UFUmmer Farooqinblogs.ummerfarooq.dev·Aug 21, 2025 · 7 min readQdrant 101Introduction Qdrant is an open-source vector database designed for storing, searching, and managing high-dimensional vectors. It's particularly useful for AI applications like semantic search, recommendation systems, and RAG (Retrieval-Augmented Gene...00
UFUmmer Farooqinblogs.ummerfarooq.dev·Aug 14, 2025 · 6 min readWhy Dense and Sparse Vectors Work Better Together: A Beginner's Guide to Multi-Vector CollectionsImagine you're looking for a book in a massive library. You might search by the exact title (keyword search) or describe what the book is about (semantic search). Sometimes you need both approaches to find exactly what you're looking for. This is pre...00
UFUmmer Farooqinblogs.ummerfarooq.dev·Aug 14, 2025 · 14 min readA Guide to Document Chunking and Vector SearchIntroduction: Why Traditional Search Falls Short Imagine you're searching through a massive company knowledge base for information about "machine learning best practices." Traditional keyword search might return hundreds of documents, but you end up ...00
UFUmmer Farooqinblogs.ummerfarooq.dev·Aug 5, 2025 · 1 min readKubernetes/Helm-charts commonly used commandsUninstall Helm Release helm uninstall <release> --namespace <namespace> #example helm uninstall qdrant --namespace qdrant Delete PVCs (Persistent Volume Claims) kubectl delete pvc --all -n <namespace> #example kubectl delete pvc --all -n qdrant D...00
UFUmmer Farooqinblogs.ummerfarooq.dev·Aug 4, 2025 · 2 min readWSL Networking and Port ForwardingConsidering vLLM is running inside WSL, and we are trying to expose it to the Windows network. Step 1: Confirm WSL Server Is Listening on 0.0.0.0 In your docker-compose or command, make sure vLLM is not bound to 127.0.0.1. It should be bound to all i...00
