AI Briefing#rag
The latest AI and developer news about #rag, with the original source and a short summary.
The latest AI and developer news about #rag, with the original source and a short summary.
LY Corporation is leveraging OpenAI's API to bring AI into major services such as LINE and Yahoo! JAPAN, while maximizing internal work efficiency.
AI21's Maestro plans and executes LLM tasks through requirement verification and iterative refinement.
Nubank has adopted OpenAI's GPT-4o to significantly enhance internal operational efficiency, customer support, and fraud detection capabilities.
AI21 released Jamba 1.6, an open model supporting 256K context.
Mistral has launched the new Mistral OCR API, which accurately extracts text, tables, formulas, and more from complex documents.
Enterprise AI emphasized that trustworthy, controllable, and traceable systems matter more than benchmarks.
Kakaopay Securities built the AI bot 'ChoonCiri' for internal knowledge search and work support using Amazon Bedrock and RAG technology.
Based on 3 years of field experience, AI21 lays out GenAI's limitations and Jamba's solution.
AI21 Labs has released a Jamba-based long-context course with DeepLearning.AI.
In 2025, enterprise AI evolves toward industry specialization, RAG, and agentic AI.
Contextual Retrieval leverages contextual information to improve RAG retrieval failure rates by up to 67%.
Three sessions on AI agents, TDD, and internal RAG bots will be held on December 18 at Pangyo Agit.
AI21 Labs became the first company developing and operating an AI cloud platform to receive ISO 42001 certification.
This covers a case study of building an LLM-as-a-Judge evaluation system to ensure the reliability of a RAG chatbot for agricultural support.
Kakao shares its AI technology application cases across six tracks, including AI agents, platforms, and multimodal AI.
Kakao will host Crew Panel Talks on the second and third days of the if(kakaoAI)2024 conference at the outdoor stage to discuss AI development experience and career growth.
Attaching document context before and after chunks to build embeddings and BM25 can significantly reduce RAG retrieval failures.
Rakuten is leveraging OpenAI's API and RAG technology to analyze vast amounts of data, driving innovation in customer service and B2B business.
France's Banque des Territoires built a RAG solution that ensures data sovereignty.
New Computer leveraged LangSmith to improve its agent memory system's recall by 50% and precision by 40%.
Hugging Face has officially launched a dedicated container for efficiently deploying embedding models on Amazon SageMaker.
Replit has launched 'Replit Guides', which supports learning technology and building applications.
It presents a strategy for building an agent that handles 1M context using an 8k context model, and using this to train long-context models.
This guide explains in detail how to fine-tune embedding models using the new training approach introduced in Sentence Transformers v3.0.