Pydantic, every mention
46 scenes, the whole family · ← back to Pydantic
tap a year for its mentions
every year anyone Samuel Colvin 58Shawn Wang 37Alessio Fanelli 11Jason Liu 4Michelle Pokrass 1Jerry Liu 1Alex Duffy 1
Verbatim, from the transcripts: the passages where Pydantic comes up
⚡️Monty: the ultrafast Python interpreter by Agents for Agents — Samuel Colvin, Pydantic
- ▶ 0:07 Shawn Wang We are here with Sam Colvin from Pydantic, who's recently launched Monty. 2 times in the scene
- ▶ 0:15 Shawn Wang How's Pydantic and Pydantic AI?
- ▶ 1:05 Samuel Colvin I think Pydantic Logfire, our observability platform. 2 times in the scene
- ▶ 6:36 Samuel Colvin Um, those of us who are maintaining Pydantic, it's a tiny number. 3 times in the scene
- ▶ 11:02 Samuel Colvin You can do some Pydansic validation of some JSON data by basically having an external function called. 3 times in the scene
- ▶ 18:21 Samuel Colvin CodePuppy is a coding agent built by an amazing guy called Michael Faffersberger at Walmart built with Pydantic AI.
- ▶ 23:20 Samuel Colvin So this is a Pydansky AI agent in this particular mode. 3 times in the scene
- ▶ 25:00 Samuel Colvin It'll be probably more interesting to look at what's going on inside log fire. 2 times in the scene
- ▶ 29:42 Samuel Colvin I mean, one of the things we're doing now in Pydantic AI is where we're about to introduce, I think there's a PR out for this.
⚡️The Future of Notebooks - with Akshay Agrawal of Marimo
- ▶ 0:18 unnamed speaker Uh, thanks to Samuel Colvin from Pydantic to, for the introduction, you know, we saw him at the AI engineer summit in New York and he was like, you should have, you should have these guys on, on the pod.
⚡️Launching AI Diplomacy: the hardest LLM Game Benchmark yet - Alex Duffy
- ▶ 20:22 Alex Duffy I know one of our GitHub issues already called us out for not using Pydantic parsing and instead of having like eight different try catches for the different JSON versions that come out of these.
The Creators of Model Context Protocol
- ▶ 1:17:21 unnamed speaker Um, you know, some of the people from Pydantic have commit access to the, the Python SDK because they did a lot of really good work there.
The Agent Network — Dharmesh Shah, Agent.ai + CTO of HubSpot
- ▶ 13:08 Alessio Fanelli That's been one of the hot topics with LandGraph and Pydantic and all that.
Agent Engineering with Pydantic + Graphs — with Samuel Colvin, CEO of Pydantic Logfire
- ▶ 0:15 Shawn Wang And today we're very excited to have Sam Colvin join us from Pydantic.ai. 6 times in the scene
- ▶ 0:25 Samuel Colvin I would say you might need Pydantic AI and Logfire as well, but, um, it gets you a long way, that's for sure.
- ▶ 2:28 Samuel Colvin So I originally didn't implement JSON Schema inside Pydantic and then Sebastian, Sebastian Ramirez, FastAPI came along and like the first I ever heard of him was over a weekend. 9 times in the scene
- ▶ 5:14 Alessio Fanelli And then how do you kind of prioritize, okay, this is worth going into more of the, and we'll talk about Pydantic AI and all of that.
- ▶ 5:29 Samuel Colvin I'll answer that, but I'll answer, which I think is like a kind of parallel question, which is Pylantic's weird because Pylantic existed obviously before I was starting a company. 3 times in the scene
- ▶ 5:57 Samuel Colvin Writing like 30,000 lines of rust just to release open source free Python library. 5 times in the scene
- ▶ 6:51 Samuel Colvin Good general purpose observability inside log fire and making Pydantic good for general purpose use cases. 2 times in the scene
- ▶ 7:41 Alessio Fanelli And then at the same time, then you released Pedente KI recently, which is a, um, you know, agent framework. 3 times in the scene
- ▶ 7:47 Alessio Fanelli And early on, I would say everybody like, you know, Langchain and like a Pedente kind of like a first class support. 3 times in the scene
- ▶ 10:16 Alessio Fanelli Like, uh, what does Pydantic can I do? 3 times in the scene
- ▶ 10:18 Samuel Colvin I glaze over a bit when I hear all of the different sorts of frameworks, but I like, and I, I will tell you when I built Pydantic, when I built Logfire and when I built Pydantic AI, my methodology is not to go and like, 2 times in the scene
- ▶ 16:08 Shawn Wang You say imagine, but like right now this pedantic AI actually resume, you know, six days later, like you said, or is this just like a theoretical thing we can go someday? 4 times in the scene
- ▶ 19:48 Samuel Colvin They just, they basically, they're having some struggles working out how to manage, ironically, dependencies that have binaries, in particular Pydantic, because these workers, where you can have thousands of them on a given metal machine,… 3 times in the scene
- ▶ 20:37 Samuel Colvin So Pydive has builds for, for Pydantic Core and for things like NumPy and basically all of the popular, like binary libraries.
- ▶ 20:57 Shawn Wang Okay, staying on graphs a little bit more, and then I wanted to go to some of the other features that you have in Panasonic AI. 2 times in the scene
- ▶ 24:47 Samuel Colvin Yeah, and it makes complete sense, and one of the things we've seen with agents is they work well when they work well, but when they, even if you have the observability through Logfire that you can see what was going on, if you don't have…
- ▶ 27:45 Shawn Wang There's sort of other, other parts of Pydantic AI that are worth commenting on. 3 times in the scene
- ▶ 30:54 Samuel Colvin It uses Pydantic, so I'm biased, but I mean, I think it's, I think it's pretty well respected anyway.
- ▶ 32:38 Samuel Colvin I think it's something that we're going to be working on soon, both in Pydantic AI and in Logfire to try and support better because like it's an unsolved problem. 2 times in the scene
- ▶ 32:38 Samuel Colvin I think it's something that we're going to be working on soon, both in Pydantic AI and in Logfire to try and support better because like it's an unsolved problem. 5 times in the scene
- ▶ 43:19 Shawn Wang Any other observations just about building Logfire, actually? 4 times in the scene
- ▶ 43:36 Shawn Wang So, uh, yeah, so to be clear, it's Pydantic Logfire and the company is, is one company that has kind of two products, an open source thing and a, and a observability thing, correct? 2 times in the scene
- ▶ 47:19 Samuel Colvin We were able, I was able to go and implement that in a weekend using our JSON parser that we built for Pidantic Core.
- ▶ 48:39 Shawn Wang But you know, my last question on Logfire is really, you know, at some point you run out sort of community goodwill just because like, oh, I use Pydantic. 5 times in the scene
- ▶ 48:39 Shawn Wang But you know, my last question on Logfire is really, you know, at some point you run out sort of community goodwill just because like, oh, I use Pydantic. 8 times in the scene
- ▶ 50:44 Samuel Colvin So Pydantic and Pydantic AI are MIT licensed and like, you know, properly open source. 4 times in the scene
- ▶ 1:00:48 Samuel Colvin if anyone who has like looked at PyDance AI, we know it's not complete yet. 2 times in the scene
- ▶ 1:01:17 Samuel Colvin And so as a company, we, we get that like making Pydantic AI the best agent framework is existential for us.
Why every AI Engineer needs an AI Gateway (ft Portkey.ai CEO)
- ▶ 4:22 unnamed speaker Not to pick on them, like, you know, Langchain, Pydantic, which we also just talked to is like, all this doesn't belong in your app code.
Building AGI with OpenAI's Structured Outputs API
- ▶ 12:21 Michelle Pokrass So you just create like a Pydantic object or a Zod object and you pass it in and you get back an object.