Ask HN: How Turn a Person into Embeddings?

2 points by caymanlau ↗ HN
We can turn the article into embeddings and find it through semantic search. I'm wondering if it's possible for us to vectorize a person so that it can be found by semantic search?

For example, we import all twitter and medium of many users and vectorize all their social content. When we type: Help me find someone who cares about AI research and is good at giving independent tech opinions. We will get a list of users.

In this way, we can find people in general fields through ambiguous language.

1 comment

[ 3.6 ms ] story [ 13.9 ms ] thread
What you propose is certainly possible, you could do that with a vector database like Weaviate (https://weaviate.io). Import the data, vectorize it, and connect it to a person with cross-references