Articles for people who
ship the stack
Rewrites on React, Node.js, TypeScript and AI. A translated body is shown when it exists. If it does not, you see the English text and a note that says so.
Tagged: rags
Practical notes: Improve RAG Performance — Part 2: HyDE (Hypothetical Document
Operable walkthrough of Practical notes: Improve RAG Performance — Part 2: HyDE (Hypothetical Document: contracts, checks, and drop-in code slots for teams shipping this pattern.
6 min readPractical notes: Designing a Cache for AI Agents: Caching Inside the Loop
Operable walkthrough of Practical notes: Designing a Cache for AI Agents: Caching Inside the Loop: contracts, checks, and drop-in code slots for teams shipping this pattern.
6 min readSemantic Search vs Vector Search: What’s the Difference, and
Semantic search vs vector search: keyword search first, then vectors and meaning, where each one wins, and how they combine for retrieval in RAG systems.
14 min readRAG Is More Than a Chatbot: What Actually Happens Inside
RAG is more than a chatbot: the ingestion engine, vector database, retrieval and generation stages, and why demos hide what production pipelines really need.
15 min readFrom Fine-Tuning to Precision: Significantly Reducing
Fine tuning plus RAG to cut hallucinations: why fine tuning alone falls short, the architecture with Ollama, and how precision improved on a narrow domain.
13 min readBuilding RAG Systems That Actually Work in Production
RAG systems that work in production: document ingestion, chunking, embeddings, a vector database, retrieval and LLM generation that stays grounded in sources.
18 min readNo stories. Just the minimal code to build a working RAG
The minimal code for a working RAG app, no stories: keys, dependencies, an embedding model, hosted Qdrant for vectors and Gemini to generate the answers.
13 min readPractical notes: Smart Ways to Improve AI Agent Responses in Production
Operable walkthrough of Practical notes: Smart Ways to Improve AI Agent Responses in Production: contracts, checks, and drop-in code slots for teams shipping this pattern.
9 min readPractical notes: Vector‑native RAG on Oracle: embeddings, HNSW/IVF, and hybrid
Operable walkthrough of Practical notes: Vector‑native RAG on Oracle: embeddings, HNSW/IVF, and hybrid: contracts, checks, and drop-in code slots for teams shipping this pattern.
11 min read
About these articles
Request a 24h estimate
Need the same stack in a production operator layer? Send the brief — estimate within 24 hours.