🔥The 9th Round of Easy Loan, Earn $40 Reward is in progress❗️ ⏰ Promotion Period: January 15th - Feburary 15th, 2025 👉 Register now and check more details at gate.io/campaigns/358

I can confirm that the star of this post is Bob van Luijt (you can confirm or deny whether you like chilli or not)

When should you consider implementing graph RAG alongside traditional RAG? Traditional RAG works great for most cases. But some apps need more. Sometimes, your application requires more than just understanding individual data points - it needs to grasp how they're connected.

Round 2 with Femke Plantinga 👇 This time, we’re covering the Weaviate Query Agent.

İstanbul’daki herkese çok geçmiş olsun 💐🧡 Benimkiler iyi, babam “pazarda yürüyordum hissetmedim” diyor. Ama herkes haliyle gergin.

The Weaviate • vector database Query Agent navigates a sea 🌊 of data in your collections to to provide the most relevant answers to user queries. On top of that, it turns out that only assuming you need to do regular similarity search over vector databases is simply not enough. SO, the query

Vector databases as knowledge based and memory for agentic AI? How? That’s what I talked about at PyCon Lithuania today 🧡 First time presenting the Weaviate • vector database Query Agent at an actual conference with the Personalization Agent making a guest appearance at the end. Slides and demo

Don’t debug with your eyes closed 👀 The Weaviate Query Agent is here to help you with all of your research tasks. Navigating through any number of collections, deciding whether to query or aggregate, taking the load off your shoulders when it comes to sifting through a maze of

🚀 Upgrade RAG to Graph RAG with Neo4j and Weaviate Naive RAG sees your data as islands. GraphRAG sees the bridges between them. By combining vector search with graph capabilities, you can: • Capture complex relationships between entities • Understand contextual networks •

Turning complex documents - with tables graphs and the whole lot - into structured data is quite a good use case for an Extraction Agent, available with one of the latest LlamaIndex 🦙 tools: LlamaExtract. But, it makes sense to build a system that is explainable, that can be

Another video with the amazing Femke Plantinga 💕

🚀 Big memory upgrade in LlamaIndex! The new, flexible Memory API blends short-term chat history and long-term memory via plug-and-play blocks: ➡️ StaticMemoryBlock for non-changing static information ➡️ FactExtractionMemoryBlock that keeps track of a list of useful facts ➡️

Improve your AI agents' memory with LlamaIndex's new Memory component! 🧠💡 Learn how to enhance your agentic applications with both short-term and long-term memory capabilities: ➡️ Store chat history for context-aware conversations ➡️ Implement static memory blocks for

Let's talk memory for agents.. 🐠 Short-term memory: that simply keeps track of the conversation history to the extent that our token limit allows us to 🐘 Long-term memory: which allows us to store a number of things, in a number of ways, once our token limit for shot-term

A life update: after a short but wonderful time at Weaviate • vector database , last week, I joined the LlamaIndex 🦙 team 🦙 Honestly, life is weird sometimes.. I don't have anything but positive things to say about the amazing team at Weaviate. I'm gonna miss them sooo so much. So first, a

Thank you ollama for bringing multi-modal model support. Because after I saw the tweet, here's what I did with LlamaIndex 🦙 Create a story based on the image, using Gemma 3 🦙 Comment if you wanna see the rest of the story..

No Eurovision this year ✌️

So.. I recently started at LlamaIndex 🦙 and have been wrapping my head around Agent workflows, building new demos and examples. So what better way to learn more than to force myself into an office hours session 💁 Join me not only to ask your LlamaIndex questions, but to

🚀 JUST LAUNCHED: Zero-day support for OpenAI Developers's latest builtin tools in LlamaIndex 🦙 Typescript! Generate cute llama images with the new integration in just a few lines of code - AI image generation ridiculously simple. 📃 Source: github.com/run-llama/Llam…

"Draw an SVG Llama" with Opus 4 😅

There's a new image generation agent by Clelia Bertelli, but it doesn't _just_ generate images. It uses structured outputs with Google Gemini to check a few things about the generated image and evaluate whether it's ready for the user or not. You can check out how she built it and run