Vibeleaderboard
← All Intel
Intel / video

OpenAI Agents SDK Crash Course (with Hugging Face Models)

Source
youtube.com
Author
Hugging Face
Date

Context

A Hugging Face tutorial asks whether OpenAI's Agents SDK, a Python framework for building AI agents that call tools, works only with OpenAI's models. The presenter runs it on an served through Hugging Face's inference providers by adding LiteLLM, an integration layer, and a Hugging Face access token. The SDK's building blocks are agents, handoffs that delegate to another agent, , and sessions that keep a conversation's memory across runs.

Because agents call functions, the model's provider listing must show support. The run also appeared in OpenAI's trace viewer, which logs reasoning, tool call and output per step, though token counts for third-party models show only if usage reporting is switched on. The demo used one small Qwen model, a weather tool and a haiku , so it shows one working setup, not general compatibility.

Terms in this piece · Glossary
  • Open-weight model — A model whose trained weights can be downloaded and run outside the maker's hosted API.
  • guardrails — The checks around a model that block bad inputs and outputs — filters, validators, and permission rules the model itself can't override.
  • tool use — A model's ability to call external functions — run code, search the web, edit files — instead of only generating text.
  • Instruction — A statement in the context that tells the model how to behave or what to do; module 3's first layer.
Read the source www.youtube.com
More from Hugging Face
Recommended reads
Comments

Checking sign-in…

Loading comments…