Reducto releases Deep Extract
raunakchowdhuri
46 points
7 comments
April 06, 2026
Related Discussions
Found 5 related stories in 89.6ms across 8,303 title embeddings via pgvector HNSW
- 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-V4: Towards Highly Efficient Million-Token Context Intelligence cmrdporcupine · 146 pts · April 24, 2026 · 50% similar
- TurboQuant: Redefining AI efficiency with extreme compression ray__ · 509 pts · March 25, 2026 · 49% similar
- DeepSeek v4 impact_sy · 455 pts · April 24, 2026 · 48% 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