse has some internal upgrade to fix this
Please try this. If you have any more issue, please let me know https://stackblitz.com/edit/stackblitz-starters-k137wi?file=index.js
could give me the parameter and maybe sample data?
i think this is same issue that docx parsed as pdf
for now there's a workaround ```ts const magic = [80, 75, 3, 4]; let documents if (buffer[0] === magic[0] && buffer[1] === magic[1] && buffer[2] === magic[2] && buffer[3] ===...
This is kind of document issue, but I'm thinking to improve some logic
You can start with this code: https://github.com/run-llama/LlamaIndexTS/blob/089f1d49c0d5155c2142a84bf3e6222e18548ee2/packages/core/src/schema/type.ts#L15 Add the code to sth like ```ts abstract transform(); ```
I added one ad-hoc plugin in our document here https://github.com/run-llama/LlamaIndexTS/blob/efb7e1b86808811c26f062f4eccbe95ede0c1eb3/apps/next/source.config.ts#L52-L112
I think you can put custom postprocessor into LITS. But PR is welcome
Can you just import `@llamaindex/cloud/reader`?