#langchain4j — Public Fediverse posts

🤖 AI systems are moving beyond prompts to agents that plan, act and interact.
At #BaselOne26, Lize Raes explains why agents aren't a passing hype, but a design pattern for building robust AI systems.

Using #LangChain4j and #Embabel, she shows how #Java combines agentic AI with type safety, reliability and testability.

🎙️ Full program: https://baselone.org/#programm

🎟️ Get your tickets: https://eventfrog.ch/BaselOne26

#AgenticAI #SoftwareEngineering #BaselOne

LLMs anzubinden ist einfach. Eine produktionsreife KI-Anwendung zu bauen, ist die eigentliche Herausforderung. Jean-Claude Brantschen zeigt, wie LangChain4j parallele Multi-LLM-Anfragen, Memory, Tools und sogar einen Chatbot mit Web-UI elegant in Java umsetzt.👉 https://javapro.io/de/langchain4j-teil-2/

#Java #LangChain4j #KI #LLM

Warum für KI-Projekte Python lernen, wenn dein Team bereits Java beherrscht? Jean-Claude Brantschen zeigt, wie LangChain4j OpenAI, Claude, Gemini und Ollama über dieselbe API verbindet – mit weniger Boilerplate und mehr Typsicherheit. Mehr erfahren: https://javapro.io/de/langchain4j-teil-1/

#Java #AI #LLM #LangChain4j #OpenAI

Connecting ☕ #Java 25 + 🦜 #langchain4j 1.18.0 to local #MLX (via OpenAI-compatible API server).
Sub-10ms TTFT, 100% offline & private! ⚡

Kevin Dubois & Mario Fusco tested whether a code assistant could design a multi-agent system using only the LangChain4j documentation.

The result? A multi-agent system capable of writing, testing, and debugging code like human engineers.

📰 Check out the #InfoQ article to see how the experiment went, what worked, and what the resulting project looks like 👉 https://bit.ly/4yXe1Ds

#Java #AI #LangChain4j #AgenticAI

As it's still built in #Java with the #micronaut framework, the #langchain4j LLM orchestration library, and @graalvm, you can download pre-built binaries from GitHub for your platform of choice:
https://github.com/glaforge/antigravity-brain-visualizer/releases/tag/v0.4.1

#AI can query your DB—but can it do it correctly? That’s the hard part. @MarcoBelladelli shows how #Hibernate + #Quarkus + #LangChain4j add validation & control back. Want fewer production surprises?

Dive in: https://javapro.io/2026/04/03/talk-to-your-data-natural-language-data-access-in-java/

#LLM #Java @Hibernate @QuarkusIO @langchain4j

What happens when one #AI call isn’t enough? You don’t add more prompts—you add agents. @kevindubois & Laura Cowen show how enterprise AI really scales.

Curious how production systems are built? Dive in: https://javapro.io/2026/03/31/agentic-ai-patterns-for-enterprise-software/

#Quarkus #LangChain4j #Microservices @QuarkusIO

As #AI applications grow, prompts become workflows—and workflows become systems. Read @LoMagnette's guide to mastering #LangChain4j Agentic Workflows, from simple agents to supervisor patterns, error handling & production-ready orchestration: https://javapro.io/2026/07/08/langchain4j-agentic-workflows-from-ai-calls-to-multi-agent-systems-in-java/

Confused by the exploding number of #AI tools in the #JVM ecosystem? Teams mix #SpringAI, #LangChain4j, MCP & #Ollama without understanding the layers underneath. Artur Skowronski explains what each part of the #Java AI stack is actually for: https://javapro.io/2026/06/03/the-gen-ai-iceberg-java-tooling-edition/

@langchain4j

Chat memory gets fuzzy fast once the UI hides what LangChain4j is actually retaining.

I wrote a Quarkus tutorial that makes retained-memory pressure visible with `TokenWindowChatMemory`, Ollama request counts, a turn ledger, and OpenTelemetry attributes. The useful split is simple: your app-level eviction budget is not the model context limit. https://www.the-main-thread.com/p/quarkus-langchain4j-chat-memory-budget #Java #Quarkus #LangChain4j #Ollama #OpenTelemetry

Local AI gets risky when the first confident answer becomes the system answer.

I wrote a Quarkus tutorial that sends the same text to two Ollama models, uses Quarkus Signals to escalate only on disagreement, and keeps `UNCERTAIN` separate from `FAILED`. https://www.the-main-thread.com/p/quarkus-langchain4j-ollama-signals #Java #Quarkus #LangChain4j #Ollama

Most #AI prototypes work. Until the next model update breaks half the system. Lutske de Leeuw & Maarten Vandeperre show how #CleanArchitecture, ports & adapters keep AI integrations from becoming spaghetti code.

Read: https://javapro.io/2026/03/17/ai-without-spaghetti-clean-architecture-in-the-age-of-ai/
#LangChain4j #Quarkus QuarkusIO #LLM

Our next #JCON2026 session is live: 'Talk to Your Data: Natural Language Data Access in #Java with #Hibernate #Quarkus and LangChain4j' with Marco Melladelli

Explore how Hibernate ORM, Quarkus, and #LangChain4j come together to enable …

Grab your coffee and hit play: https://youtu.be/tMW5jxX6DoA

LangChain4j CDI 1.3.1 released -- simpler Human-in-the-Loop agents, @RegisterSimpleAgent alignment, nested scope fix, new WildFly example, and LangChain4j 1.15.1. AI + Jakarta EE keeps getting better! #Java #AI #JakartaEE #OpenSource #langchain4j

Tired of stitching #AI SDKs into your #JakartaEE stack manually? #LangChain4J-CDI lets you declare an interface, annotate it, & inject it anywhere — REST, EJB, schedulers. @EliteGentleman demonstrates the model-driven approach.

Worth a closer look? Read: https://javapro.io/2026/02/25/bring-ai-into-your-jakarta-ee-apps-with-langchain4j-cdi-formerly-smallrye-llm/

Confused by the exploding number of #AI tools in the #JVM ecosystem? Teams mix #SpringAI, #LangChain4j, MCP & #Ollama without understanding the layers underneath. Artur Skowronski explains what each part of the #Java AI stack is actually for: https://javapro.io/2026/06/03/the-gen-ai-iceberg-java-tooling-edition/

@langchain4j

Cheap questions should not burn the same local model as real debugging work.

I wrote a Quarkus + LangChain4j tutorial that classifies prompts, routes them between two Ollama models, and keeps the decision observable with CDI events and tests. https://www.the-main-thread.com/p/quarkus-langchain4j-model-routing #Java #Quarkus #LangChain4j #Ollama

LangChain4j: Chat With Documents

#ai #java #langchain4j

https://mydeveloperplanet.com/2024/01/24/langchain4j-chat-with-documents/

LangSmith does not need to stay in the Python corner.

I wrote a Quarkus walkthrough that sends LangChain4j traces to LangSmith over OTLP, including plain chat, tool calls, and controlled failures. It also covers the two easy footguns: /otel vs /otel/v1/traces, and region-specific endpoints.

https://www.the-main-thread.com/p/quarkus-langchain4j-langsmith

#Quarkus #LangChain4j #OpenTelemetry #Observability

🚀 langchain4j-cdi 1.2.0 is out!

🤖 @RegisterAgent: 8 agentic topologies (SIMPLE→A2A)
🔌 MCP Server support for CDI beans
⚡ ${config} & #{EL} expressions in annotations
All CDI-native, enterprise-ready.
Thanks to @yblazart.bsky.social , Buhake Sindi and Don Bourne
#Java #AI #LangChain4j #JakartaEE

Every deterministic workflow step does not need a planner call.

This piece shows how to keep MCP tools boring inside a LangChain4j graph: one Quarkus MCP server, one workflow app, /topology, and tests that hit real Ollama instead of stubs.

https://www.the-main-thread.com/p/quarkus-langchain4j-mcp-tool-agents

#Java #Quarkus #LangChain4j #MCP

Agent demos love static diagrams. Production gives you a different graph.

This post shows how to expose a live LangChain4j topology from Quarkus with AgentMonitor, HtmlReportGenerator, and an SSE feed for recent runs.

https://www.the-main-thread.com/p/quarkus-langchain4j-topology-http

#Java #Quarkus #LangChain4j #Observability

Agent names are not a routing strategy.

This walkthrough builds a Quarkus + LangChain4j sample that uses filesystem Skills to make ownership explicit, keeps a baseline supervisor for comparison, and proves the routing with HTTP tests.

https://www.the-main-thread.com/p/agent-skills-quarkus

#Quarkus #LangChain4j #Java #AIEngineering

Once a tool-calling assistant grows from 5 tools to 50, the problem stops being “prompting” and starts being context geometry.

This walkthrough builds a Quarkus + LangChain4j + Ollama example and shows what tool search actually changes: smaller working sets, visible search rounds, and more prompt headroom even when local latency is messy.

https://www.the-main-thread.com/p/langchain4j-tool-search-quarkus-ollama

#Quarkus #LangChain4j #Ollama #Java

Still building #AI with one model per request? You’re already behind. @kevindubois & Laura Cowen map the shift to agentic systems & why orchestration beats prompts.

Ready to design real AI architectures? Dive in: https://javapro.io/2026/03/31/agentic-ai-patterns-for-enterprise-software/

#Java #LangChain4j @langchain4j

In this #InfoQ article, Vignesh Durai explains how agentic and multimodal AI systems can be engineered using #ApacheCamel & #LangChain4j.

The solution combines LLM-based reasoning, retrieval-augmented generation (RAG), and image classification.

🔗 Read now: https://bit.ly/4sXdlcM

#AI #LLMs #DataPipelines

Tomorrow I’m speaking at the Bangalore JUG Special Talk on Open-Source GPU-Powered Image Generation with LangChain4j. We’ll walk through a Java-based stack using Spring, LangChain4j, ONNX Runtime, CUDA, and SD4J to build a cloud-ready image generation service with monitoring and a real-time UI.
RSVP: https://www.meetup.com/bangalorejug/events/314000765/

#Java #AI #LangChain4j #OpenSource #GPU

Exclusive Devoxx UK Discount for Quarkus Devs!

Want to catch all the supersonic, subatomic Java talks at Devoxx UK? Grab £50 off your registration with the exclusive code DVX26QUARKUS.

Don't miss the Quarkus sessions, and be sure to drop by the Quarkus Community Booth. Let's talk high-performance, cloud-native apps, and our latest Generative AI integrations with LangChain4j.

See you in London!

#DevoxxUK #Quarkus #Java #AI #LangChain4j #OpenSource #quarkusworldtour