Mike Porter

I've just posted a new video: Text-to-SQL: Create Logical Plans & Prune Your Schema w/ piglets & Apex-SQL. This video is the first time sharing a modular text-to-SQL toolkit I've been working on called piglets. See comments.

Text-to-SQL: using piglets to prepare your context with @duckdb and @openai In this video we use piglets 🐷 to prepare our context for the text-to-SQL step. It also demonstrates a new piglets primitive, Policies. youtube.com/watch?v=cNXm1t…

piglets v0.1.14 - Now includes Semantic Linking, this is a Text-to-SQL technique taken from Apex-SQL where we combine a schema agnostic plan with a database schema to produce schema specific guidance. github.com/mportdata/pigl…

@sspaeti I’m looking forward to reading this later. I love a solution that’s vendor agnostic.

Instead of duplicating measures in each BI tool, store them centrally in an Analytics API. This is the DRY principle applied to metrics. One metric definition, accessible via GraphQL, SQL, or REST. ssp.sh/brain/analytic…

Use piglets with Gemini-2.5-Flash to perform Logical Planning and Dual-Pathway Pruning on a TPC-H database in @duckdb

Adobe Premiere captions keep transcribing me as saying “Gemini-2.5-Flush”.

piglets Github: github.com/mportdata/pigl… YT Video: youtu.be/MARYRBQY2OE?si… Apex-SQL paper: arxiv.org/abs/2602.16720

piglets is a modular text-to-SQL framework I'm working on. In this video we look at Logical Planning and Dual-Pathway Pruning and use piglets to use those to prune the schema of a @googlecloud @googcloudtech BigQuery dataset using gpt-5.2 from @OpenAI @OpenAIDevs. The approaches here are implementations of methods found in the Apex-SQL paper from @Bowen_Pony et al.

I’m sure Claude Code used to be better at continuing after an internet disconnection.

@leonardojvida @duckdb @motherduck It’s great, it was really straight forward and I didn’t need to do much.

@mportdata @duckdb @motherduck thank you @mportdata, I made it with that goal in mind!

piglets is a text-to-SQL toolkit. Current features: Planning Pruning More features coming soon. All LLM providers supported (via @LangChain). Databases: @googlecloud BigQuery @duckdb @motherduck @Snowflake #texttoSQL github.com/mportdata/pigl…

APIs and limited releases for AI models are not a safety policy, they’re a business model (which is totally ok as long as you’re transparent about it). Especially on cyber-security, they give a false impression of control and safety whereas in reality they massively increase the risks because they create asymmetry of capabilities and much easier/broader use than open-source model weights even from non-technical people.

@leonardojvida massive thanks to yourself and whoever else made this: github.com/leonardovida/d… it meant I could add support for @duckdb and @motherduck in a single train ride.

To see why planning and pruning are useful, and how you can use piglets to do this check out my video: youtube.com/watch?v=MARYRB…

@steipete Great name

MCPorter 🧳 0.9.0 is out. Call MCPs from TypeScript or as CLI - per-server tool filtering - sturdier stdio shutdowns - Windows OAuth URL quoting fix - OAuth config docs - schema-declared string coercion for tool calls github.com/steipete/mcpor…

VIDEO youtube.com/watch?v=MARYRB…

For anyone wondering why my text-to-SQL toolkit is called piglets 🐷: 1. piglets are small = modular 2. I’ve watched so much @ThePrimeagen I now pronounce it text-to-SQueal 🐷

I've just posted a new video: Text-to-SQL: Create Logical Plans & Prune Your Schema w/ piglets & Apex-SQL. This video is the first time sharing a modular text-to-SQL toolkit I've been working on called piglets. See comments.

@Bowen_Pony I’ve implement some parts of your paper here. Great paper and something I’m going to keep implementing more of. Thanks.

🚀 Introducing our new paper: APEX-SQL: Talking to the data via Agentic Exploration for Text-to-SQL! Shifting Text-to-SQL from passive translation to active agentic exploration unlocks up to an 18.33% performance leap on enterprise databases. 📝 Paper: arxiv.org/pdf/2602.16720