【ざっくり理解】ベクトルDBは新しい技術なのか？ ─ 1975年からRAGまで、古いものと新しいものを分けて見る

#ベクトル検索 #べクトルDB #rag #LLM #歴史

#BizzSummitES is a wrap!

It was a great experience to be in Madrid and share the stage with my dear friend @fabiofranzini.com , talking about how we can make enterprise knowledge truly usable by #AI.
#BizzSummitES #MicrosoftCopilot #CopilotStudio #AzureAISearch #RAG #AI #MVPBuzz

Systems Thinking for Agentic AI

An LLM is powerful , but an LLM alone is not an AI system.

Now available on
📘 Leanpub
leanpub.com/staai

📗 Google Books play.google.com/store/books/...

Ediz Najim
staaicore.com

#agenticai #aiengineering #SoftwareArchitecture #LLM #RAG #MCP #SoftwareEngineering

🔧 Runs on #vLLM with Aleph Alpha's inference plugin, exposing an OpenAI-compatible API. Needs 2x A100/H100 80 GB or 1x H200/B200/B300. Best fit: on-prem #RAG over long German documents like laws, contracts and manuals

#PostgreSQL #in-process with #vectorsearch extensions directly #embedded in your #Python app. #OpenSource Apache 2.0 lic

- Similarly search: #pgvector + #pgvectorscale, high-performance storage
- #FullText search: #pg_textsearch, #BM25 and #ranking
#AI #LLM #Embeddings #Agents #RAG

After learning how RAG gives AI better context, the next question is how AI connects to the world around it.

MCP, which means Model Context Protocol, helps applications reach tools and data in a structured way, while governance defines what they can actually do.

#MCP #RAG

People ask: Michael, how do we feed Alfresco, Documentum & FileNet into AI?

1 Explain it like I’m five!
2 We built the OASIS CMIS Connector.
Java 25, Zero-Trust ACLs... That’s what she said.

👉 opencrawling.org/blog/introdu...

#TheOffice #CMIS #EnterpriseAI #OpenCrawling #RAG #Java25 #OpenSource

"I Built a RAG Pipeline. Then I Realized Retrieval Wasn't the Hard Part." by Shiven Vasan

#rag #llm #large-language-model

Ractigen Therapeutics Unveils Groundbreaking RNA Therapy Data at WMS 2026 #Japan #Hiroshima #Ractigen_Therapeutics #Duchenne_Muscular_Dystrophy #RAG-18

"Building a Serverless RAG Pipeline with Amazon Bedrock Knowledge Bases and AWS Lambda" by Mahi kumar

#aws-lambda #ai-engineering #serverless #rag #amazon-bedrock

IBM ai-services v0.3 から v0.4.0 へのマイグレーション

#IBMPower #Spyre #AI #LLM #rag

📝 Neuer Blog-Beitrag: RAG-Frameworks 2026: LlamaIndex, LangChain/LangGraph, Haystack und Co. im Vergleich

Welches RAG-Framework passt 2026 zu Ihrem Projekt? Ein Vergleich von LlamaIndex, LangChain/LangGraph, Haystack, DSPy und RAGFlow mit Entscheidungshilfe für Entwickler.

#RAG #KI #LLM

"Building My First RAG Pipeline with Bedrock" by jayanthi KS

#amazon-bedrock #knowledge-bases-for-bedrock #rag

"RAG or Fine-Tuning: Differences and When to Use Each" by Eduardo Lara

#rag #aws-community-builders #ai-assisted #chatbots #llm

"From Zero to RAG Hero: Building a Serverless Doc-QA App with Amazon Bedrock and OpenSearch Serverless" by Major Mbandi

#generative-ai #rag #amazon-opensearch #amazon-bedrock #serverless

Enterprise knowledge lives in workflows, not just static PDFs! ⚡

Alfresco Process Services is now native in OpenCrawling:
• Active & historic BPMN crawls
• Dynamic typed variables
• Candidate group ACLs
• Secure MCP Server

👉 opencrawling.org/blog/introdu...

#AI #RAG #BPMN #OpenSource

"Generative AI Fundamentals: From FMs to AWS Applications" by Dineshraj Dhanapathy

#gen-ai #rag #amazon-bedrock #large-language-model #prompt-engineering

社内の業務マニュアルを探すのに時間をかけていたり、同僚に聞いて迷惑かけていませんか？

安全な社内AIにマニュアルやPDF、Webサイトを登録すれば、AIアバターが聞くだけで必要情報を即抽出して提示してくれるよ♪
頼れる相棒の詳細はプロフノリンクから！ #AIアシスタント #RAG

Standard LLMs don't know your company's private data. RAG (Retrieval-Augmented Generation) connects smart AI models to your verified internal documents so your web assistant gives accurate answers without hallucinations or costly retraining.

Read more: www.linkedin.com/posts/samsaf...

#RAG #LLM