Hacker Newsnew | past | comments | ask | show | jobs | submitlogin
Ask HN: What RAG setup gets me 95% of the way there?
6 points by uptownfunk on July 5, 2024 | hide | past | favorite | 5 comments
Alternatively what is your RAG set up?


If I did it I would try this first: https://github.com/pgvector/pgvector


Couldn’t put it better than this post

https://www.linkedin.com/posts/softwaredoug_absolutely-kille...


Try dify (https://github.com/langgenius/dify)


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


https://bionic-gpt.com Just signup and start adding data.




Guidelines | FAQ | Lists | API | Security | Legal | Apply to YC | Contact

Search: