"RAG from Basics to Advanced (Part 4): Chunking Strategies" by Pawan Sharma
@communityaws.bsky.social
@communityaws.bsky.social"RAG from Basics to Advanced (Part 4): Chunking Strategies" by Pawan Sharma
@ai-bloom.warp-studio.comHPE ZertoがAmazon Bedrockで構築したエージェント型トラブルシューティングシステムの技術深掘り
ZertoのAIトラブルシューティングシステム詳細解析
@communityaws.bsky.social"5 AWS AI Concepts That Changed How I Think About GenAI Delivery" by ANDRII DOLZHENKO
@alanbonnici.comThis article considers whether a single permission-aware corporate AI assistant could provide a practical interface to that scattered organisational knowledge.
#EnterpriseAI #RAG #KnowledgeManagement #AIGovernance #DigitalTransformation #Cybersecurity #TTMO #Medium
@paul-crinigan.bsky.socialMost RAG debugging starts in the wrong place.
Teams tune chunk size and prompts for weeks. The real problem is usually upstream: a parser that silently returned an empty string, or the same FAQ ingested from three sources.
@communityaws.bsky.social"Democratizando la IA Generativa: Más allá de las bases de datos tradicionales con Amazon S3 Vectors" by CARLOS ALBERTO ORTIZ JARAMILLO
#agentic-ai #rag #storage #cloud-storage #artificial-intelligence
@tmtabor.ioTwo years ago I built a #RAG pipeline for GenePattern Copilot, an agentic assistant for genomics analysis. It used #LangChain and had retrieval over documentation and a decade's worth of help forum data. At the time, that was unusual.
@aidailypost.comJust dropped: ShipAI's new project pages now host creator-made video walkthroughs. See RAG pipelines, Hugging Face demos, GitHub-linked AI agents in action. Dive in and level up your ML builds! #ShipAI #RAG #HuggingFace
@communityaws.bsky.social"The model that made my RAG detector work was the one I had to delete" by Hiya Lodha
#amazon-bedrock #amazon-bedrock-agents #rag
@ipolyzos.comA fascinating RAG problem: deleting a record may not completely remove its influence on future retrieval.
API-level deletion ≠ semantic erasure.
@0xdanieltran.bsky.socialLocal embedding chatbot ensures zero‑trust data flow. Build with difines.org/ai and stay compliant with GDPR. Perfect for regulated crypto services. #AI #RAG #Compliance
@latreon.bsky.socialBundles Ollama, Open WebUI, n8n, ComfyUI, and RAG into a single local stack. Instead of manually stitching together local AI tools, ODS turns your PC or Mac into a private AI server.
Up 260 stars over seven days.
https://github.com/Osmantic/ODS
#Python #AI #LLM #RAG #AIAgents
@communityaws.bsky.social"RAG from Basics to Advanced (Part 3): What Actually Happens Inside Retrieval" by Pawan Sharma
@jissonews.bsky.social10月14日(水)13:00-17:15に、エレクトロニクス実装学会 #JIEP 生成AI実装技術研究会が公開研究会『生成AIの本質〜対象の自然言語表現とその産業応用』を開催。講演4件。LLM/Transformerの基礎、外観検査結果の言語表現とRAGフィードバック、RAGを置き換えるサロゲートモデル(交通誘導ロボット)、Google Colab＆OllamaでのRAG構築体験。杉並区・回路会館およびオンラインにて。詳細は jiep.or.jp/tech-comm... に。
#Seminar #GenerativeAI #RAG
@aiblogpost.bsky.socialVector Database Selection Guide: Pinecone, Weaviate, and Chroma Compared
Discover how to pick the right vector database for your AI workloads. A deep dive into Pinecone, Weaviate, and Chroma with feature…
https://ai-blog-seven-wine.vercel.app/en/posts/2026-09-08-am-pwf3o
#vector-database #AI #RAG
@orioltic.bsky.social
@djaouadfrih.bsky.social⚡ RAG vs Fine-Tuning Which one do you need? RAG is for external knowledge. Fine-tuning is for behavior. Comment RAG for the comparison sheet. #RAG #FineTuning #LLM
@bastacon.bsky.social🧠 LLM + eigene Daten? Genau da kommt #RAG ins Spiel.
Thorsten Kansy zeigt auf @entwicklerde.bsky.social:
🔎 Azure AI Search
🗄️ SQL Server 2025
⚙️ .NET 10
🔐 Security & Kosten
👉 Jetzt auf entwickler.de lesen:
https://tinyurl.com/447ns3xe
@avatarbot-mtbs.bsky.social