SherryLiu a143ae8ff1 Faiss v.s. Original RAG. Taide model. преди 7 месеца
..
README_faiss.md a143ae8ff1 Faiss v.s. Original RAG. Taide model. преди 7 месеца
faiss_index.py a143ae8ff1 Faiss v.s. Original RAG. Taide model. преди 7 месеца
output.txt a143ae8ff1 Faiss v.s. Original RAG. Taide model. преди 7 месеца

README_faiss.md

Comparing Faiss with the original RAG. Using the TAIDE LLM model. Using created embeddings in the Supabase db.

Did not apply multi_query on Faiss (it will generate very similar answers from the original RAG). Applied multi_query on the original RAG only.

Evaluate on: 1. speed 2. RAGAS score Some of the result is in the output.txt

Faiss: https://engineering.fb.com/2017/03/29/data-infrastructure/faiss-a-library-for-efficient-similarity-search/