/openaiworkshop

Primary LanguageJupyter NotebookMIT LicenseMIT

OpenAI workshop

Created by: Denise Schlesinger, Limor Levi and Vlad Feigin

⚡ Build OpenAI applications to search your own data ⚡ This agenda covers a range of topics, from the basics of LLMs and GPT to more advanced topics like prompt engineering and embeddings. The labs provide hands-on experience with OpenAI, including connecting to the platform, creating prompts, and working with embeddings. The final lab even allows participants to ask SQL database questions in English, demonstrating the power of OpenAI in natural language processing.

Agenda

  • 1- Presentation - Introduction to LLMs, GPT and prompts
  • 2- Lab #1 - Connect to OpenAI and ask questions
  • 3- Lab #2 - Create prompts for summarization, json, tabular answer
  • 4- Presentation - Embeddings (30 mins)
  • 5- Lab #3 - Create embeddings in pandas
  • 6- Presentation - Langchain, Vector databases, agents, toolkits (30 mins)
  • 7- Lab #4 - Create embeddings with Faiss and Langchain
  • 8- Lab #5 - Ask your SQL DB questions in English
  • 9- Presentation - Lab #6 - Cognitive services + OpenAI
  • 10- Lab #6 - Cognitive services + OpenAI

Requirements