Clelia Bertelli

♻️ I have recently shifted the design of my AI applications from plain AI agents to AI-powered workflows, and I wanted to share the reasons behind this choice, so I wrote a blog post📝: clelia.dev/2025-07-22-i-a… 🔭 In the post, I give my opinions about how workflows are the…

💯 Read and study this ⤵️ Excellent writeup on the value of workflows (vs agents) for getting real work done reliably with AI.

🙋 The community asked: "Is NotebookLlaMa ever going to get a space where we can see all our previously processed documents?" 🦙📚 And we responded with a new feature: all your documents are now in one place - a full-fledged document management UI: watch the demo below👇 🔒 And…

Last week @itsclelia and I had our own mini hack day and ended up creating @llama_index nodes for @n8n_io Here's what we got: · LlamaExtract: use extraction agents within n8n workflows · LlamaParse: parse complex documents · LlamaCloud: use your existing LlamaCloud indexes as…

Introducing LlamaCloud official @n8n_io nodes! @tuanacelik and I have been working on getting LlamaParse, LlamaExtract and LlamaCloud Index available into n8n so that you can use best-in-class parsing, retrieval and structured data extraction in your workflows🚀 Watch the demo…

New LlamaParse feature: header and footer detection! If you're using Balanced or Premium mode, we will automatically detect page headers and footers. This allows you to selectively hide them from your parsed output (useful to avoid repetition) or to add prefixes and suffixes to…

LlamaCloud nodes for @n8n_io are here! We've created and n8n nodes that bring LlamaCloud's document parsing and extraction agents, as well as your LlamaCloud indexes as knowledge bases into your n8n automation workflows. 🤖 Connect LlamaCloud nodes to your existing workflows…

Ready to build cutting-edge AI agents that push the limits of LLMs? 🚀 We're excited to sponsor the A2A Agents Hackathon in San Francisco this Saturday, July 26, where our VP of Developer Relations @seldo will be speaking and judging alongside incredible experts from…

Automate RFP Responses in Minutes with our open-source project! Learn how to transform the time-consuming RFP (Request for Proposal) response process from hours of manual work into an automated workflow that takes just minutes. This open-source demo showcases LlamaIndex's…

🎙️ Always wanted to turn your documents into in-depth, podcast-like conversations? 🦙📚 NotebookLlaMa, our OSS @NotebookLM clone, just got an upgrade on that side! 🎧 You can now customize the style of the conversation and the target audience, as well as add instructions and…

NotebookLlaMa just got another great upgrade! This time, it's podcast generation 🎙️ You can now choose the focus points of the conversation, the conversational tone and style, as well as the target audience - watch the demo below!👇 Big shout out to @ngalluzzo_ for getting ther…

Introducing `gut` - an AI agent for git 🤖🧑‍💻 This is a really neat CLI-based tool from @itsclelia that lets you ask about and execute git commands through natural language! Describe what you want to do in English (e.g. a complex rebase), and it’ll let you review and auto-execute…

At the beginning of my coding journey, I struggled with git and @github, as many programmers do. Since git and GitHub are nowadays extremely important skills to have, I decided to create something that could help people execute git/gh commands in the CLI simply using natural…

Context engineering for agents usually refers to text context - but visual context is just as important too! 🖼️ A lot of valuable info is stored as images: camera images, webpage screenshots, diagrams/charts/overall document understanding tasks. When you index your enterprise…

This is basically Cursor over your research papers 🧑‍💻 Besides asking research questions, help read (and write) commands and code to do deeper analysis on implementation details. Check it out below 👇

If you’re using AI agents for large-scale document extraction 📑✂️, you will need to craft a good structured output schema. Most LLMs support structured output these days, but here are tips and tricks from learned experience💡 1️⃣Try to limit schema nesting to 3-4 levels. 2️⃣ Make…

Build advanced agentic RAG applications that go beyond simple Q&A to perform multi-step reasoning, make decisions, and dynamically interact with both internal knowledge bases and external APIs. This comprehensive @aws guide shows you how to create a powerful research tool using…

📈 Table extraction is a key component of intelligent document processing, and we know it very well - that's why we added support for one-click table extraction within LlamaParse. Check out this notebook: github.com/run-llama/llam… And the demo below!👇

Agents to extract structured tables from any PDF in seconds ⚡️ A lot of PDFs (financial reports, research papers, invoices), have complex charts and tables that require a lot of human effort to format into a tabular representation (e.g. in Excel, CSV, or Pandas). We added a…

Spoke at @mlopscommunity meetup yesterday about @qdrant_engine mcp-for-docs Got pics And come onnn, what're these face expression lmaooo