Deniz
How should I abstract the LLM provider (Ollama → Bedrock/OpenAI)?
Build one narrow complete(prompt, opts) interface with three implementations picked by config, and treat context window, latency and cost as config.
Tag
AI-powered systems: RAG, agents, MCP, LLM integration and the AI-assisted development loop. Questions under this tag, answered directly.
1 answered questions carry this tag.
Build one narrow complete(prompt, opts) interface with three implementations picked by config, and treat context window, latency and cost as config.