RAG, search and information retrieval

Read the Portuguese translation →

The synthesis for this topic is available in Portuguese.

Videos in this topic

• Pinecone Changelog: Hybrid search in one index, BYOC, and VQ-Bench
• Top Open-Source GitHub Projects : VoiceStudio, tamagui, FSearch, sgrep, Indra & snapcn #302
• ChatGPT + PubMed: 2 Formas de Pesquisar Artigos Científicos com IA
• JEV AI Model Explained | System One AI, How It Works & Real-World Application | Will it replace LLM?
• V7 cuts costs 78% while boosting accuracy with GPT‑5.6 Luna
• O Mito do RAG Clínico: Por Que o GPT e o Gemini Venceram as IAs Hospitalares.
• How I Keep Up with AI Without Drowning in It (Free Skill)
• Super memória vs. Segundo Cérebro: como obter maior produtividade com I.A.?
• MiniCPM-V 4.7 1B: Install with Ollama and llama.cpp, Then Push It to the Limit
• Top Open-Source GitHub Projects : OpenBao, Magnitude, herdr, Compositor, WeKnora & BongoCat #296
• Indra OCR | Read a 568-Page Book in 77 Seconds (No GPU)
• Qdrant Just Gave Away 10 Billion Vectors For Free (FineWeb 10b)
• GitHub Trending monthly #11（2026.09）
• Agent Memory Is Solved. Agent Learning Isn’t. — Karthik Ranganathan, Yugabyte
• Distill the LLM, Don’t Serve It: Search & Personalization at DoorDash — Raghav Saboo, DoorDash
• Lakebase Search: Build AI Retrieval for Agents with Lakebase Postgres
• From Context to Memory: Your Agents Need a Real Memory Layer — Anders Swanson, Oracle
• ChatGPT Spaces ou Obsidian: onde guardar o conhecimento da empresa?
• DeepSeek V4.1 Flash 1017: A “Minor” Update?
• É fake: imagens de protestos na França com idosos e Pantera Cor-de-Rosa são IA
• How Bridgewater Turned 100 Million Documents Into an Edge - Sam Green & Aaron Linsky, Bridgewater
• Google Vids agora gera vídeos a partir de um só documento
• Most AI Second Brains Are Built Wrong
• Unstract : Extract Data from Unstructured Docs
• Governing AI Agents with Unity Catalog and Unity Gateway on Databricks | Unity Catalog Demo
• Building AI Agents with Real-Time Web Data — Yohan Raju, Bright Data
• Pinecone 2.0 — Edo Liberty, Pinecone
• 😱 ASSUSTADOR! Gemini Notebook virou uma FÁBRICA DE SKILLS GRÁTIS — chega de repetir tarefas!
• DeepSeek V4.1 Flash is CRAZY
• Add Web Search to Managed Deep Agents for free with One MCP Config
• Memory-Aware Agent Harnesses for Anti-Money Laundering — Nacho Martinez, Oracle
• Backtest Your Agent Against Yesterday’s Web — Ryan Ahern, Exa
• RAG Needs a Map: Using GraphRAG to Retrieve Connected Context — Nyah Macklin, Neo4j
• AWESOME or Overhyped? OXR Document Parsing, Tested With My Own Ugly PDFs
• Why You Can’t Trust Vector Database Benchmarks
• Evals in AI: A Deep Dive — Tejas Kumar, IBM
• If we want them to do Knowledge Work, design them as Knowledge Agents — Benjamin Clavié, Mixedbread
• Beyond RAG: A Relational Context Engine That Cuts Token Burn — Unblocked
• RAG Simply Explained
• MLflow Autolog: Trace LLM Calls in One Line | MLflow A–Z: A
• “It Blew Me Away” | Box’s First Look at GPT-6 Astra
• Nova Era do NotebookLM: Modo Co-create e recurso Air-gapped
• Building the Document Context Layer for AI Agents — Jerry Liu, LlamaIndex
• Training Your Own Embedding Model Is Not As Hard As You Think
• NotebookLM Atualizou: Veja as Mudanças e seus impactos
• Agentic Search vs Vector Search for Coding Agents: We Ran the Eval
• From Scratch to SOTA: Training a 3B State-Space Vision Model — Krishna Prasad Srinivasan, Sarvam
• Suas notas agora podem entrar na mente do NotebookLM
• The Model Swap Workshop: GPT-5.5 vs Kimi vs DeepSeek vs Mistral
• Build RAG with JEV
• This Tiny 0.8B AI Reads Documents Better Than OCR?
• Inside Weaviate’s MCP Ecosystem | Webinar
• Grep or Embeddings? Agentic Search Over Company Documents — George He, LlamaIndex
• Essential Skills for Becoming an AI Engineer: RAG, AI Agents, & More
• Embedding Gemma 2: Multimodal Search & RAG (Free Colab)
• Even a VPN Can’t Hide You From This (Browser Fingerprinting)
• Keyword Search Is Dying. Is Your Catalog Ready for AI Agents? — PayPal
• XERJ’s CRAZY Local Search for AI Agents: I Tested It, It Broke, Then It Got AWESOME
• OpenJev : Open-Sourced Jev AI
• Introducing EmbeddingGemma 2: An open model for natively multimodal embeddings
• Stop Renting Your AI’s Memory — Dylan Couzon, Qdrant
• Road to NODES 2026 - Build Your First Knowledge Layer
• Your Coding Agent Is 6 Months Out of Date — Jakub Hojsan, Exa
• How to Test AI Agents When No Benchmark Exists — Nathanael Weill, Air Canada
• Do Not Let Models Invent Numbers - Vinoo Ganesh, Kepler
• LEANN: 201 GB vs 6 GB?! I Installed This INSANE Vector DB
• Tecent Octop (Opensource): Wait, Tencent just ENDED OpenAI Dots & Muse!?
• In-Context Retrieval with Siddharth Gollapudi - Weaviate Podcast #146!
• Your Fridge Is a Valid Payment Device — Eleonora Drykina & Nina Žižakić, In The Pocket
• MemT-1.0: AI Memory INSIDE the Model Is CRAZY (I Tested the Idea)
• GRÁTIS: AULA COMPLETA 2 HORAS SOBRE FINE-TUNING
• 8 Jev Use Cases That Feel Like Cheating
• PostgreSQL Hybrid Search Course – Keyword (BM25) + Vector Retrieval
• Vector Isn’t Enough: Hybrid Search & Retrieval — Jeff Vestal & James Williams, Elastic
• Introducing pg_pinecone: Open-Source Vector Search Inside Postgres
• LLM Wiki: The 4 Layers Every Repo Needs | Harness Engineering 101
• You Built Your AI Second Brain. Now What? (Here’s How to Evolve It)
• Hermes Agent: Obsidian + OpenViking + Hindsight | Memória Externa na Prática
• This Tiny 2B AI vs Claude Code’s Token Bill (Real Test)
• Your Coding Agent Wastes SO MANY Tokens Just Finding Code - Here’s the Fix
• We Built an AI Support Agent That Resolves 80% of Tickets — AssemblyAI
• Teaching Agents to Search with NVIDIA Data Designer — Dhruv Nathawani, NVIDIA
• Stop Fine-Tuning to Fix Retrieval Problems — Anant Srivastava
• Stop Chunking Like It’s 2022 — Yuval Belfer, AI21 Labs
• This 150M Model Claims #1. I Tested It.
• Your LLM App Returned 200 OK. It Was Still Wrong. — Marina Petzel, Datadog
• Obsidian + Jev é absurdo! Segundo cérebro em tempo real (veja como)
• Claude Code Is MISSING One Key Thing. Here’s How to Fix It!
• Beyond RAG: Build a Relational Context Engine from Scratch — Peter Werry, Unblocked
• Como identificar um DEEPFAKE? 5 sinais de que um vídeo pode ser feito por IA
• Building AI Assistants with On-Device Memory
• Stop Prompting AI. Use Karpathy’s Method Instead.
• From Raw Documents to AI-Ready Data — Leo Platzer & Jeff Koss
• Long-Horizon Agents Need Experiments, Not Just Prompts — Erina Karati
• Total Recall: Agent Memory and Harness Engineering — Ignacio Martinez, Oracle
• Neo4j Live: AgentMemory for .NET: Persistent AI Agent Memory Engine
• Using Jev In Your Agent Harness
• Haiku 5.5: a alternativa BARATA ao Claude Opus MERECE atenção?