1 Prerequisites This skill 5 Unlocked

Skill · Applied AI · Understand, serve and integrate language models

Call an LLM from Python: completion, streaming, conversation, structured output and images

Call an LLM from Python with LiteLLM or the Ollama SDK: completion, streaming, conversation, parallel calls and JSON output validated by Pydantic.

Start lesson 1The Applied AI domain

• 5 lessons
• ~4 h 35 of reading
• 5 quizzes
• 0 proof lab

The path

Where it comes from, where it leads

What you need to know first, where you stand on this skill, and what it opens next. Your status is computed in your browser, from what you have read and passed.

Before · 1 prerequisite

• Read and transform data (JSON, YAML, APIs)

Recommended before · 2

• Run and serve an open source LLM, from the workstation to the GPU
• Write reliable prompts: roles, few-shot, Chain-of-Thought and ReAct

This skill, for you

Call an LLM from Python: completion, streaming, conversation, structured output and images

Computing

It unlocks · 5 skills

• Build a tool-using AI agent: ReAct loop, function calling and typed output
• Analyze an LLM application's risks with the OWASP Top 10 for LLM 2025 and choose defense-in-depth controls
• Operate an LLM gateway: routing, fallback, cache, keys and budgets
• Trace LLM calls with OpenTelemetry GenAI up to Grafana Tempo
• Embed a corpus and index it in a vector database

Lessons

How to learn it

5 lessons, about ~4 h 35, in program order. Each lesson ends with its quiz.

The program

5 lessons · ~4 h 35

1. 1Introduction à LiteLLM (in French)· 65 min
2. 2Appels asynchrones (in French)· 70 min
3. 3Ollama : SDK Python et Structured Output (in French)· 70 min
4. 4Ollama : sorties structurées (JSON / Pydantic) (in French)· 35 min
5. 5Ollama : vision (Gemma 4, Llama 3.2) (in French)· 35 min

Beyond the lessons

Assess, practise, pass the proof

Reading a lesson confirms nothing. A skill is confirmed by a passed quiz, practised in a guided lab, and put to the test by a challenge or a mission; an imported lab result is not verified by the site.

Assess yourself

5 quizzes

At the end of the lessons: passed at 70%, they confirm the skill.

Practice

No guided lab

No guided lab practices it yet.

Proof

No proof

Neither a challenge nor a mission with a proof yet.

Around it

Who requires it, who teaches it

Required by

No published job requires it yet.

Taught by

• Python IA (in French)

Same block · Understand, serve and integrate language models

• Explain how an LLM works, its inference and its quantization
• Write reliable prompts: roles, few-shot, Chain-of-Thought and ReAct
• Run and serve an open source LLM, from the workstation to the GPU
• Operate an LLM gateway: routing, fallback, cache, keys and budgets

×

See in the glossary →