JetThoughts has been building software since 2008. Book a call, or write to sales@jetthoughts.com. You'll leave the call with a written one-page scope within 2 working days.
A 30-minute call; pick a time.
Building RAG Applications in Rails With pgvector
Retrieval-augmented generation in a Rails app using pgvector and the neighbor gem: schema, chunking, an HNSW index, and why filtering after an approximate index can return too few rows.
· JetThoughts Team
How to Cut LLM Application Costs With Token Budgets
Where LLM spend actually goes: the fixed prompt you resend every call. Measure tokens from API usage, use prompt caching, batch what can wait, and cache identical requests.
Complete Guide to Ruby on Rails AI Integration 2025
Master Ruby on Rails AI integration with OpenAI, Anthropic, and LangChain in 2025. Production patterns, security best practices, and 50+ working code examples.
Tell us what you need built