Guides

Task-oriented walkthroughs — migrate from OpenAI, build RAG with embeddings, wire up audio pipelines.

Pick a guide based on what you're trying to build. Each one is concrete: real code, real endpoints, no hand-waving.

Switch your existing OpenAI client to Bastion in two lines. Caveats and edge cases.

Embed documents, retrieve the most relevant chunks, ground a chat answer.

Transcribe speech, run it through an LLM, speak the answer back.

Best practices

Production-readiness checklist — secrets, retries, timeouts, observability, cost control.

Migrating from OpenAI

Two-line code change to point an existing OpenAI integration at Bastion.