Archive

Introduction There are various approaches to implementing Retrieval-Augmented Generation (RAG). One such method, known as Graph RAG, leverages the structure and relationships within a knowledge graph to retrieve information relevant to a user's query. In this article, we compare a naive RAG implementation — which relies on standard vector

🔗Source code with README: https://github.com/yuniko-software/tokenizer-to-onnx-model The Challenge of Working with Embedding Models Text embeddings have become essential components in modern AI applications, from semantic search and RAG applications to recommendation systems. However, implementing them across different programming languages presents significant challenges: * Python-centric ecosystem: Most embedding models

⏱️ Estimated reading time: ~10 minutes One of the key challenges for companies working with AI is enabling efficient access to internal knowledge. At first glance, it might seem easy: just feed your corporate documents into a large language model (LLM) and let it generate answers. But in practice, such solutions

🔗Source code with README: https://github.com/yuniko-software/bge-m3-qdrant-sample Why Hybrid Search with Reranking? The combination of BGE-M3's all-in-one embedding model, Qdrant, and hybrid reranking offers significant advantages over traditional methods: * Combines strengths of multiple approaches - Integrates semantic understanding from dense vectors, keyword precision from sparse vectors,

The idea of MCP Servers had been on my mind for a while, and one evening I decided to dive in to learn the technology and practice creating AI agents. I wanted to build something fun, so I ended up creating an MCP Server for Minecraft. GitHub - yuniko-software/minecraft-mcp-server: