Show HN: DocStrange: An LLM-Ready Data Platform That Performs Better Than Gemini
docstrange.nanonets.com
Show HN: DocStrange: An LLM-Ready Data Platform That Performs Better Than Gemini
1–7 of 7 posts
Re: Show HN: DocStrange: An LLM-Ready Data Platform That Performs Better Than Gemini
#2We have developed DocStrange to create LLM-ready data from images and PDFs. We have open-sourced a 3B finetuned model also. You can try both the open-sourced and private models from the demo.
HF: https://huggingface.co/nanonets/Nanonets-OCR2-3B Demo: https://docstrange.nanonets.com/ Blog: https://nanonets.com/research/nanonets-ocr-2/
This model is an improvement over our last open-source model. We have fixed some of the issues that the community faced and some of the features that were requested (handwritten, multi-lingual).
The models are trained on 3 million documents, including handwritten documents, financial reports, complex tables, documents with watermarks, and stamps. Feel free to try it and share feedback.
Re: Show HN: DocStrange: An LLM-Ready Data Platform That Performs Better Than Gemini
#3We have developed DocStrange to create LLM-ready data from images and PDFs. We have open-sourced a 3B finetuned model also. You can try both the open-sourced and private models from the demo. HF: https://huggingface.co/nanonets/Nanonets-OCR2-3B Demo: https://docstrange.nanonets.com/ Blog: https://nanonets.com/research/nanonets-ocr-2/ This model is an improvement over our last open-source model. We have fixed some of…
Do you guys provide api support also? I am processing documents for a project
Re: Show HN: DocStrange: An LLM-Ready Data Platform That Performs Better Than Gemini
#4We have developed DocStrange to create LLM-ready data from images and PDFs. We have open-sourced a 3B finetuned model also. You can try both the open-sourced and private models from the demo. HF: https://huggingface.co/nanonets/Nanonets-OCR2-3B Demo: https://docstrange.nanonets.com/ Blog: https://nanonets.com/research/nanonets-ocr-2/ This model is an improvement over our last open-source model. We have fixed some of…
Do you guys provide api support also? I am processing documents for a project
Yeah, we do have api support. Currently, you can process 10k documents per month free. Let me know if you face any issues.
Re: Show HN: DocStrange: An LLM-Ready Data Platform That Performs Better Than Gemini
#5[dead]
Re: Show HN: DocStrange: An LLM-Ready Data Platform That Performs Better Than Gemini
#6Is it better than gemini pro or flash? do you have any benchmarking data? I want to use it for markdown from scanned pdfs.
Re: Show HN: DocStrange: An LLM-Ready Data Platform That Performs Better Than Gemini
#7Is it better than gemini pro or flash? do you have any benchmarking data? I want to use it for markdown from scanned pdfs.
We have evaluated against Gemini-2.5-flash. You can check the benchmarks here https://nanonets.com/research/nanonets-ocr-2/#markdown-evalu...