bolha.us is one of the many independent Mastodon servers you can use to participate in the fediverse.
We're a Brazilian IT Community. We love IT/DevOps/Cloud, but we also love to talk about life, the universe, and more. | Nós somos uma comunidade de TI Brasileira, gostamos de Dev/DevOps/Cloud e mais!

Server stats:

253
active users

#rag

1 post1 participant0 posts today

Wie können wir sicherstellen, dass KI-Systeme präzise, nachvollziehbar und auf dem neuesten Stand bleiben?

Morgen beim #INNOQTechnologyLunch erklärt Robert Glaser, wie #RAG dazu beiträgt, Wissenslücken zu schließen und die Genauigkeit generativer KI zu verbessern – durch gezielte Erweiterung mit echten Daten.

🗓️ 2. April
🕛 12:15 CET

Link im Kommentar 👇

#RubyLang #hivemind: I have a passel of #SQL spaghetti that I'd like to turn into a set of #Rails models. I'm not finding a good SQL-specific #LLM that understands interrelated SQL files for #RAG that groks the newer features of #RoR 8+. I'd like #model_enums & seeds.rb support.

Know an LLM model that's any good at doing even 50% of the #boilerplate work? It doesn't have to be perfect; it just has to make it less tedious to extract the boilerplating.

Suggestions?

Mistral #OCR is an Optical Character Recognition API that sets a new standard in document understanding. Unlike other models, Mistral OCR comprehends each element of documents—media, text, tables, equations—with unprecedented accuracy and cognition. It takes images and PDFs as input and extracts content in an ordered interleaved text and images.
As a result, Mistral OCR is an ideal model to use in combination with a #RAG system taking multimodal documents (such as slides or complex PDFs) as input. #AI

mistral.ai/fr/news/mistral-ocr

mistral.aiMistral OCR | Mistral AIIntroducing the world’s best document understanding API.