I really wish that Google made an endpoint that's compatible with the OpenAI API. That'd make trying Gemini in existing flows so much easier.
Is that not this? https://ai.google.dev/api/compatibility
Ingesting PDFs and why Gemini 2.0 changes everything
71–80 of 456 posts
Re: Ingesting PDFs and why Gemini 2.0 changes everything
#72I think this is one of the few functional applications of LLMs that is really undeniably useful.
OCR has always been “untrustworthy” (as in you cannot expect it to be 100% correct and know you must account for that) and we have long used ML algorithms for the process.
Re: Ingesting PDFs and why Gemini 2.0 changes everything
#73I really wish that Google made an endpoint that's compatible with the OpenAI API. That'd make trying Gemini in existing flows so much easier.
I believe this is already the case, at least the Python libraries are compatible, if not recommended for more than just trying things out:
Re: Ingesting PDFs and why Gemini 2.0 changes everything
#74CTO of Reducto here. Love this writeup! We’ve generally found that Gemini 2.0 is a great model and have tested this (and nearly every VLM) very extensively. A big part of our research focus is incorporating the best of what new VLMs offer without losing the benefits and reliability of traditional CV models. A simple example of this is we’ve found bounding box based attribution to be a non-negotiable for many of our c…
> deterministically
How are you planning to do this?
Re: Ingesting PDFs and why Gemini 2.0 changes everything
#75I 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…
So are you mostly processing PDFs with data? Or PDFs with just text, or images, graphs?
Re: Ingesting PDFs and why Gemini 2.0 changes everything
#76I 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…
I've been fighting trying to chunk SEC filings properly, specifically surrounding the strange and inconsistent tabular formats present in company filings. This is giving me hope that it's possible.
isn't everyone on iXBRL now? Or are you struggling with historical filings?
Re: Ingesting PDFs and why Gemini 2.0 changes everything
#77Earlier quoted context omitted.
How do today’s LLM’s like Gemini compare with the Document Understanding services google/aws/azure have offered for a few years, particularly when dealing with known forms? I think Google’s is Document AI.
I've found the highest accuracy solution is to OCR with one of the dedicated models then feed that text and the original image into an LLM with a prompt like: "Correct errors in this OCR transcription".
This is what we do today. Have you tried it against Gemini 2.0?
Re: Ingesting PDFs and why Gemini 2.0 changes everything
#78I think very soon a new model will destroy whatever startups and services are built around document ingestion. As in a model that can take in a pdf page as a image and transcribe it to text with near perfect accuracy.
I think the Azure Document Intelligence, Google Document AI and Amazon Textract are among the best if not the best services though and they offer these models.
Re: Ingesting PDFs and why Gemini 2.0 changes everything
#79> Why Gemini 2.0 Changes Everything Clickbait. It doesn't change "everything". It makes ingestion for RAG much less expensive (and therefore feasible in a lot more scenarios), at the expense of ~7% reduction in accuracy. Accuracy is already rather poor even before this, however, with the top alternative clocking in at 0.9. Gemini 2.0 is 0.84, although the author seems to suggest that the failure modes are mostly arou…
In this use-case, accuracy is non-negotiable with zero room for any hallucination.
Overall it changes nothing.
Re: Ingesting PDFs and why Gemini 2.0 changes everything
#80I'm building a system that does regular OCR and outputs layout-following ASCII; in my admittedly limited tests it works better than most existing offerings.
It will be ready for beta testing this week or the next, and I will be looking for beta testers; if interested please contact me!