BloomTech’s Downfall: A Long Time Coming

Class Central is learner-supported. When you buy through links on our site, we may earn an affiliate commission.

Scrimba

Intro to Mistral AI

via Scrimba

Go to class Write review

Overview

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.
  • 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

Syllabus

  • Intro to Mistral AI
    • 1. Welcome to the course
    • 2. Intro to Mistral by Sophia Yang
    • 3. Sign up for La Plateforme
    • 4. Mistral's Chat Completion API
    • 5. Mistral's Chat Completion API - part 2
    • 6. Mistral's models
    • 7. What is RAG?
    • 8. What are embeddings?
    • 9. RAG - Chunking text with LangChain
    • 10. RAG - Completing the splitDocument function
    • 11. RAG - Creating our very first embedding
    • 12. RAG - Challenge: embedding all chunks and preparing it for the vector db
    • 13. Set up your vector database
    • 14. Vector databases
    • 15. RAG - Uploading data to the vector db
    • 16. RAG - Query and Create completion
    • 17. RAG - Improve the retrieval and complete the generation
    • 18. Function calling
    • 19. Function calling - Adding a second function
    • 20. Function calling - Unpacking the function and arguments
    • 21. Function calling - Making the call
    • 22. Function calling - Updating the messages array
    • 23. Function calling - Creating the loop
    • 24. Running Mistral locally
    • 25. Outro & recap - Mistral AI

Reviews

5.0 rating, based on 1 Class Central review

Start your review of Intro to Mistral AI

  • Profile image for Dhawal Shah
    Dhawal Shah @dhawal
    This course is approximately 90 minutes in length, or longer if you decide to code along.

    While simple, it brings together a number of different concepts, such as RAG, Vectors, Embeddings, and Function Calling, into a single course with working code examples in JavaScript that you can experiment with directly in your browser.
Go to class

Never Stop Learning.

Get personalized course recommendations, track subjects and courses with reminders, and more.

Sign up for free
Someone learning on their laptop while sitting on the floor.