Harrison Chase: belief

Transcript context

…Maybe we should. I've thought about this. Yeah. I'd love to host that meeting. It's really been a lot of, you know, one of the amazing things is we get to interact with so many different people. So it's been a lot of kind of like just pattern matching on what people are doing and trying to see those patterns before they punch us in the face or something like that. So for retrieval, it was the pattern of seeing like, Hey, yeah, like a lot of people are using vector sort of stuff. But there's also just like other methods and people are offering like hosted solutions and we want our abstractions to work with that as well. So we shouldn't bake in this paradigm of doing like semantic search too heavily, which sounds like basic now, but I think like, you know, to start a lot of it was people needed help doing these things. But then there was like managed things that did them, hybrid retrieval mechanisms, all of that. I think another example of this, I mean, Langsmith, which we can maybe talk about was like very kind of like, I think we worked on that for like three or four months before announcing it kind of like publicly, two months maybe before giving it to kind of like anyone in beta. But this was a lot of debugging these applications as a pain point. We hear that like just understanding what's going on is a pain point. I mean, you two did a webinar on this, which is called Agents vs. Chains. It was fun, baby.…

Stored transcript either side of the excerpt. The highlighted words are the published quote; the surrounding text is unedited source, never generated.