Public feed · Elektrine

View on Loforo »

Photodromm - Claire Click It! …For the best image. #NSFW #adult #erotic #sexy #nude

When mixing chat memory with RAG, follow-up questions make perfect sense to people, but not to your vector store. This recipe shows how to make RAG conversation-aware by folding chat history into retrieval queries. https://medium.com/@thetalkingapp/spring-ai-recipe-making-rag-conversation-aware-189b82a37060 #SpringAI #RAG #Java #LLM #VectorSearch #GenAI

@habuma@fosstodon.org ##4932825

Claude Code isn&#39;t the only place you can use Markdown-defined subagents. In this week&#39;s Spring AI Recipe, learn how to create Claude-style subagents and wire them into Spring AI with TaskTool. https://thetalkingapp.medium.com/spring-ai-recipe-defining-claude-style-subagents-9563644b9121 #SpringAI #Java #AgenticAI #AIAgents #LLM

@habuma@fosstodon.org ##4932824

Today&#39;s Spring AI recipe is giving me some technical challenges. As such, I find myself delaying publication of the recipe until I sort out the issues. I hope that you&#39;ll accept my apologies for the delay. I hope to get it working and publish the recipe tomorrow. Otherwise, I&#39;ll set it aside and give you a different recipe tomorrow.

@habuma@fosstodon.org ##4932823

Vector similarity finds what’s relevant. Metadata filtering makes sure your RAG pipeline finds what’s relevant and applicable. This Spring AI Recipe shows how to filter vector searches using document metadata. https://medium.com/@thetalkingapp/spring-ai-recipe-filtering-rag-results-with-metadata-bef2f8a7cb72 #SpringAI #Java #RAG #VectorSearch #GenAI

@habuma@fosstodon.org ##4932822

Graph-based workflows give you explicit control over how an agent moves from one task to the next. In this recipe, see how to build graph-based workflows with LangGraph4j and Spring AI. https://medium.com/@thetalkingapp/spring-ai-recipe-building-a-graph-based-agentic-workflow-with-langgraph4j-0fbfcce25a57 #SpringAI #LangGraph4j #AgenticAI #Java

@habuma@fosstodon.org ##4932821

I&#39;ve upgraded the code for my Spring AI recipes that cover Embabel to build against Embabel 1.5.0 (and therefore, Spring Boot 4.1.0). Enjoy! - Embabel recipes: https://www.habuma.com/springairecipes/#embabel - Recipes code: https://github.com/habuma/spring-ai-recipes #SpringAI #Embabel #SpringBoot #AgenticAI

@habuma@fosstodon.org ##4932820

You don&#39;t need a full-blown agent framework to build an agent. If you&#39;ve used Spring AI&#39;s ChatClient with tools, you may already be using one of the most fundamental agentic patterns: ReAct. See how in today&#39;s Spring AI Recipe. https://medium.com/@thetalkingapp/spring-ai-recipe-reasoning-and-acting-react-30d364955c2f #SpringAI #Java #AgenticAI #ReAct #AIAgents

@habuma@fosstodon.org ##4932819

In today&#39;s Spring AI Recipe, we see how playing &quot;HyDE and seek&quot; gives better results from RAG queries. https://medium.com/@thetalkingapp/spring-ai-recipe-better-rag-results-with-hyde-1d2d360a1b58 #SpringAI #Java #RAG #HyDE #GenAI

@habuma@fosstodon.org ##4932818

Vector search understands what you mean. BM25 finds the exact terms you use. Why choose? In this Spring AI Recipe, we combine them with hybrid search and Reciprocal Rank Fusion to get the best of both worlds. https://medium.com/@thetalkingapp/spring-ai-recipe-better-rag-results-with-hybrid-search-6e6ab2d09003 #SpringAI #RAG #HybridSearch #BM25 #Java

@habuma@fosstodon.org ##4932817

Retrieval found the documents. But are they really the best documents to put in your prompt? In this Spring AI Recipe, we apply reranking to ensure the most relevant context. https://medium.com/@thetalkingapp/spring-ai-recipe-better-rag-results-with-reranking-37c76fb325da #SpringAI #Java #RAG #Reranking #GenerativeAI

@habuma@fosstodon.org ##4932816

As your AI application gains more tools, do you really need to send all of them to the LLM on every request? In this Spring AI Recipe, I show how ToolSearchTool discovers the right tools on demand, keeping prompts lean as your toolbox grows. https://medium.com/@thetalkingapp/spring-ai-recipe-efficient-tool-use-ab9f57abf45f #SpringAI #Java #AgenticAI

@habuma@fosstodon.org ##4932815

Want to run Spring AI against a local LLM? This recipe shows how to use open-weight models with LM Studio, Docker Model Runner, and Ollama, with surprisingly few changes to your app. 🔗 https://medium.com/@thetalkingapp/spring-ai-recipe-running-against-local-llms-3b7af32f035b #SpringAI #Java #LocalLLM #GenAI

@habuma@fosstodon.org ##4932814

How local can a local LLM get? With ModelJars and Models, you can skip the model server entirely and run inference inside the same JVM as your Spring AI application. See how in this Spring AI Recipe! https://medium.com/@thetalkingapp/spring-ai-recipe-running-against-an-in-jvm-model-70311a054eaf #SpringAI #Java #LocalLLM #GenerativeAI #ModelJars

@habuma@fosstodon.org ##4932813

Conversational memory helps an AI remember what you&#39;ve talked about. But the longer the conversation runs, the more context it has to carry around. What if it could remember the important stuff without remembering every word? https://medium.com/@thetalkingapp/spring-ai-recipe-summarizing-chat-memory-e61236ac05cd #SpringAI #Java #SpringBoot #GenerativeAI #ChatMemory #SpringAIRecipes

@habuma@fosstodon.org ##4932812

Securing an MCP server with an API key is easy, but sometimes you need something more robust. In this recipe, we’ll put OAuth 2.0 to work with Spring AI to secure an MCP server. https://medium.com/@thetalkingapp/spring-ai-recipe-securing-an-mcp-server-with-oauth-01496ca9e17e #SpringAI #MCP #OAuth2 #SpringSecurity #Java #AgenticAI

@habuma@fosstodon.org ##4932811

Even when an LLM has all the facts it needs, it can still get them wrong. Let&#39;s explore FactCheckingEvaluator and discover why fact-checking AI responses isn&#39;t always as straightforward as it seems. https://medium.com/@thetalkingapp/spring-ai-recipe-fact-checking-ai-responses-43de77740493 #SpringAI #Java #AIEvaluation #FactChecking

@habuma@fosstodon.org ##4932810

Fact-checking an entire AI response can hide unsupported claims. What if you decompose the response and fact-check each claim individually? https://medium.com/@thetalkingapp/spring-ai-recipe-decomposing-answers-into-claims-for-fact-checking-49861bed1374 #SpringAI #Java #AIEvaluation #FactChecking

@habuma@fosstodon.org ##4932809

What if you could run a Spring AI application without a Maven or Gradle project? In this Spring AI Recipe, see how JBang turns a few Java files into a runnable Spring AI chat loop. https://medium.com/@thetalkingapp/spring-ai-recipe-a-no-build-chat-loop-with-jbang-36cee6039980 #SpringAI #Java #JBang #SpringBoot

@habuma@fosstodon.org ##4932808

Why should a Java-based STDIO MCP server need a build step before a client can run it? With JBang, it doesn’t. You can build Spring AI MCP servers and clients that run straight from Java source. https://medium.com/@thetalkingapp/spring-ai-recipe-no-build-mcp-with-jbang-8b26ce148cf1 #SpringAI #MCP #JBang #Java #SpringBoot

@habuma@fosstodon.org ##4932807

What if you don’t need an LLM to generate an answer, but simply need AI to make a judgment? In my latest Spring AI Recipe, I explore Jev, System One models, and fast, structured AI judgments. https://medium.com/@thetalkingapp/spring-ai-recipe-making-ai-judgments-with-jev-12ee580ae976 #SpringAI #Java #Jev #SystemOne

@triploidtree@mastodon.ie ##4932806

Craft night this evening at @tog from 1830 to 2030 Do drop by, bring some crafty project to work on. People are friendly, you&#39;ll find some of the @lovelacespace folks to chat to. Me, I might add a button to the heather blazer, mess with inkstitch, knit, or try to plan some workshops (hey @chebe &lt;3 ) See you there!

@arnobert@chaos.social ##4932805

CQ POTA, CQ WSA. Great evening in DE-0795, 79 QSOs on 2 and 70. #hamradio