DeepSeek-V4, 1M Context and the New Inference Portability
Learn what DeepSeek-V4’s “no Nvidia GPU” claim means for inference. See where NVIDIA Triton Inference Server fits, plus Docker builds you can ship.
Genesys Memory System: 89.9% LoCoMo vs Vectors
Learn why vector search fails for agent memory and how Genesys Memory System uses a causal graph to hit 89.9% LoCoMo. Build it with Docker Compose.
Building a Full RAG Stack on Docker with Ollama, Open WebUI, Qdrant, and VectorAdmin
TL;DR (Executive Summary) This project implements a local, privacy-focused Retrieval-Augmented Generation (RAG) stack using Docker, combining Ollama (TinyLlama and nomic-embed-text), Open WebUI, Qdrant, and VectorAdmin. The system delivers end-to-end capabilities…
Docker-based Model Runner for AWS CloudWatch Log Analysis
Concise Summary This project Convert plain-English questions into concise summaries over CloudWatch-style logs. Conversational CloudWatch converts natural-language questions into structured insights over CloudWatch-style logs. It runs locally or with LocalStack,…
Text-to-SQL Agent with Docker MCP and Model Runner | Smarter and Safer
A containerized approach to natural language database queries with built-in safety and auditability Author: Vishesh Sharma and Karan Singh Date: November 12th, 2025 Core The original Text-to-SQL setup worked but…