Around PyConES? Check out Marcelo Trylesinski, The FastAPI Expert, talk about Generative AI Monitoring with #PydanticAI and #Logfire. 🗓️ Saturday, October 18 at 12pm (local time) He will show how PydanticAI enables more reliable agent responses, while Logfire provides real-time insights for efficient troubleshooting. #pythoncommunity #pyconespana #python #pydantic #opensource
Pydantic
Software Development
First we build Pydantic, next Pydantic Logfire - uncomplicated observability
About us
From the team behind Pydantic, Logfire is a new type of observability platform built on the same belief as our open source library — that the most powerful tools can be easy to use.
- Website
-
https://pydantic.dev
External link for Pydantic
- Industry
- Software Development
- Company size
- 2-10 employees
- Type
- Privately Held
- Founded
- 2022
Employees at Pydantic
Updates
-
Pydantic reposted this
By default, LLMs output unstructured text. But thanks to structured outputs, you can guide LLMs to output structured data instead, according to your precise schema. That makes LLMs way more helpful for automation workflows, entity extraction, and classification. That's what we talked about in today's live stream: https://lnkd.in/evE3W_Xr We showed how to define schemas using Pydantic models, including field descriptions, enums, and nested models. Then we showed entity extraction scenarios, processing GitHub issues, webpages, Word documents, PDFs, Images, and more! Oh and I did a bonus demo of my LinkedIn agent, which uses Pydantic-AI with structured outputs to read my LinkedIn networking requests and decide whether to accept or ignore. Structured outputs are sooo dang useful.
-
-
Looking to learn how to design and build reliable agents that run for hours? Join our founder Samuel Colvin and Jason Liu tomorrow for an online session on Building Durable Agents with Pydantic AI. Sign up! https://lnkd.in/eqGErq2F #pydanticai #pydantic #logfire #durableagents
Samuel Colvin from Pydantic is joining me tomorrow at 2pm EDT to talk about what most agent frameworks ignore: durable execution. The problem: your agents die after one conversation. The workflows you actually need run for hours, manage state across multiple steps, and need to survive failures and restarts. Pydantic AI integrates with Temporal specifically to solve this. Tomorrow Samuel is walking through the architecture decisions that make it work: state management that persists, job tracking and monitoring, streaming results over long runtimes, and how to design agents for real economic value instead of chat demos. This isn't about making better chatbots. It's about building agents that can handle the complex, multi-step workflows businesses actually need. Be sure to register: https://lnkd.in/g4hunici (notes + recording sent to everyone who signs up)
-
Apache DataFusion is arguably the most exciting open source analytical database right now. it was definitely the right choice of database for Pydantic Logfire. Adrian Garcia Badaracco and the Pydantic database team are contributing back to the open source project to make the database even faster for us and the community. #apachedatafusion #opensource #community #pydanticlogfire
I was fortunate to be involved in this amazing effort within the Apache DataFusion community to make some queries 25x faster (some more, some less, read the blog post for more!). Thank you to Andrew Lamb and the amazing community for making this happen! https://lnkd.in/d5Day266
-
We just released a brand new #SQL linting feature on our #observability platform, Pydantic #Logfire! 🚀 We have enhanced our SQL editor to lint your queries before execution time. Now, it catches issues like misspelled keywords, duplicate field names, or missing columns and group by clauses. And since it knows your schema, the editor also flags invalid column references and suggests how to correct it. It is based on Apache DataFusion's powerful diagnostic errors. Hear more from our Databaseologist Matthew Kim on the video below. #pydantic #PydanticLogfire #ApacheDataFusion #aiobservability
-
Last night, we joined the folks at CopilotKit for an evening building Fullstack Agents with Pydantic AI & AG-UI. Thank you Composio for having us! #agents #pydanticai #agui #pydantic
-
-
Pydantic reposted this
🗓️Tonight: Join us for a hands-on workshop, building Fullstack Agents with Pydantic AI & AG-UI. Build your first PydanticAI Agent, and learn how to hook it up to a Frontend application with Samuel Colvin & Tyler Slaton! Generously hosted at Composio's awesome new offices in The Embarcadero🌉 🧑💻Come with your laptop, prepared to build-along! https://luma.com/j9he9xe9
-
-
Pydantic v2.12 is here! 🚀 ✨Support for Python 3.14: lazy type annotations (PEP 649 & 749) 🎯 A new MISSING sentinel: differentiate between default values and None 📦 PEP 728 Support: TypedDict with typed extra items for more flexible validation 🔗 Smarter URL Handling - Preserve empty URL paths More details on https://lnkd.in/eP5vNSY9 #pydantic #pydanticvalidation #opensource #release #python314
-