Master LLM Prompt Programming with DSPy – Complete tutorial in 8 amazing examples!

In this video, we talk about Stanford NLP’s DSPy – a new LLM Programming framework that helps with prompting, bootstrapping, optimizing, and fine-tuning Language Models. We go through 8 examples that step by step explain the major concepts behind DSPy and how to build really complex LLM programs with just a few lines of code! Let’s build programs with both LLMs (like ChatGPT, Mixtral, Gemini, LLama-3) as well as local models (like T5, LLama, GPT-1 etc)!

#ai #promptengineering #python

Youtube Members and Patrons will get access to write-ups, slides, notebooks, and bonus content from all videos on my channel!

Patreon post link: https://www.patreon.com/posts/access-to-dspy-109759018

Visit my Patreon link to see what else is available:
https://www.patreon.com/NeuralBreakdownwithAVB

Links:
DSPy Page: https://dspy-docs.vercel.app/docs/intro
How to Setup DSPy: https://github.com/stanfordnlp/dspy?tab=readme-ov-file#1-installation
Intro DSPy Notebook: https://github.com/stanfordnlp/dspy/blob/main/intro.ipynb

Videos you may like:
The Full History of NLP Explained – https://youtu.be/uocYQH0cWTs
Attention to Transformers Playlist – https://www.youtube.com/playlist?list=PLGXWtN1HUjPfq0MSqD5dX8V7Gx5ow4QYW

Timestamps:
0:00 – Intro
0:47 – Prompt Programming vs Engineering
3:14 – Example 1 – Basic QA
6:20 – Example 2 – Chain of Thought
11:43 – Example 3 – Predicting floats, bools, JSON
14:14 – Example 4 – Retrieval Augmented Generation (RAG)
17:49 – Example 5 – Multi Hop
20:33 – Example 6 – Optimizers and Few Shot Prompts
23:54 – Example 6b – Assert and Suggest
25:46 – Example 7 – Generating Datasets
27:35 – Example 8 – Finetune a T5 model with ChatGPT
33:45 – Outro