dovelome

I like what you are doing! I suggest you create a proxy service that will route the traffic to the AI provider.

You can cache questions and answers heavily and use a B25 search with a vector embedded to retrieve the best results for you.

   RAG pipeline
   ├── BM25 + TF-IDF + RRF retrieval
   ├── cross-encoder reranking
   ├── knowledge-graph entity linking
   └── multi-angle intent detection
        │
        ▼
   LLM synthesis  (Claude / local models)

I believe this future is happening now! I see a lot of movement in the industry to understand what AI efficiency is and how to properly quantify it. The industry is eager to know the ROI of the ratio of token usage, Mr merges, and value delivered.