Go Pro!Bootcamp

Bootcamp

Study group

Collaborate with peers in your dedicated #study-group channel.

Code reviews

Submit projects for review using the /review command in your #code-reviews channel

Intro to Mistral AI

Enroll for freeGet started!

Join 838 other students

Log in to get

Access to all our free courses
Interactive hands-on content
100s of code challenges
Join a friendly community
Enroll for free
Subscribe to access!Subscribe to access!

Subscribe to access to this course and ALL other courses. You get a 30-day money-back guarantee, no questions asked.

Subscription includes

All courses and career paths
100s of coding challenges
Certificates of completion
Exclusive Pro members chat
The course creator Per Harald Borgen

with Per Harald Borgen

Course level: Intermediate

Learn how to use the Mistral AI to build intelligent apps, all the way from simple chat completions to advanced use-cases like RAG and function calling. Created in collaboration between Mistral AI and Scrimba.

You'll learn

La Plateforme

Chat Completions API

Streaming

Mistral 7B

Mistral 8x7B

Mistral's commercial models

Embeddings

Vectors

Setting up a vector database

Semantic search

Chunking with LangChain

RAG

AI agents

Function calling

Ollama

Running models locally

man

Prerequisites

Before taking this course, you should have an intermediate level understanding of Vanilla JS including working with APIs and async JavaScript. Below are our suggested resources to get you up to speed.

Created in partnership with

Mistral AI is a pioneer in open-source development of Large Language Models (LLMs), founded by ex-employees of Meta Platforms and Google DeepMind.

Meet your teacher

The course creator

Per Harald Borgen

Front-end developer and co-founder of Scrimba. Per loves helping other people learn new skills so that they can improve their lives. He makes his tutorials as simple as humanly possible, and focus on getting the students to the point where they can start building projects on their own.

Follow me on twitter

Why this course rocks

Get up-to-speed with Mistral AI through a crash course developed in partnership with the AI provider itself.

Throughout 25 interactive lessons, you will learn how to build intelligent applications that span from straightforward chat completions to complex functionalities like Retrieval-Augmented Generation (RAG) and function calling.


Starting off, you’ll get an introduction to Mistral's open-source models, including Mistral 7B and Mistral 8x7B, and progresses to their commercial models. You'll gain hands-on experience leveraging the full suite of Mistral’s La Plateforme.

The rest of the course is mainly focused on two essential paradigms in AI engineering: knowledge retrieval and AI agents. In the first part, you’ll learn how to split text documents with LangChain, convert them into embeddings, store them in a vector database, and finally perform retrieval.

In the AI agents segment, you’ll learn how to give Mistral access to the functions within your app, and let their models decide when to call them. This skill will enable you to create a whole new type of user experience, where people can interact with your apps through conversation instead of mere clicking.

Towards the end, we will also go through how you can use Ollama to easily run inference on your own computer, and use it as the backbone of any AI app you develop locally.


So if you’re looking for a quick but well-rounded intro to Mistral, this is your perfect course.

F to the A oracle to the Q
What is Mistral AI?

Mistral AI is a Paris-based pioneer in the creation of large language models (LLMs). Founded by ex-employees of Meta Platforms and Google DeepMind, Mistral rose to prominence in the AI community in 2023 when they launched the world’s most capable open-weights LLMs, Mistral 7B and Mixtral 8×7B. Since then, they have also released an API platform, a chat assistant, several commercial models (not open-source), and an improved open-source Mixtral model.

Why use Mistral AI?

A key benefit of Mistral is how flexible their solutions are. Both their open and closed models can be deployed outside of the Mistral platform, either via a cloud provider, or on your own dedicated server, ensuring that the data stays fully within your walls, and with advanced levels of customization.