Just wondering how to figure out the major difference of results:
- Generated embeds for each of 1500 text documents via text-embedding-ada-002.
- Inserted the 1500 embeds with meta to Pinecone Index(Cos).
- Generated an embed for a question via text-embedding-ada-002
- Used the openai cosine similarity method to obain top3 results, with high score and meaningful results.
- However, I sent the same embed of the question in a query to Pinecone, resulting in totally wrong and meaningless top3 results.