All videos
0:00 / 0:00
research

Llama 3 RAG Demo with DSPy Optimization, Ollama, and Weaviate!

Connor Shorten17 June 2026Watch on YouTube

What you'll learn

  • Llama 3 delivers improved performance metrics and training insights for LLM applications
  • DSPy framework integrates with Llama 3 through Ollama for RAG implementations
  • MIPRO optimization automatically finds the optimal prompt configuration for your use case

Frequently asked questions

What is RAG and how does it work with Llama 3 and DSPy?
RAG (Retrieval-Augmented Generation) combines retrieving external information with generation. The video demonstrates how Llama 3, DSPy, and Weaviate form a RAG system where MIPRO optimizes the prompts.
What is MIPRO and what is it used for?
MIPRO is DSPy's optimization tool that automatically finds the best prompts for your Llama 3 model without manual prompt engineering.
How does Llama 3 run locally through Ollama?
Ollama enables running Llama 3 locally on your machine, eliminating the need for a cloud API and giving you full control over your model.
What is Weaviate's role in this setup?
Weaviate serves as the vector database for the RAG system, enabling efficient retrieval of relevant information before Llama 3 generates answers.

Topics

llama-3ragdspyllm-frameworksprompt-optimization

In this video

WeaviateWeaviate

Read next

Description from the channel

Hey everyone! Thank you so much for watching this overview of Llama 3 looking at the release notes and seeing a demo of how to integrate it with DSPy through Ollama and how to use DSPy's MIPRO to find the optimal prompt when using this new large language model for RAG! We are hosting an event in San Francisco on May 1st with Arize AI and Cohere, featuring a talk from Omar Khattab, the lead author of DSPy! Hope to see you there! https://lu.ma/dspy Introducing Meta Llama 3: https://ai.meta.com/blog/meta-llama-3/ Ollama Llama 3: https://ollama.com/library/llama3 Weaviate Recipes: https://github.com/weaviate/recipes/blob/main/integrations/llm-frameworks/dspy/llms/Llama3.ipynb Chapters 0:00 Llama3!! 1:28 Release Notes 5:35 Performance Reporting 9:50 Training Details 17:32 DSPy Demo!