Tuana
@tuanacelik
Posts about AI/ML and occasionally other random tidbits. DevRel & AI Engineering at @llama_index from Istanbul ☀️ in Amsterdam 🚲
Join our own @tuanacelik at ODSC's Agentic AI Summit tomorrow! She'll be presenting a hands-on workshop where you'll learn how to: ➡️ Build agents using LlamaIndex - Learn to create autonomous applications that use goals and tools to accomplish tasks independently ➡️ Compose…
Amsterdam AI meetup coming up July 31st lu.ma/vzwsj72w
We're partnering with @Snowflake to bring you hands-on talks and concrete patterns you can implement immediately. Join us at our Amsterdam meetup on July 31st where we'll show you exactly how teams are building high-quality data agents in production. Build production-ready…
A new walkthrough for a research agent using @llama_index and @Google Gemini, fresh out the oven 🥨 Given a topic: 🌎 Use Gemini 2.5 pro with its server side google search tool 📝 Create an agent that takes notes as it gets results from its websearch 👀 Create other agents that…
I’m finally back in the game of giving talks. Pleasure to talk about event driven agentic AI with @llama_index today, first in person talk since joining 🚀 Especially great because it was in Amsterdam, my adopted home.
Check out this NotebookLM clone NotebookLlaMa by @itsclelia 🚀 Over 1k ✨on GitHub: github.com/run-llama/note…
We surpassed 1000 stars on @github with NotebookLlaMa! Thanks you all for your support and your interest, and stay tuned for new updates!🥹 ⭐ Find it here: github.com/run-llama/note…
🦙 Since you loved NotebookLlaMa, our open-source, LlamaCloud-backed @NotebookLM alternative, we decided to give you more features! In the latest release you can: 📊 Extract and download images and tables from your files, and interactively visualize all tabular data ✅ Chat with…
Agent meetup in Amsterdam 🇳🇱 Finally a meetup on home turf 🚲 Amsterdam (and Europe) friends, we’re hosting an in-person event at the @Snowflake HQ here with @_jreini on July 31st: Document agents, building them and evaluating them 👇 lu.ma/vzwsj72w
Ready to build production-grade data agents that work with real enterprise data? 🏗️ Join us and @Snowflake in Amsterdam on July 31st for hands-on talks about building data agents that actually work in production: 🤖 Learn how to tame complex paperwork with document agents using…
It's clear that many agentic applications are designed for tackling complex documents—think massive PDFs, slide decks, and all forms of unstructured data. These document agents operate in two key layers: 1️⃣ A tool to convert documents into a format digestible by an LLM. 2️⃣ An…
With all of this "context engineering" chatter, I've been thinking about how much of LLM performance hinges not just on model architecture, but on how you feed it context a lot lately. So, inspired by the piece from @_philschmid we co-authored a blog on Context Engineering with…
I like this new terminology around context engineering that's picking up. It's a good way to think about how to build actually effective agentic applications. TLDR: there's a shift from talking about 'prompt engineering' to 'context engineering'. This puts way more focus on…
Use all of your LlamaCloud tools within powerful agentic applications! We've open-sourced the LlamaCloud MCP server that connects your LlamaCloud project directly to MCP clients like @AnthropicAI Claude Desktop, giving you instant access to your private data and LlamaExtract…
Today we're announcing the first stable release of @llama_index workflows. A lightweight framework for building complex, multi-step agentic AI applications in Python and Typescript. v1.0 also introduces the first standalone version of Workflows, with its own repository, package,…
Since MCP there are questions about whether it removes the need for you to build your own RAG workflows with vector search. And my answer to that is: It always made sense to think about whether vectorizing your data even made sense for your use case in the first place. And…
Last week, we concluded the @Gradio MCP hackathon with @huggingface and there were some pretty cool projects that came out of it! One of them (the @llama_index winner) - is the "Nasa Space Explorer" 🔭🪐 15 MCP tools across 3 servers that provide live data on: ☄️ Asteroid info:…
Yesterday @Zoom announced Zoom RTMS at the developer summit, which gives you real-time access to audio, video, and transcript data from Zoom Meetings. This couples nicely with @llama_index's event-driven agent workflows. So I've created a mini demo: Build your own @NotionHQ…
Want to build your very own Meeting Notetaker agent for @NotionHQ? Well, @Zoom just announced RTMS at the developer summit today 🚀 This allows you to make use of real-time data from Zoom Meetings (video, transcripts and more) in your applications! Check out the full example by…
Tomorrow, I'm happy to join @LGFunderburk and @AIMakerspace for a discussion on memory. Note: not all applications that are 'agentic' necessarily _need_ memory. And what type of memory you need also depends on the use case. In the last few weeks @LoganMarkewich have had..what,…