Inference Providers - Best Way to Build with Open Source Models
HuggingFace via YouTube
-
34
-
- Write review
AI, Data Science & Cloud Certificates from Google, IBM & Meta
Master Production-Ready Machine Learning, Step by Step
Overview
Google, IBM & Meta Certificates – 40% Off
One plan covers every Professional Certificate on Coursera.
Unlock All Certificates
Learn how to leverage Hugging Face's unified Inference Providers API to seamlessly integrate open-source AI models into your applications through a single, consistent interface. Discover how to access and utilize various AI capabilities including chat completions with large language models, image generation, and embedding creation using real Python code examples. Master the process of selecting appropriate models and providers from the Hugging Face Hub using the "Inference available" filter, and understand how to create fine-grained access tokens with proper permissions for inference provider calls. Explore the transparent pricing model with zero Hugging Face markup, learn about free monthly credits available for different account tiers, and monitor your usage through the dedicated dashboard. Gain practical experience with OpenAI-compatible client integration, enabling you to easily swap between different models or providers with minimal code changes while maintaining production-ready deployments.
Syllabus
0:00:00 - Intro: What are HF Inference Providers?
0:01:07 - Selecting models & providers on the Hub
0:04:32 - Creating HF access token
0:06:08 - Chat completions with open‑source LLMs
0:10:09 - Text‑to‑image generation
0:12:30 - Embeddings for RAG
0:14:36 - Pricing, credits, and production tips
Taught by
Hugging Face