Build a RAG in 10 minutes! | Python, ChromaDB, OpenAI
RAG is an essential methodology for everyone who wants to get real value out of Large Language Models. With RAG you minimize the risk for hallucination and you are able to provide specific data to the LLM about your use case or organization. In this video you'll build a RAG in 10 minutes!
⭐️ Links ⭐
🔗 Download all scripts: https://tomstechacademy.com/retrieval...
🔗 Download the PDF: https://edis.ifas.ufl.edu/publication...
🔗 ChromaDB documentation: https://docs.trychroma.com/getting-st...
🔗 LangChain documentation: https://python.langchain.com/v0.1/doc...
⭐️ Timestamps⭐
00:00 - Intro
00:21 - Preparation of the environment
00:49 - Download the PDF file
01:25 - Filling the semantic database (fill_db.py)
03:01 - How to get started with ChromaDB
03:50 - Splitting a PDF file to chunks with LangChain
05:08 - Adding data to ChromaDB
06:28 - Creating the retrieval part with OpenAI
09:22 - Testing the RAG
⭐️ Follow me ⭐
💼 LinkedIn: / thomas--janssen
✅ Instagram: / tomstechacademy
❗ Some of my videos contain affiliate links. When you click on these kind of links, I get a small percentage in case you make a purchase via the website. Be aware that this doesn't cost you anything - you never pay more than the standard retail price.
#largelanguagemodels #rag #python
