Johannes Rabauer

Quanta Live: Building Local AI Search with pgvector & LangChain4j - Part 2 Building Quanta (Part 2) – Vector Search with Quarkus, pgvector & OllamaIn this session, we’re diving deep into the brains of Quanta — the part that makes it...

🎥 Watch the replay → youtube.com/live/cY2anCL...
📦 Code → github.com/JohannesRaba...
#AI #LangChain4j #Quarkus #Ollama #pgvector #LocalAI #LiveCoding

Quanta Live: Building Local AI Search with pgvector & LangChain4j - Part 2 Building Quanta (Part 2) – Vector Search with Quarkus, pgvector & OllamaIn this session, we’re diving deep into the brains of Quanta — the part that makes it...

No cloud, no GPUs, no expensive APIs.
Just open-source tools working together to make local AI useful and fun.

I am still adding a few finishing touches, but the core search flow is already complete.

In this session we:
🧩 Extracted text with Apache Tika
🧠 Created embeddings using Ollama (LLaMA 3.2)
💾 Stored them in PostgreSQL with pgvector
🔍 Queried files semantically with Quarkus and LangChain4j

And it works beautifully.

Quanta Part 2 is done! 🎉
We now have a fully working AI file searcher that can vectorize your files and let you search them using natural language.

All running locally with Quarkus, Ollama, and pgvector.

😱

Thanks very much, Catherine!
It will be a lot of fun, no matter the outcome 🤦🏻‍♂️🤓

Really looking forward to it!

Quanta Live: Building Local AI Search with pgvector & LangChain4j - Part 2 Building Quanta (Part 2) – Vector Search with Quarkus, pgvector & OllamaIn this session, we’re diving deep into the brains of Quanta — the part that makes it...

AI is more accessible than ever. No GPUs, no fancy infrastructure, no giant models needed.
Just you, some open-source tools, and a bit of curiosity. 🤓
Join me live as we build an AI file searcher using Quarkus, Ollama, and pgvector.

🎥 Join here → youtube.com/live/cY2anCL...

I'm so happy the idea catches on! I truly look at them every day 🤓

We are going live today, in just 2 hours! See you there😊

Really looking forward to some comparisons between frameworks 🤓

Is there a place with "best-practice-guardrails" or something similar? It seems like an awful chore to think of every possible unwanted in- and output and put that into code...

Securing LLM Responses in Java: Guardrails with Quarkus and LangChain4j

Securing LLM Responses in Java: Guardrails with Quarkus and LangChain4j
Learn how to protect your AI applications from prompt injection, unsafe outputs, and risky prompts with practical guardrail patterns in Quarkus.

www.the-main-thread.com/p/java-quark...

It looks like you changed passwords since the leak: I tried to login to localhost:8080 with password "pw", but access was denied 😂

Good for you! :)

GitHub - JohannesRabauer/quanta: ai-file-search - lets you find files in a natural language way and summarizes files ai-file-search - lets you find files in a natural language way and summarizes files - JohannesRabauer/quanta

🧠 Open-source & still evolving:
github.com/JohannesRaba...

What would you add next, smarter summaries, multi-agent explorers, or something wild?
#LangChain4j #Quarkus #Ollama #pgvector #ApacheTika #AI #Java #LLaMA3

Quanta tracks file changes, re-vectorizes updates, and returns instant, intelligent answers; all locally.
We debugged Quarkus quirks, Tika headaches, and got Ollama humming 💪
youtube.com/live/OenMqG5...

Under the hood:
⚡ Next.js (frontend)
☕ Quarkus + LangChain4j (backend brains)
🦙 Ollama (LLaMA 3.2 embeddings)
🐘 PostgreSQL + pgvector
📄 Apache Tika for text extraction from any file type

Just went live building Quanta: an AI-powered file searcher that understands your files 🤖📂
It watches your filesystem, vectorizes docs, and lets you query them in natural language.
Let’s make local AI search actually useful 👇

Favorite input field 😅

Unfortunately because of an emergency in the family i have to postpone the session again...i am really sorry.

Thank you very much! :)

Happy birthday Catherine! :)

Thanks! I am unsure about PostgreSQL with pgvector, but since i have the most experience with it, i'm willing to try ^^
Why did you choose PostgreSQL, if you did?

Building Quanta – An AI File Searcher with Next.js, Quarkus, Ollama & PostgreSQL (Live Coding) In this live coding session, we’re starting Quanta – an AI-powered file searcher that can watch your filesystem, vectorize documents, and let you search & su...

I’ll be building Quanta live on stream. 🎥
Join, ask questions, and help me shape it as we go.

Follow along — this will be fun. 🚀
www.youtube.com/live/OenMqG5...

#AI #LangChain4j #Quarkus #Nextjs #Ollama #pgvector #LocalAI #LiveCoding

To make this work, I’m combining:
⚡ @nextjs.org frontend
⚡ @quarkus.io + @langchain4j.dev backend
⚡ Ollama (LLaMA 3.2) for AI
⚡ PostgreSQL + pgvector for embeddings

A lot of moving parts → one AI-powered file explorer.

Quanta will:
📂 Scan your filesystem
🗂️ Catalogue files automatically
📝 Summarize their contents
🔍 Let you find them later with natural language search

No more “where did I save that doc?” moments.

After building an AI storytelling app for fun…
…it’s time to create something actually useful. 🚀

Meet Quanta – an AI file searcher.

Excited to welcome Johannes Rabauer as our newest Oracle ACE Associate! 🚀
Johannes crafts secure, scalable Java solutions. Cloud, AI, frameworks & clean code—he’s passionate about making developers’ lives easier.
Learn more: ace.oracle.com/ords/ace/pro...
#OracleACE

A smiling man wearing glasses, a black t-shirt, and a lanyard points to an Oracle ACE Associate certificate. The certificate is awarded to Johannes Rabauer in recognition of technical and community leadership contributions to Oracle communities from July 2024 to August 2025. It is signed by Gerald Venzl, VP of Database Product Management, ACE Program, and dated September 2025. In the background, there is an illustration of a golden trophy with a spade symbol.

Just unlocked a new achievement: 🏆 Oracle ACE Associate!
Big thanks to the Oracle community 🙌
Catch me dropping Java wisdom at JCON or on YouTube 😂
#OracleACE #Java #DevCommunity @oracleace.bsky.social

Can We Give Our AI Agents Real Memory? (LangChain4J + Ollama + Java Live Coding) Part 11 – Giving Agents Real Memory in LangChain4J (Live Java Coding with Ollama)In this live session, we’ll tackle one of the hardest (and most exciting) ch...

Part 10: Agents came alive in LangChain4J + Ollama 💡
Part 11 (Sat 20:00 CET): Can we give the entire system memory that persists in PostgreSQL?
One landscape, many agents, real continuity.
Join the experiment 👉 youtube.com/live/Jpid86_...
#Java #AIAgents