On: 32k context length text embedding models

[ldjkfkdsjnv]

I build a RAG system with voyage and it crushed openai embeddings, the difference in retrieval quality was noticeable

[Oras → ldjkfkdsjnv]

What evaluation metrics did you use?

[ldjkfkdsjnv → Oras]

None, I just tested it over and over, with 100 users.