|
|
|
|
|
by cmogni1
410 days ago
|
|
I think the most interesting thing to me is they have multi-hop search & query refinement built in based on prior context/searches. I'm curious how well this works. I've built a lot of LLM applications with web browsing in it. Allow/block lists are easy to implement with most web search APIs, but multi-hop gets really hairy (and expensive) to do well because it usually requires context from the URLs themselves. The thing I'm still not seeing here that makes LLM web browsing particularly difficult is the mismatch between search result relevance vs LLM relevance. Getting a diverse list of links is great when searching Google because there is less context per query, but what I really need from an out-of-the-box LLM web browsing API is reranking based on the richer context provided by a message thread/prompt. For example, writing an article about the side effects of Accutane should err on the side of pulling in research articles first for higher quality information and not blog posts. It's possible to do this reranking decently well with LLMs (I do it in my "agents" that I've written), but I haven't seen this highlighted from anyone thus far, including in this announcement. |
|
Would be interesting to see comparisons for custom web search RAG vs API. I'm assuming that many of the search "params" of the API could be controlled via prompting?