Ask HN: What RAG setup gets me 95% of the way there?

6 points by uptownfunk ↗ HN
Alternatively what is your RAG set up?

5 comments

[ 3.0 ms ] story [ 21.8 ms ] thread
This will get you the first 80%:

* Any solid search engine (bm25 + embeddings and hnsw)

* Any api to a model (gpt3.5, gpt4, claude, etc)

* Some middleware to call search then build the prompt

Then the remaining:

* Create an eval dataset, then tune the search and the prompt as needed