Ask HN: If embeddings are so powerful, why are they mostly used for retrieval?

Vector embeddings natively are capable of much more than just retrieval. Even when OpenAI released their initial embedding models, it mentioned that their embeddings are natively capable of Search, Clustering, Recommendations, Anomaly Detection, Diversity Measurement, and Classification. But ev...

Source: [Hacker News](https://news.ycombinator.com/item?id=49685838)