Weaviate

Single vs. Multi-Agent Systems: Which is right for your project? Learn all the key patterns in multi-agent systems and download our free ebook to get you started! We cover: - Single vs multi-agent systems - Patterns in multi-agent systems - 6 examples of agentic architectures - ... and much more! Download https://lnkd.in/gRdNCgf2

Missed our last intro to Weaviate? We’re running it back on August 19 — same solid content, fresh chance to join in live. This session is for anyone building with AI who wants to see: • How Weaviate works under the hood (beyond the “vector DB” label) • The difference between hybrid, semantic, and keyword search — and when to use which • How to plug it into your GenAI stack for RAG, agents, and other real-world patterns • A live demo + Q&A so you can get answers right away If you’re dealing with embeddings, search, or scaling LLM-powered apps, this will help you skip guesswork and start building faster. 📅 August 19 — 9am PT / 12pm ET / 6pm CET 🔗 https://lnkd.in/eDP-UnF3 Come see what Weaviate can do — and how to make it work for you.

Two terminal commands. That’s all it takes to build an agentic RAG app. And yes, using your own data. If you’ve spent time with AI chatbots, you’ve probably noticed they’re often black boxes: Text in, Text out, and you’re left guessing how they got there… Now, what if you could watch the entire reasoning process, all the steps the LLM takes, what it looks at, and why it chooses one answer over another? That’s what 𝗘𝗹𝘆𝘀𝗶𝗮, an open-source agentic framework from Weaviate makes possible. It’s built to make AI interactions transparent while working intelligently with your data. Setup takes two commands: 1. pip install elysia-ai 2. elysia start So what makes it different? 🌳 𝗗𝗲𝗰𝗶𝘀𝗶𝗼𝗻 𝗧𝗿𝗲𝗲 𝗔𝗿𝗰𝗵𝗶𝘁𝗲𝗰𝘁𝘂𝗿𝗲: Watch in real-time as the AI traverses its decision tree, showing you exactly what tools it's considering and why. No more wondering "how did it come up with that?" 📊 𝗗𝘆𝗻𝗮𝗺𝗶𝗰 𝗗𝗶𝘀𝗽𝗹𝗮𝘆 𝗙𝗼𝗿𝗺𝗮𝘁𝘀: While other assistants are stuck with text responses, Elysia intelligently chooses from seven display types - tables, product cards, charts, documents, and more. It analyzes your data structure and automatically selects the most appropriate format. 🧠 𝗔𝘂𝘁𝗼𝗺𝗮𝘁𝗶𝗰 𝗗𝗮𝘁𝗮 𝗔𝘄𝗮𝗿𝗲𝗻𝗲𝘀𝘀: Unlike traditional RAG systems that perform blind vector searches, Elysia actually understands your data structure before querying. It generates metadata, creates summaries, and builds a comprehensive understanding of what's available. The technical stack is refreshingly simple - powered by Weaviate for all retrieval operations, with DSPy handling LLM interactions. But the real magic is in the pure Python decision logic that orchestrates everything. Out of the box, it connects to your Weaviate cluster and performs intelligent searches using just natural language - automatically generating filters and search parameters. 𝘛𝘩𝘦 𝘦𝘯𝘵𝘪𝘳𝘦 𝘱𝘳𝘰𝘫𝘦𝘤𝘵 𝘪𝘴 𝘰𝘱𝘦𝘯 𝘴𝘰𝘶𝘳𝘤𝘦 - use it as-is for data search, or customize it with your own tools for any agentic AI use case. It’s also shipped with a nice UI. How to get started: GitHub: https://lnkd.in/dRG5m9ad Demo: https://elysia.weaviate.io Blog: https://lnkd.in/dDYggfFk #ai #rag #agentic

Start CRUD'ing with Weaviate in 60 seconds: Step 1: https://lnkd.in/euJnPpiX Step 2:

AI chatbots have a problem They’re text in → text out machines. No memory of how you want results shown. No understanding of your data’s structure. No transparency into their reasoning. But… meet Elysia from Weaviate (100% Open-source) It’s an open-source, agentic RAG framework that doesn’t just answer, it decides, explains, and adapts. Think: ▹AI that picks the right tools at the right time. ▹AI that knows whether a query is even possible. ▹AI that chooses the best way to display results, table, chart, conversation view, e-commerce card. ▹AI that learns from your feedback over time, getting faster and cheaper without losing quality. 𝐓𝐡𝐞 𝐭𝐡𝐫𝐞𝐞 𝐩𝐢𝐥𝐥𝐚𝐫𝐬 𝐭𝐡𝐚𝐭 𝐦𝐚𝐤𝐞 𝐄𝐥𝐲𝐬𝐢𝐚 𝐝𝐢𝐟𝐟𝐞𝐫𝐞𝐧𝐭 1️⃣ Decision Tree Agents A pre-defined web of nodes, each a possible action, navigated by agents with global context. They track past decisions, predict future ones, handle errors, and give you real-time visibility into every step. 2️⃣ Dynamic Data Displays Not all data should be shown as plain text. Elysia analyzes your collections, maps them to optimal formats, and can even enable actions directly from those views (think: “Add to cart” from a product card). 3️⃣ Automatic Data Expertise Before it ever searches, Elysia inspects your data’s structure, generates metadata, and understands relationships, avoiding the blind, hit-or-miss vector searches most RAG systems rely on. 𝐄𝐧𝐠𝐢𝐧𝐞𝐞𝐫𝐢𝐧𝐠 𝐡𝐢𝐠𝐡𝐥𝐢𝐠𝐡𝐭𝐬 ▹Chunk-on-Demand - No expensive pre-chunking; documents are chunked only when relevant. ▹Multi-Model Strategy - Small models for quick reasoning, big models for deep tool operations, fully configurable. ▹tatic Frontend Serving - Entire NextJS UI shipped via FastAPI in one pip install. ▹Feedback Memory - Uses your positively rated queries to improve future answers (even with smaller models). Elysia moves beyond the "Ask–Retrieve–Generate" loop. [ Check comments section for the 𝐃𝐞𝐦𝐨 ]

𝐄𝐥𝐲𝐬𝐢𝐚: 𝐀𝐧 𝐀𝐠𝐞𝐧𝐭𝐢𝐜 𝐅𝐫𝐚𝐦𝐞𝐰𝐨𝐫𝐤 𝐏𝐨𝐰𝐞𝐫𝐞𝐝 𝐛𝐲 Weaviate A new agentic framework, Elysia, has been introduced. This platform is designed to use tools in a decision tree format, where an agent dynamically decides which tools to use based on its environment and context. Here's a quick look at the key details: - 𝐂𝐨𝐫𝐞 𝐅𝐮𝐧𝐜𝐭𝐢𝐨𝐧𝐚𝐥𝐢𝐭𝐲: Elysia's decision agent framework enables dynamic tool usage within a decision tree structure. - 𝐂𝐨𝐦𝐩𝐚𝐧𝐲 𝐈𝐧𝐭𝐞𝐠𝐫𝐚𝐭𝐢𝐨𝐧: The framework is pre-configured to connect and interact with Weaviate clusters, using built-in query and aggregate tools to handle data retrieval. - 𝐊𝐞𝐲 𝐂𝐨𝐧𝐭𝐫𝐢𝐛𝐮𝐭𝐨𝐫: Danny James Williams is noted for his recent work, including a significant merge request and updates to the README. - 𝐀𝐜𝐜𝐞𝐬𝐬𝐢𝐛𝐢𝐥𝐢𝐭𝐲: Elysia is available as a Python package, requiring Python 3.12, and can be installed via pip install elysia-ai. The project is currently in beta, and its development can be followed on the official GitHub repository. Github: https://lnkd.in/es_GzDgu For the latest updates and information, follow us @ World AI 360

I’ve lost count of how many RAG demos I’ve seen that break as soon as the data is messy or the query is ambiguous. Building with a decision-tree approach, dynamic displays, and feedback loops is the practical engineering needed to make these systems reliable. Elysia 🦾 Great job team Weaviate. Victoria Slocum | Danny Williams | Edward Schmuhl | Philip Vollet | Femke Plantinga Love the name Elysia. Always curious about the naming stories, how did this one come about?

Build a 100% local RAG pipeline with OpenAI’s GPT-OSS and Weaviate! Check it out: https://lnkd.in/d7JN3PpD

We just released an open source framework that sets up agentic search and RAG in a full web UI on your own data in just two terminal commands. Meet Elysia - a decision tree based agentic system that dynamically displays data, learns from user feedback, and chunks documents on-demand. Most AI chatbots are stuck in a text-in, text-out world. But what if your AI could dynamically decide not just what to say, but 𝗵𝗼𝘄 𝘁𝗼 𝘀𝗵𝗼𝘄 𝗶𝘁? Elysia is designed to completely rethink how we interact with data through AI. Three features that set it apart: 🌳 𝗗𝗲𝗰𝗶𝘀𝗶𝗼𝗻 𝗧𝗿𝗲𝗲 𝗔𝗿𝗰𝗵𝗶𝘁𝗲𝗰𝘁𝘂𝗿𝗲: Unlike simple agentic platforms, Elysia uses a pre-defined web of nodes, each orchestrated by a decision agent that evaluates its environment and strategizes the best tool to use. You can watch the entire decision process in real-time. 🎨 𝗗𝘆𝗻𝗮𝗺𝗶𝗰 𝗗𝗶𝘀𝗽𝗹𝗮𝘆 𝗙𝗼𝗿𝗺𝗮𝘁𝘀: Elysia can choose from 7 different ways to present your data - tables, product cards, tickets, conversations, documents, charts, and more. It automatically analyzes your data structure and picks the most appropriate format. 🧠 𝗔𝘂𝘁𝗼𝗺𝗮𝘁𝗶𝗰 𝗗𝗮𝘁𝗮 𝗘𝘅𝗽𝗲𝗿𝘁: Connect your Weaviate Cloud instance and Elysia becomes an instant expert on your data. It analyzes collections, generates metadata, and understands your data structure before performing any queries. Getting started is ridiculously simple: pip install elysia-ai elysia start That's it. You get a full web interface AND a Python library. Bonus features we're excited about: • Chunk-on-demand: No more pre-chunking everything • Feedback system that learns from your preferences • Multi-model strategy for cost optimization • Everything runs from a single Python package We're already using Elysia to power the chat interface in our AI skincare app, Glowe. The entire project is open source and designed with customization in mind. Get started: 🔗 GitHub: https://lnkd.in/es_GzDgu 📖 Demo: https://elysia.weaviate.io 🎮 Blog post: https://lnkd.in/ewJ_BeJi