This is a preview article. Connect a Strapi instance to
VITE_STRAPI_URL to render the full post body via the Strapi Blocks renderer.All posts
Technical Deep Dives
Multi-LLM Orchestration: Model Switching, Comparison, and Fallback
How Simmetric Chat orchestrates Ollama, OpenAI, Anthropic, OpenRouter, and Gemini with 20 provider presets, a Cmd+K model palette, and side-by-side comparison.
Simmetric Team·15/04/2026·7 min read
Related articles
Simmetric
Technical Deep Dives
Scaling Simmetric Chat to Multiple Instances with Redis and pg-boss
Simmetric Chat scales horizontally behind any load balancer, with no sticky sessions. How state moves to Redis, Postgres, and the pg-boss job queue.
Simmetric Team · 03/09/20269 min read
Simmetric
Technical Deep Dives
Building a Hybrid RAG Pipeline with Reciprocal Rank Fusion
How vector similarity and PostgreSQL full-text search run in parallel and fuse through Reciprocal Rank Fusion into answers with citations and relevance scores.
Simmetric Team · 12/06/20267 min read
Simmetric
Technical Deep Dives
Embeddable Chat Widgets: Architecture and Security
The two-step loader and sandboxed iframe behind Simmetric Chat's widget, with isolated sessions, rate limiting, and layered knowledge-base access.
Simmetric Team · 30/04/20267 min read