CSV is a lot lighter on tokens, compared to json, so it can go further, before a LLM gets exhausted.
If you haven't already seen the DeepSeek OCR paper [1], images can be profoundly more token-efficient encodings of information than even CSVs!
[1]: https://github.com/deepseek-ai/DeepSeek-OCR/blob/main/DeepSe...
alt Hacker News
If you haven't already seen the DeepSeek OCR paper [1], images can be profoundly more token-efficient encodings of information than even CSVs!
[1]: https://github.com/deepseek-ai/DeepSeek-OCR/blob/main/DeepSe...