Pixeltable @pixeltablehq

AI Data Infrastructure — Declarative, Multimodal, and Incremental https://t.co/YzWK3wqlz4 pixeltable.com San Francisco Joined August 2024

Tweets

146
Followers

195
Following

17
Likes

141

Pierre Brunelle @pjlbrunelle

2 days ago

pip install pixeltable -> unified storage, orchestration, and retrieval for your multimodal ai workloads right there on your machine.

0 1 1 98 1

Pierre Brunelle @pjlbrunelle

2 days ago

@eersnington @adamwathan @FFmpeg If you struggle with ffmpeg: x.com/pixeltablehq/s…

Pixeltable @pixeltablehq

a week ago

@eersnington @adamwathan @FFmpeg If you struggle with ffmpeg: x.com/pixeltablehq/s…

0 1 3 313 2

Download Image

0 1 1 168 1

🚀 @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

0 4 9 2K 3

Download Image

Pixeltable @pixeltablehq

a week ago

Latest video-related built-in UDFs we added: clip(), extract_frame, segment_video(), concat_videos(), overlay_text(), and VideoSplitter!

0 1 3 313 2

Download Image

Pixeltable @pixeltablehq

a week ago

If you're building AI applications today, you've probably experienced this pain: spending 80% of your time on data infrastructure and only 20% on the AI that actually matters. You're not alone. Traditional data engineering worked great for the SQL era. Build tables, run ETL…

0 3 7 290 1

Pierre Brunelle @pjlbrunelle

2 weeks ago

𝗕𝗬𝗢 𝗲𝗺𝗯𝗲𝗱𝗱𝗶𝗻𝗴𝘀 𝗶𝗻 𝗣𝗶𝘅𝗲𝗹𝘁𝗮𝗯𝗹𝗲. Pixeltable maintains embeddings on updates: • Return pxt.Array[(d,), pxt.Float] for exact dims • Cache the model inside the UDF • Use batch_size for throughput • Drop‑in add_embedding_index

1 1 1 134 1

Download Image

lux 𓅪怪鹰 @lux

2 weeks ago

@BuildWithJit @kurosci i'm building a lot on @pixeltablehq stack lately. Curious what you are using for your processing flow?

0 1 1 74 0

Maxime Rivest 🧙‍♂️🦙🐧 @MaximeRivest

2 weeks ago

1h40 youtube video: Prompt Engineering in Python | Automatic and Programmatic Prompt Optimization | Complete Course How to code, your own, automatic prompt optimizer. How the most advanced prompt optimization tool, DSPy, works and how to fully leverage its capabilities. How…

12 33 178 24K 207

Download Image

Pierre Brunelle @pjlbrunelle

2 weeks ago

Pixeltable SDK: the "primitives" to build real multimodal AI apps (really fast) - create_table: persistent, versioned memory for app state and media - create_view: iterator-driven chunking; incremental updates, no duplication - add_computed_column: declare DAG nodes;…

1 1 1 161 2

Download Image

Pierre Brunelle @pjlbrunelle

2 weeks ago

Your multimodal AI App just hit bad data. Now what?!?! 1) Your AI workloads should handle real-world, messy data without crashing. 2) You should be able to easily isolate and analyze failures without searching through massive log files. 3) You should be able to incrementally…

0 1 2 138 1

Download Image

Pierre Brunelle @pjlbrunelle

2 weeks ago

From One Video to Thousands of Searchable Frames: - Your 30-minute video became 1,800 searchable frames - Zero data duplication (frames materialized on-demand) - Cross-modal search (find frames using text descriptions and/or other images) - Automatic synchronization (add new…

0 3 7 579 4

Download Image

Pierre Brunelle @pjlbrunelle

3 weeks ago

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…

0 3 5 304 3

Download Image

Pierre Brunelle @pjlbrunelle

3 weeks ago

@pixeltablehq automatically versions every change to your data and schema - no configuration required. This isn't just backup functionality; it's a core architectural feature that enables: 1. Automatic Version Tracking - Every table operation (inserts, updates, deletes, schema…

0 1 2 46 0

Pierre Brunelle @pjlbrunelle

3 weeks ago

Why juggle 5+ tools for your multimodal AI Apps stack when you can use 1.

0 1 2 145 0

Download Image

Pierre Brunelle @pjlbrunelle

3 weeks ago

@anshnanda_ Check out @pixeltablehq for your multimodal data infra needs!

0 1 2 50 0

Pierre Brunelle @pjlbrunelle

a month ago

@jacob_weiss_ @shawnshenjx I mean they should use @pixeltablehq. @shawnshenjx you should look at this implementation, happy to jump on a call :) github.com/multi-modal-ai…

0 1 2 185 1

Akshay 🚀 @akshay_pachaar

a month ago

MCP powered multimodal RAG app! It lets you do RAG over: - Audio - Video - Images - And text 100% open-source, here's a step-by-step guide:

Akshay 🚀 @akshay_pachaar

a month ago

MCP powered multimodal RAG app! It lets you do RAG over: - Audio - Video - Images - And text 100% open-source, here's a step-by-step guide: https://t.co/URV1TM5u3q

17 59 551 108K 1K

4 41 212 19K 203

Download Video

Pierre Brunelle @pjlbrunelle

a month ago

You don't need an AI Eval Framework. You need data infrastructure: 1. Ingest evaluation data 2. Apply data preprocessing/feature extraction 3. Run models to generate predictions 4. Compare predictions v. ground truth 5. Compute eval metrics 6. Analyze results & identify issues

0 2 8 336 4

Download Image

Pierre Brunelle @pjlbrunelle

a month ago

@skirano @OpenRouterAI You can also do that in pixeltable and iterative programmatically very fast while deciding if you want it to be ephemeral runs or store results, have lineage and versioning and not just for text :) .. manages rate limits/caching/parallelization... https://t.co/GfO2BJkVcj

2 1 2 624 2

Download Image

Akshay 🚀 @akshay_pachaar

a month ago

I just built the ultimate MCP server for Multimodal AI. It lets you do RAG over audio, video, images and text! 100% open-source, here's the full breakdown...👇