Posts tagged "AI / LLMs"
Essays, field notes, and engineering write-ups by Al Amin Ahamed covering AI / LLMs — practical patterns, gotchas from production code, and lessons learned shipping real systems. Topics include architecture decisions, performance tuning, debugging stories, and integration notes you can apply directly to your own AI / LLMs work.
· 0 min read
MCP Servers for Laravel: A Production Pattern
How I built the MCP server that powers AI access to this portfolio — JSON-RPC over Streamable HTTP, Sanctum bearer auth, an ability-scoped tool registry, and the gotchas worth knowing before you ship.
· 9 min read
RAG on SQLite: Pure-PHP Cosine Similarity Without pgvector
How I built RAG retrieval against a SQLite database using pure-PHP cosine similarity — when it scales, when it doesn't, and the migration path to pgvector.
· 10 min read
A Multi-Provider AI Driver Pattern for Laravel
A clean driver pattern for switching between Claude, OpenAI, Groq, and Ollama in a Laravel app — with failover, testing, and a single calling interface.
· 8 min read
Cutting Claude API Costs by 89% with Prompt Caching
A practical Laravel integration of Anthropic prompt caching — what to cache, the 1024-token minimum, multi-breakpoint strategies, and real cost numbers.
· 8 min read
Building a RAG Pipeline in Laravel with pgvector
How I built the AI chat on this site: chunking documents, generating embeddings with Voyage AI, storing them in pgvector, and answering questions with Claude.
· 9 min read
Semantic Search with pgvector and Laravel Scout
Add meaning-based search to your Laravel app using a custom Scout driver, pgvector HNSW index, and Voyage AI embeddings — with a hybrid keyword fallback.