Hacker News Board Hacker News, browsed like a classic message board
Live data from Hacker News

Ingesting PDFs and why Gemini 2.0 changes everything

sergey.fyi

Post reply on HN
Print view View original

181–190 of 456 posts

Re: Ingesting PDFs and why Gemini 2.0 changes everything

#181

Post by serjester »

llm_trw wrote: post #171
ajcp wrote: post #137

Earlier quoted context omitted.

Not sure what service you're basing your calculation on but with Gemmini I've processed 10,000,000+ shipping documents (PDF and PNGs) of every concievable layout in one month at under $1000 and an accuracy rate of between 80-82% (humans were at 66%). The longest part of the development timeline was establishing the accuracy rate and the ingestion pipeline, which itself is massively less complex than what your workflo…

>Not sure what service you're basing your calculation on but with Gemmini The table of costs in the blog post. At 500,000 pages per day the hardware fixed cost overcomes the software variable cost at day 240 and from then on you're paying an extra ~$100 per day to keep it running in the cloud. The machine also had to use extremely beefy GPUs to fit all the models it needed to. Compute utilization was between 5 to 10%…

That assumes that you're able to find a model that can match Gemini's performance - I haven't come across anything that comes close (although hopefully that changes).

Re: Ingesting PDFs and why Gemini 2.0 changes everything

#182

Post by rahimnathwani »

freezed8 wrote: post #180

(disclaimer I am CEO of llamaindex, which includes LlamaParse) Nice article! We're actively benchmarking Gemini 2.0 right now and if the results are as good as implied by this article, heck we'll adapt and improve upon it. Our goal (and in fact the reason our parser works so well) is to always use and stay on top of the latest SOTA models and tech :) - we blend LLM/VLM tech with best-in-class heuristic techniques. So…

Hi Jerry,

How well does llamaparse work on foreign-language documents?

I have pipeline for Arabic-language docs using Azure for OCR and GPT-4o-mini to extract structured information. Would it be worth trying llamaparse to replace part of the pipeline or the whole thing?

Re: Ingesting PDFs and why Gemini 2.0 changes everything

#183

Post by manmal »

gapeslape wrote: post #146

In my mind, Gemini 2.0 changes everything because of the incredibly long context (2M tokens on some models), while having strong reasoning capabilities. We are working on compliance solution ( https://fx-lex.com ) and RAG just doesn’t cut it for our use case. Legislation cannot be chunked if you want the model to reason well about it. It’s magical to be able to just throw everything into the model. And the best thing…

Maybe a dumb question, have you tried fine tuning on the corpus, and then adding a reasoning process (like all those R1 distillations)?

Re: Ingesting PDFs and why Gemini 2.0 changes everything

#184

Post by j_timberlake »

lazypenguin wrote: post #27

I work in fintech and we replaced an OCR vendor with Gemini at work for ingesting some PDFs. After trial and error with different models Gemini won because it was so darn easy to use and it worked with minimal effort. I think one shouldn't underestimate that multi-modal, large context window model in terms of ease-of-use. Ironically this vendor is the best known and most successful vendor for OCR'ing this specific ty…

This sounds extremely like my old tax accounting job. OCR existed and "worked" but it was faster to just enter the numbers manually than fix all the errors.

Also, the real solution to the problem should have been for the IRS to just pre-fill tax returns with all the accounting data that they obviously already have. But that would require the government to care.

Re: Ingesting PDFs and why Gemini 2.0 changes everything

#185

Post by dwheeler »

I wish more PDFs were generated as hybrid PDFs. These are PDFs that also include their original source material. Then you have a document whose format is fixed, but if you need more semantic information, there it is!

LibreOffice makes this especially easy to do: https://wiki.documentfoundation.org/Faq/Writer/PDF_Hybrid

Re: Ingesting PDFs and why Gemini 2.0 changes everything

#186

Post by freezed8 »

rahimnathwani wrote: post #182
freezed8 wrote: post #180

(disclaimer I am CEO of llamaindex, which includes LlamaParse) Nice article! We're actively benchmarking Gemini 2.0 right now and if the results are as good as implied by this article, heck we'll adapt and improve upon it. Our goal (and in fact the reason our parser works so well) is to always use and stay on top of the latest SOTA models and tech :) - we blend LLM/VLM tech with best-in-class heuristic techniques. So…

Hi Jerry, How well does llamaparse work on foreign-language documents? I have pipeline for Arabic-language docs using Azure for OCR and GPT-4o-mini to extract structured information. Would it be worth trying llamaparse to replace part of the pipeline or the whole thing?

yes! we have foreign language support for better OCR on scans. Here's some more details. Docs: https://docs.cloud.llamaindex.ai/llamaparse/features/parsing... Notebook: https://github.com/run-llama/llama_parse/blob/main/examples/...

Re: Ingesting PDFs and why Gemini 2.0 changes everything

#187

Post by rahimnathwani »

freezed8 wrote: post #186
rahimnathwani wrote: post #182

Earlier quoted context omitted.

Hi Jerry, How well does llamaparse work on foreign-language documents? I have pipeline for Arabic-language docs using Azure for OCR and GPT-4o-mini to extract structured information. Would it be worth trying llamaparse to replace part of the pipeline or the whole thing?

yes! we have foreign language support for better OCR on scans. Here's some more details. Docs: https://docs.cloud.llamaindex.ai/llamaparse/features/parsing... Notebook: https://github.com/run-llama/llama_parse/blob/main/examples/...

What is disable_ocr=True for? Is it for documents that already have a text layer, that you don't want to OCR again?

Re: Ingesting PDFs and why Gemini 2.0 changes everything

#188

Post by Andrex »

j_timberlake wrote: post #184
lazypenguin wrote: post #27

I work in fintech and we replaced an OCR vendor with Gemini at work for ingesting some PDFs. After trial and error with different models Gemini won because it was so darn easy to use and it worked with minimal effort. I think one shouldn't underestimate that multi-modal, large context window model in terms of ease-of-use. Ironically this vendor is the best known and most successful vendor for OCR'ing this specific ty…

This sounds extremely like my old tax accounting job. OCR existed and "worked" but it was faster to just enter the numbers manually than fix all the errors. Also, the real solution to the problem should have been for the IRS to just pre-fill tax returns with all the accounting data that they obviously already have. But that would require the government to care.

They finally made filing free.

So, maybe this century?

Re: Ingesting PDFs and why Gemini 2.0 changes everything

#189

Post by tomrod »

makeitdouble wrote: post #172
lazypenguin wrote: post #27

I work in fintech and we replaced an OCR vendor with Gemini at work for ingesting some PDFs. After trial and error with different models Gemini won because it was so darn easy to use and it worked with minimal effort. I think one shouldn't underestimate that multi-modal, large context window model in terms of ease-of-use. Ironically this vendor is the best known and most successful vendor for OCR'ing this specific ty…

> After trial and error with different models As a mere occasional customer I've been scanning 4 to 5 pages of the same document layout every week in gemini for half a year, and every single week the results were slightly different. To note the docs are bilingual so it could affect the results, but what stroke me is the lack of consistency, and even with the same model, running it two or three times in a row gives di…

Consider turning down the temperature in the configuration? LLMs have a bit of randomness in them.

Gemini 2.0 Flash seems better than 1.5 - https://deepmind.google/technologies/gemini/flash/

Re: Ingesting PDFs and why Gemini 2.0 changes everything

#190

Post by woah »

llm_trw wrote: post #101

This is using exactly the wrong tools at every stage of the OCR pipeline, and the cost is astronomical as a result. You don't use multimodal models to extract a wall of text from an image. They hallucinate constantly the second you get past perfect 100% high-fidelity images. You use an object detection model trained on documents to find the bounding boxes of each document section as _images_; each bounding box comes…

Getting "bitter lesson" vibes from this post
Post reply on HN