SJSriniketh Jinsrinikethj.hashnode.dev·Aug 11 · 9 min readMore than Observability for Haystack: A Practical Guide to KitaruHaystack is an open-source framework and orchestration layer for your agents. Kitaru is also an open-source framework for tracing your agents. The real power comes when you combine these tools in the 00
ABAditya Biranjeinadityabiranje210.hashnode.dev·Jul 23 · 27 min readDesigning the Ingestion Layer of a Production RAG SystemMost RAG postmortems point at retrieval. Wrong chunks come back, the reranker doesn't help, the LLM hallucinates around a gap in context. Almost none of it is a retrieval bug. By the time a query hits13A
TSTina Sharmaintheaicartographer.hashnode.dev·Jul 7 · 28 min readHow to Use Semantic Caching with Qdrant to Optimize Token Costs in Customer SupportMost people remember the story because it was funny. Someone asked McDonald’s AI-powered drive-through assistant to write Python code instead of ordering food. The internet laughed. Engineers noticed 10
JCJim Chundevalelinaccidentalcomplexity.hashnode.dev·Jul 5 · 19 min readPart 3: Open WebUI, a One-Sided Load Balancer, and a Bug Hiding One Field DeepTwo Birds, One Qdrant With the core database built and my own homelab knowledge ingested, I had a second idea. Open WebUI, the chat front end I already run for my Hailo and Gemma models, has its own b00
JCJim Chundevalelinaccidentalcomplexity.hashnode.dev·Jul 4 · 8 min readPart 2: Herding Files Across Five Pis, Dodging Junk, & Teaching Qdrant What MattersThe Plan Was Simple Qdrant was running. I had a collection. All I needed to do was feed it something. My homelab "knowledge" was scattered across five different Pis: config files here, Modelfiles ther00
JCJim Chundevalelinaccidentalcomplexity.hashnode.dev·Jul 3 · 9 min readPart 1: RAID, Rust, and a Very Stubborn Memory AllocatorThe Idea I’ve had a local AI stack running for a while now: Hermes on WhatsApp, Gemma 4 on CPU, two Hailo AI HAT+ boards handling NPU inference, and Open WebUI tying most of it together. It was good a00
CDCoding Dropletsincodingdroplets.com·Jun 26 · 9 min readChoosing a Vector Store for .NET AI Apps: sqlite-vec vs SQL Server 2025 vs Qdrant - Enterprise Decision GuideEvery .NET team building a Retrieval-Augmented Generation (RAG) feature or semantic search endpoint hits the same question early: which vector store should we use? The answer shapes infrastructure cos00
SSsatyam sahuinthebuildersnotebook.hashnode.dev·Jun 23 · 30 min readBuilding an Offline “Life Memorizer” with Gemini 2.0 & Qdrant EdgeOriginally published on Medium. Reposted here for the Hashnode community. Consider this. You are trying to find where you left an item, like your wallet or keys, inside your own house. You know you s20
MPMohana Priya Rinmona23.hashnode.dev·Jun 22 · 2 min readWhy I chose Qdrant over ChromaDB in my RAG SystemWhen I started building Nexus — my multi-source RAG system — one of the first real decisions I had to make was picking a vector database. It sounds like a small choice. It isn't. First, why do you eve00
LSLakhan Samaniinblog.authorizer.dev·Jun 16 · 11 min readYour AI assistant can leak files people aren't allowed to see — here's how to fix itTL;DR Vector search ignores your permission model: an engineer can ask your RAG assistant about board-level financials and get them, because semantically close = retrieved, and a restricted chunk in 106JZSRI