This is crazy good 🤯

The OpenAI-based AI-edits feel almost antiquated in that context.

Getting appetite for a small SQL editing model to make this faster. Bit concerned about potential quality (or lack thereof), and heterogeneity of clients, but may be worth a try.. Or Groq/SambaNova?.. :)

We also have an eval space on huggingface where you can evaluate different prompts and models (for DuckDB) -->
huggingface.co/spaces/duckd...
And a leaderboard -->
huggingface.co/spaces/duckd...

It's an interesting question. Thinking that pay-as-you-go endpoints with general purpose models + rag/prompt eng. may be the more practicable and economical choice here. You could do 10k requests/month with a few $. I'm also working on a paper on how to do that well for DuckDB Text2SQL.

Interested in a *PhD in Data Engineering* in Berlin? Our institute has several openings for PhD positions as part of its graduate school, see the post below!

And check out the following page for details on how to work with the DEEM Lab as part of the graduate school deem.berlin#jobs-189196

Just realized the video was too long. Here with 3x speedup 🏃

Updated our MCP connector and docs recently. It's super easy to install and gives your Claude Desktop, DuckDB superpowers!

🔗 pypi.org/project/mcp-...

Trying today's #AdventOfCode with #DuckDB and a tiny 🤏 bit of help 🍿🙆‍♂️ - Claude Desktop & the MCP connector for DuckDB solved it in <3 minutes?

Here's the solution it came up with 👀 gist.github.com/tdoehmen/8a6...

Added support for local DuckDB pypi.org/project/mcp-... and a new system prompt with lots of knowledge about DuckDB syntax and functions. Feel free to give it spin - curious how it works for you @davidgasquez.com

Created a experimental MCP server for MotherDuck earlier today, happy to share the code or add local duckdb support pypi.org/project/mcp-...

3 - I'm not sure how to feel about text-only interfaces in that context, esp. with tool-to-tool communication in mind. Maybe I'm missing something, but wish I could just pass an arrow table from the MotherDuck connector to Claude's Data Anlayst. @anthropic.com :)

2 - I believe the true power of this comes from being able to use different tools in the same context. E.g. "Here are some spreadsheets, a presentation, a few docs, and a s3 bucket with some sales data. Tell me what happened in the last 2 months, and put it into context of recent political events"

1 - I like the idea of extending Claude's capablities with e.g. large-scale data analytics, knowledge retrieval etc., all within Claude's familiar user interface.

Experimented a bit with @anthropic.com's Model Context Protocol (MCP) - it feels like a nice UX for local tool use. Pushed a simple @motherduck.com connector to PyPI that enables querying MotherDuck tables with #Claude Desktop.

Here's how to get started:
pypi.org/project/mcp-...

Some thoughts..🧵

fresh fresh, DuckDB now has a llms dot txt at duckdb.org/duckdb-docs.md