Does anyone have insight on whether it’s going to give better results to use fewer, longer embedding texts, or to split these texts up into more smaller fragments? (I’m not worried much about the question of token limits, that I can handle either way.) Here’s what I’m thinking about. I’d prefer t…

Embedding - text length vs accuracy? - #14 by EricGT - API

Topic		Replies	Views	Activity
Embeddings results using Ada-Embedding-data-002 API	10	2424	March 29, 2023
Searching Using Vectors Derived from Long Text Segments in an Embedding Model API embeddings , api	4	2543	December 15, 2023
Embedding Longer Texts API	8	15593	December 25, 2023
How to Optimize Text Chunking for Improved Embedding Vectorization? API vector-db , semantic-search	6	11424	December 15, 2023
Embedding and searching from similar embeddings API	6	6841	October 27, 2023