Developer news without the noise — My Dev News in Telegram.
Tag
All blog posts with this tag.
Production RAG cannot leave authorization to the model. How to isolate tenants, apply access lists before retrieval, close hidden leak channels, and measure recall under tight filters.
Qdrant, Pinecone, Weaviate, pgvector, and Milvus compared for agent memory: filtering, hybrid search, tenancy, and quantization.
How to run a vector database as an index layer: ANN algorithms, filters, tenancy, operations, and when pgvector beats a dedicated store.
A practical guide to production RAG architecture: ingestion, chunking, hybrid retrieval, reranking, evaluation, observability, security, and staged delivery for engineering teams.
More LLM calls do not necessarily cost more: support teams should measure the cost of resolving a question, not generating one answer.
A production RAG pipeline depends on document chunking, embeddings, pgvector, cost controls, and observability—not just an LLM.
Profiling, indexes, ORM refactors, materialized views, connection pooling, and cache — a practical PostgreSQL and MySQL guide.
Jobs table, row locks, JSONB payloads, LISTEN/NOTIFY, and goroutine workers — no Redis if Postgres is already in your stack.
DBOS and Obelisk: local SQLite plus Litestream to S3 for workflow state; Postgres when you need HA and shared scale.
Metrics Layer / Headless BI as an executable contract for metrics—not a data catalog—and why LLMs should not invent SQL on their own.
Chroma, Pinecone, Qdrant, Weaviate—not QPS charts, but packaging, API stability, and the path from dev to production.
The tsk case: finite state transducers in Rust, shared Finnish suffixes, and why SQLite FTS was only a stepping stone.