Dev-focused LLM training: 2-day hands-on in Berlin!

💯 Prompts + tools, RAG (pgvector), LangChain/LangGraph, FastAPI, LoRA/QLoRA.

Mar 16–17 or May 18–19, 2026. More information and registration: ▶️ https://www.fokus-akademie.de/en/courses/llm-training-basic.html

#LLM #GenerativeAI #AIEngineering #Python #FastAPI

Legacy code is inevitable. 🔍

At #ArcOfAI, Venkat Subramaniam explores how AI can complement our thinking by scanning complex legacy systems, surfacing potential issues, and helping us reason more clearly about difficult code.

https://www.arcofai.com/speaker/7e0794827e8242ef8464e383e1209fad

🎟️ Tickets: https://arcofai.com

#ArcOfAI #AIEngineering #SoftwareArchitecture #LegacyCode #CleanCode #DeveloperTools #GenerativeAI #TechLeadership #SoftwareDevelopment

Experiencing indirect prompt injection when building #AI applications?

That's a key reason to use a #RAG pipeline instead of an #MCP server when building an application for untrusted users.

See https://docs.pgedge.com/pgedge-postgres-mcp-server/v1-0-0-beta2/guide/mcp-vs-rag/ for more insights 👀

#aiapps #appdev #aidev #aiengineering #llm

RAG (Retrieval Augmented Generation) is the solution. Here's how to build your own RAG server from scratch using ollama, Open WebUI and Chroma DB!

✅ Document processing ✅ Vector embeddings ✅ Smart retrieval ✅ Production-ready API

https://www.alanbonnici.com/2026/02/how-to-create-local-rag-enabled-llm.html

#RetrievalAugmentedGeneration #RAG #AIEngineering #LLM #Python #TTMO #OpenSource #AI

AI Engineer (@aiDotEngineer)

세계적인 AI 엔지니어링 컨퍼런스가 마이애미에서 열린다는 안내입니다. AIEMiami 주최로 ReactMiamiConf 팀이 운영하며 엔지니어, 창업자, 기술 리더를 위한 엄선된 세션과 네트워킹 기회를 제공합니다. 행사 사이트(ai.engineer/miami)로 등록 및 정보 확인 가능하다고 홍보하는 공지입니다.

https://x.com/aiDotEngineer/status/2021277187723403497

#ai #conference #aiengineering #miami

🚀 Big Data meets AI—powered by Iceberg, Spark & LLMs

At #ArcOfAI, Pratik Patel shows how to build a real architecture that lets users query massive datasets with natural language—no dashboards, no SQL, just questions & insights.

https://www.arcofai.com/speaker/1c241471d7f04018a0da70efffd35b32

🎟️ Get tickets: https://arcofai.com

#ArtificialIntelligence #BigData #DataArchitecture #ApacheSpark #ApacheIceberg #LLM #GenAI #EventStreaming #Kafka #Flink #AIEngineering #TechLeadership

We’re excited to welcome Azul as a Premium Supporter of Arc of AI! 🎉

Their support helps deliver hands-on AI learning, practical workshops, and the kind of peer connections that help teams ship better AI systems. We’re excited to build this experience together in April.

🔗 Become a supporter: https://www.arcofai.com/supporters

🎟️ Tickets: https://arcofai.com

#ArcOfAI #AICommunity #AIEducation #AIEngineering #Java #DeveloperCommunity #TechEvents #ArtificialIntelligence #MachineLearning

Query rewriting is where many RAG systems quietly succeed or fail.

Before embeddings. Before vector search.
Right at the boundary between user intent and retrieval.

I wrote a hands-on Java guide showing how to implement Query Transformers with LangChain4j and Quarkus Easy RAG, and why this step matters for predictable retrieval.

https://www.the-main-thread.com/p/query-rewriting-rag-java-langchain4j-quarkus

#Java #Quarkus #LangChain4j #RAG #LLM #AIEngineering #OpenSource #Fediverse

#AIEngineering #swemistakes #microservices

https://codegood.co/writing/the-microservice-that-should-have-been-a-function

Our open-source #MCP server knows how to explore and understand the #PostgreSQL database schema. 📚

If a knowledgebase package is installed, the server will have semantic search capabilities, even over any data you might have embeddings for in the database - even with no prior schema knowledge.

This means you can use it with #Claude Code without preloading a schema file. 🐘

Try it on #GitHub: https://github.com/pgEdge/pgedge-postgres-mcp

#claudecowork #claudecode #llm #ai #aidev #postgres #opensource #aiengineering