Ankush Gola, LangChain — Interview with Alexy

Hello everybody, I'm Alex Krarov from Hello everybody, I'm Alex Krarov from Lakes Hall here on location with Ankush Lakes Hall here on location with Ankush who is the CTO and co-owner of Lakes who is the CTO and co-owner of Lakes Hall in their new office. Have they been Hall in their new office. Have they been here 3 weeks? here 3 weeks? >> Yeah, we've been here for 3 weeks. Yeah, >> Yeah, we've been here for 3 weeks. Yeah, great to have you Alexi. great to have you Alexi. >> So you're hosting the Datafusion with >> So you're hosting the Datafusion with with Hadera. Tell us a little bit like with Hadera. Tell us a little bit like what's your use of Datafusion? How come what's your use of Datafusion? How come you guys picked this? What's like your you guys picked this? What's like your due to Rust? And all these good things. due to Rust? And all these good things. >> Yeah, so we use Datafusion to build our >> Yeah, so we use Datafusion to build our data layer for agent observability. It's data layer for agent observability. It's called Smithy B. It powers our agent called Smithy B. It powers our agent observability product Linksmith. observability product Linksmith. We decided to use Datafusion because We decided to use Datafusion because it just came with a lot of capabilities it just came with a lot of capabilities out of the box. We didn't have to out of the box. We didn't have to reinvent like query planning or reinvent like query planning or optimizer rules or anything like that. optimizer rules or anything like that. It gave us the flexibility to make our It gave us the flexibility to make our own execution plans and optimizer rules own execution plans and optimizer rules and our own dialect and our own dialect for querying as well. So yeah, it was a for querying as well. So yeah, it was a great balance of like batteries included great balance of like batteries included and extensibility. and extensibility. And yeah, it just had a great community And yeah, it just had a great community behind it. So super excited to support behind it. So super excited to support that today with our meet up. that today with our meet up. >> And I just talked with you a little bit >> And I just talked with you a little bit before. So again, I'm learning about 3 before. So again, I'm learning about 3 DB and you think I'm an expert. So you DB and you think I'm an expert. So you mentioned it's basically a novel kind of mentioned it's basically a novel kind of database. It's supporting your own database. It's supporting your own product. It's meant to speed things up product. It's meant to speed things up and basically make agents more and basically make agents more efficient. efficient. >> Yeah, agent observability more >> Yeah, agent observability more efficient. Yeah, so basically the efficient. Yeah, so basically the problem that Smithy B solves is like problem that Smithy B solves is like agent observability is a pretty agent observability is a pretty challenging data infrastructure problem. challenging data infrastructure problem. The payloads associated with agent The payloads associated with agent traces are large. The types of queries traces are large. The types of queries that you have to perform on them are you that you have to perform on them are you know pretty bespoke I would say as well, know pretty bespoke I would say as well, pretty unique. You have to be good at pretty unique. You have to be good at like random access queries, like time like random access queries, like time range scans. You have to be good at range scans. You have to be good at analytics. And so we had to build analytics. And so we had to build something that had the right balance of something that had the right balance of performance, like flexibility, performance, like flexibility, portability for our specific use case. portability for our specific use case. >> Yeah, and so how do you go like do you >> Yeah, and so how do you go like do you program with Rust or do you use program with Rust or do you use Datafusion out of the box like Datafusion out of the box like >> Yeah, we are we are we are we are fully >> Yeah, we are we are we are we are fully like Smithy B is fully built in Rust. like Smithy B is fully built in Rust. Yeah, that's how we're able to leverage Yeah, that's how we're able to leverage data fusion. data fusion. >> yourself Rust developers or do you just >> yourself Rust developers or do you just go like tell your developers like just go like tell your developers like just like go like go >> I I no, absolutely not. [laughter] No, >> I I no, absolutely not. [laughter] No, you cannot write code in a database. Uh you cannot write code in a database. Uh Um no, yeah. So, I'm I'm pretty Um no, yeah. So, I'm I'm pretty hands-on. I've done a lot of the SmithDB hands-on. I've done a lot of the SmithDB development. We have an awesome team development. We have an awesome team here here um of uh um of uh nine people and you know, we're all like nine people and you know, we're all like super hands-on Rust developers and you super hands-on Rust developers and you know, trying to make this thing better know, trying to make this thing better and better. and better. >> So, this is exciting because you know, I >> So, this is exciting because you know, I started the community in July at AWS started the community in July at AWS uh Builder Loft and we really hope you uh Builder Loft and we really hope you guys will come and speak and my promise guys will come and speak and my promise was that AI is now basically Python on was that AI is now basically Python on top and Rust uh beneath. It's like an top and Rust uh beneath. It's like an iceberg. The tip of it is in Python and iceberg. The tip of it is in Python and infra is in Rust. Do you think this is infra is in Rust. Do you think this is the future? This is how we're the future? This is how we're converging? converging? >> Yeah, I mean I I I think like for >> Yeah, I mean I I I think like for certain systems it definitely makes a certain systems it definitely makes a lot of sense to develop in Rust. Um in lot of sense to develop in Rust. Um in some systems it makes less sense to some systems it makes less sense to develop in Rust. Uh but yeah, I mean I develop in Rust. Uh but yeah, I mean I think uh we actually started built you think uh we actually started built you know, LinkSmith was uh there's a lot of know, LinkSmith was uh there's a lot of Python in LinkSmith. We started moving Python in LinkSmith. We started moving some stuff to Go. We moved the entire some stuff to Go. We moved the entire data layer to Rust uh with SmithDB um data layer to Rust uh with SmithDB um and so yeah, I think it's a common and so yeah, I think it's a common pattern that a lot of people take. pattern that a lot of people take. >> So, super excited. Thanks for hosting. >> So, super excited. Thanks for hosting. We're looking forward to talking to you. We're looking forward to talking to you. >> Appreciate it.