@neural_avb: Up next: Tool Calling inside RLMs Tools are not called during generation, instead they are python functions injected di…

X AI KOLs Following Tools

Summary

fast-rlm v1.14 introduces direct Python function injection for tool calling, accepts any Python dict as input, guarantees structured output via schema declaration, and allows agents to call subagents.

Up next: Tool Calling inside RLMs Tools are not called during generation, instead they are python functions injected directly into the REPL. The RLM can call them inside the code and store results in a variable within the python session (instead of directly loading into context https://t.co/Ntrrp75ADw
Original Article
View Cached Full Text

Cached at: 05/22/26, 01:41 AM

Up next: Tool Calling inside RLMs

Tools are not called during generation, instead they are python functions injected directly into the REPL.

The RLM can call them inside the code and store results in a variable within the python session (instead of directly loading into context https://t.co/Ntrrp75ADw

AVB (@neural_avb): New version of fast-rlm out today (v1.14)

New features in this release:

  • Input to RLM need not be string, can be any python dictionary
  • Output schema declaration -> RLM is guaranteed to return output in your designed structured output
  • Agents can call subagent with explicit

Similar Articles

Python 3.15.0 candidate 2 is here!

Simon Willison's Blog

Hugo van Kemenade announces the final release candidate for Python 3.15, scheduled for October, and encourages third-party maintainers to prepare their projects by testing and publishing wheels.

Introducing wrapture

Simon Willison's Blog

Introducing wrapture, a new Python library for monkeypatching, testing, and tracing with OpenTelemetry support, entirely AI-assisted in its development.