SSuneelinblog.suneeldk.in·Apr 8 · 4 min readRAG: Retrieval Augmented GenerationRAG is the dominant architecture for production AI applications that need to answer questions about specific documents, recent events, or private data. Understanding it completely — including its fail20
SSuneelinblog.suneeldk.in·Apr 8 · 4 min readChunking: Why Document Splitting Determines RAG QualityDevelopers often focus on which LLM to use or which embedding model is best. In practice, chunking strategy has a larger impact on RAG quality than either of those choices. A mediocre LLM with good ch00
SSuneelinblog.suneeldk.in·Apr 7 · 4 min readVector Databases: Infrastructure for Semantic SearchVector databases are purpose-built for one operation that general-purpose databases handle poorly: finding the k most similar vectors to a query vector. Understanding why this requires specialized inf00
SSuneelinblog.suneeldk.in·Apr 7 · 4 min readSemantic Search: How Meaning-Based Retrieval WorksSemantic search is the retrieval mechanism in RAG. Getting it right is the difference between an AI assistant that finds the correct information and one that retrieves garbage and hands it to the LLM.00
SSuneelinblog.suneeldk.in·Apr 5 · 4 min readVectors and Embeddings: The Mathematical Foundation of AI SystemsBefore you can build a RAG system, design a semantic search engine, or understand why vector databases exist, you need to understand embeddings. This is the concept that makes everything else work. Wh00
