Microsoft open-sources Fabric-RLM: LLMs write code to recursively chew through big data
adnan_hashmi · x · 2026-09-26
Sandeep Pawar of Microsoft's Fabric CAT team open-sourced Fabric-RLM, a Python library implementing the Recursive Language Model (RLM) in Microsoft Fabric, tackling the pain of large CSVs, wide Excel files and PDF batches that don't fit in context — or answers you can't verify.
Built on MIT's RLM paper (Alex Zhang, Tim Kraska, Omar Khattab) and DSPy's RLM module: instead of stuffing everything into the prompt, the model writes Python, runs it in a subprocess inside your notebook session, inspects results, fixes its own code and recurses. Users supply a plain-English task, inputs (Lakehouse files, Delta tables, semantic models, CSVs...) and an output contract of fields and types. The author spent 5 months on it.
Related event: Microsoft Open-Sources Fabric-RLM for Recursive LLM Data Processing(2 posts)→
More from coding & agent
- The best post on evals: a demo doesn't prove your AI agent is reliable in production — alex_verem · 2026-09-27
- GPT 6 (Non-Astra) Underdelivers: Devs Report Prompt Misreads, UI Rewrites, and Long-Task Failures — vaishnavsm · 2026-09-27
- Antigravity + Gemini 3.8 Flash builds PDF corpora at scale with a bulk-conversion skill — doodlestein · 2026-09-27
- Dev: Astra is the most capable model behind an agent, but its context handling is trash — Unique-Werewolf-2784 · 2026-09-27
- Nearly every prompt injection I catch hides in the HTML, not the visible text — kumard3 · 2026-09-27
- Production agent dev: every AI memory tool is a vector store in a trench coat — According_Bee_2957 · 2026-09-27