Intro to Mistral AI

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

• 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