dovelome

Check it out: https://blog.r-lopes.com/how-it-works

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.

Love it

Sorry to heard that. I also have adhd and I’ve looking for solutions since I was 11 years old, now I am 29 years old and pretty much tested all the vitamins, exams, medication, therapy and bunch of other things. Today I found how to manage my adhd, the basic stuff, eat well, exercise and sleep well. It seems so simple but we need to find a synergy between all the basic, vitamins we sometimes have to take, CBT and so on. The doctor Le Grand on YouTube helped to discover a lot of alternative treatments and it worked, so well that I think I am using the super power of adhd and not longer controlled by a incessant mental energy.