Private Data Inference on PLGrid Infrastructure

This training introduces basic inference concepts through examples on private data. During this session, you are going to learn how to use RAGs to tune the conversation with a model on a given document, how to make the model utilize custom functions, e.g., a weather app, and a fast way to create a UI with Gradio UI. The training will be held on PLGrid infrastructure, namely the PLGrid LLM Forge. It is an LLM inference service deployed on Cyfronet supercomputers. A brief introduction to PLGrid LLM Forge will be provided at the end of the training. The course is intended for PLGrid users who want to start using LLMs without the complicated setup.

Level

Agenda

1. Introduction to inference
2. RAG concepts:
   1. Document indexing
   2. RAG in action
   3. Conversation management
3. Tool calling
4. Gradio UI
5. PLGrid LLM Forge overview

Requirements

Basic knowledge of Python.

No recommended training before this one.

No account required.

Participants' computers should be internet browser.

Venue

The workshop will be held online via Zoom. The meeting link will be sent to registered participants.

Language

English

Duration

2 h

Registration

The Registration and the Waiting list close automatically after 26th June 2026. The Registration may close prematurely if the limit number of participants is hit beforehand, but the Waiting List will be available until the deadline above.