Articles

Learn where vector search helps, why an existing PostgreSQL database can be a sensible starting point, and when ordinary queries are enough. Try a small SQL example before choosing an index or another database.

Understand what embeddings do, see how text becomes a vector, and compare model options using your own search questions. Includes an API example, a simple diagram and an invoice example that keeps money and supplier IDs in exact database checks.

Split a document into useful pieces while keeping its headings, tables, source pages and permissions. Learn when invoice data should stay in rows, how to split policies, and how to check the result.

Build an ontology from an empty Python file, inspect actual graph records and their sources, and extend a maintenance example to multiple required parts. Six chapters combine plain-language explanations with a downloadable, locally tested implementation.

Use repository navigation, behavior-preservation tests, isolation and review to make bounded changes to established business systems.

Compare hosted and self-hosted deployment, capacity, caching effects and model routing through cost per successful task, rather than headline token prices.

Design workflows that survive crashes and long approvals without repeating consequential actions. Follow state, retries, idempotency and recovery evidence.

Understand evolving attacks through documents and tool outputs, the defenses introduced in response, and the limitations that still require application controls.

Build evaluation evidence that grows with the system: retrieval, supported answers, tool actions, calibrated judges, failure costs and release decisions.

Compare parsing, OCR and vision-assisted extraction, with original document examples, table structure, schema validation and page-level evidence.

Follow the development from document search to hybrid, graph and agentic retrieval. Compare them using source permissions, changing versions, evidence quality and operational cost.

Understand APIs, backend MCP and WebMCP in one guide: where each fits, how tool contracts evolve, and which identity, permission and context boundaries the application must enforce.

Start with the business problem, then choose rules, retrieval, workflows or agents. Learn how permissions, human review, cost limits and evaluation shape the complete system.

Trace context limits, larger windows, retrieval, preloading, caching and persistent memory. Understand which problems each approach solves, what it cannot solve, and how to choose today.