News for hackers. Stuff that matters.
Re:Putting Andrew Ng's OCR models to the test by serjester on Friday February 28, 2025 @12:57AM (#43202174)
Personally I find it frustrating they called it "agentic" parsing when there's nothing agentic about it. Not surprised the quality is lackluster.
Re:Putting Andrew Ng's OCR models to the test by ritvikpandey21 on Friday February 28, 2025 @01:52AM (#43202527)
we're not the biggest believers in 'agentic' parsing! we definitely do believe there's a specific role for LLMs in the data ingestion pipeline, but this occurs more when bar graphs/charts/figures -> structured markdown.

we're messing around with some agentic zooming around documents internally, will make our findings public!

Re:Putting Andrew Ng's OCR models to the test by pierre on Friday February 28, 2025 @01:49AM (#43202510)
If you want to try agentic parsing we added support for sonnet-3.7 agentic parse and gemini 2.0 in llamaParse. cloud.llamaindex.ai/parse (select advanced options / parse with agent then a model)

However this come at a high cost in token and latency, but result in way better parse quality. Hopefully with new model this can be improved.