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

Question

Alternatively what is your RAG set up?

langcss · Accepted Answer

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

softwaredoug · Answer

Couldn&rsquo;t put it better than this posthttps://www.linkedin.com/posts/softwaredoug_absolutely-kille...

omidh · Answer

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

cmcollier · Answer

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

ianpurton · Answer

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

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

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.