Reducto releases Deep Extract
raunakchowdhuri
46 points
7 comments
April 06, 2026
Related Discussions
Found 5 related stories in 521.6ms across 14,015 title embeddings via pgvector HNSW
- DeepSeek reasonix, DeepSeek native coding agent with high caching and low cost Alifatisk · 507 pts · May 24, 2026 · 56% similar
- Show HN: DeepRepo – AI architecture diagrams from GitHub repos uwais12 · 12 pts · March 29, 2026 · 52% similar
- DeepSeek-V4: a million-token context that agents can use ibobev · 12 pts · April 28, 2026 · 52% similar
- DeepSeek Slashes AI Costs to Cents dstala · 13 pts · May 29, 2026 · 52% similar
- DeepSeek-V4: Towards Highly Efficient Million-Token Context Intelligence cmrdporcupine · 146 pts · April 24, 2026 · 50% similar
Discussion Highlights (4 comments)
skadamat
How does this compare to DataLab ( https://www.datalab.to/ )
willwjack
Any learnings from deploying agents at such massive scale?
aleks5678
We used Reducto and it did struggle with long documents. As we process financial documents going over 300+ pages using Gemini 3 Flash is producing high accuracy extracts super fast.
cyanydeez
I like to play guess which LLM open source package is that XKCD comic. Looks like it's something like: https://huggingface.co/docs/transformers/model_doc/layoutxlm