AI is empowering everyone to create data-driven documents. We're proud to announce our @OpenAI ChatGPT plugin integrating Noteable's interactive notebook platform into ChatGPT. Ready for the details? Buckle up for an exciting ride! 🧵

🚀 @pixeltablehq + @pydantic integration! Type safety in Pixeltable just got even better! Define your data models once, get validation everywhere across your storage and orchestration layers: -> pip install pixeltable pydantic | @samuel_colvin

An alternative to Text-to-SQL We launched pxt.retrieval_udf(), a feature that transforms any Pixeltable table into an AI-queryable tool for agentic workflows. Traditional RAG excels at unstructured data (at least Pixeltable does) but struggles with structured information. Now

Pixeltable: AI Data Infrastructure Providing a Declarative, Incremental Approach for Multimodal Apps

@realsohamparekh Good luck! You gonna need a Data Infra that actually handles videos/images/audio then! @pixeltablehq is built by the team who created parquet (the file format), Twitter, Amazon, and Airbnb ML Platforms... You'd be surprise how much we abstract data plumbing for you.

If you want to help build the next-gen open source multimodal AI data infrastructure, DMs open. You'll work alongside people who built: F1/BigTable, parquet format, Impala, Yellowbrick, MapR, Dremio, SanDisk and built the ML platforms at Airbnb/Twitter (X), & Amazon.

@jxnlco I DM'd you my bank information.

The Ultimate Python Library for Multimodal AI Meet Pixeltable—a unified, declarative framework that handles your entire multimodal pipeline, from data storage to model execution. Seamlessly manage images, videos, text, and tabular data—all in one place. 100% open-source.

@levie Memory is simply storage, orchestration, retrieval and indexing. No need for fancy abstraction. You just need a multimodal data infrastructure: https://t.co/dljalCQAlM What matters is the pre- and post-processing from the given “MCP” client to maintain that external memory

@LiorOnAI We should find a more efficient way to configure LLMs other than wasting 24k tokens.

@svpino Thanks for the post @svpino. The updated location for this tutorial is:

@svpino Pixelagent isn't just another agent framework. It's a collection of clear, concise examples demonstrating how to build robust, customizable agent functionality directly on top of @pixeltablehq's data infrastructure. I hope it inspires people to build their own agent class from

Here is a step-by-step tutorial on building a complete stateful OpenAI agent. (If you know Python, this is all you need to learn to build a working agent in an hour, including complete explanations of every component.) This agent: • It's conversational • Has persistent

What do you use for coding in Cursor, as of today?

@mattshumer_ Happy to chat. Long-term memory here in 20 lines of code, lazy evaluation, efficient caching/parallelization... all in the database: https://t.co/Kpf1bNRL2v I've a couple of sample apps on Github where I'm using it already. An infinite-memory discord and multimodal local

Try in Carmel.

Who said there were only 24 hours in a day?

After 1.5 days (still multitasking like crazy on many other stuff). Mostly hooked up to mock endpoints but people who have never built a B2B/C SaaS Product with such complex workflows do not understand how life-changing this is. Dumb stuff such as browse/search/sticky

Wordpress is dead. Vibe coded in 2 hours while multi-tasking with @cursor_ai and @AnthropicAI (Sonnet 3.7) this entirely functioning website with login/sign-up, input forms, blog, custom UI, animations... I didn't write one line of code.

Build an AI RPG Adventure App in 30 minutes. - Define your character, e.g. Elon Musk - Choose Your Genre, e.g. Cyberpunk - Define a starting Scenario, e.g. You're the CEO of Neural Link Industries in Austin, 2049... - Choose your next move 👇

Excited to announce our new open source project: @pixeltablehq – a declarative data infra for multimodal AI apps. Store, transform, index, and iterate on your data through an intuitive table interface. Less compute, less code, more insights, and no more redundant processing.