본문으로 건너뛰기

Retrieval Augmented Generation with LlamaIndex

In this session you'll learn how to get started with Chroma and perform Q&A on some documents using Llama 2, the RAG technique, and LlamaIndex.
Dan Becker
Dan Becker

무료 계정 만들기

실습 문제하고 트랙하세요.

Google로 계속하기계속 진행하시면 다음 사항에 동의하는 것으로 간주됩니다: 이용약관 및 개인정보 처리방침 그리고 귀하의 데이터가 미국에 저장된다는 점에 동의하는 것으로 간주됩니다.

함께 코드 따라하기

코드 따라하기 ↗

Large language models (LLMs) like Llama 2 are the must-have technology of the year. Unfortunately, LLMs can't accurately answer questions about your business because they lack enough domain knowledge. The solution is to combine the LLM with a vector database like Chroma—a technique known as retrieval augmented generation (RAG). Beyond this, incorporating AI into products is best done with an AI application framework, like LlamaIndex.

In this session you'll learn how to get started with Chroma and perform Q&A on some documents using Llama 2, the RAG technique, and LlamaIndex.

Key Takeaways:

  • Learn how to store text in the Chroma vector database.
  • Learn how to use retrieval augmented generation to combine LLama 2 and Chroma.
  • Learn how to develop AI applications using LlamaIndex

Additional Resources

[COURSE] Dan's course: Introduction to Deep Learning in Python

[CODE-ALONG SERIES] Become a Generative AI developer

[SKILL TRACK] OpenAI Fundamentals

[SKILL TRACK] Deep Learning in Python

[BLOG] The Top 5 Vector Databases

[TUTORIAL] Mastering Vector Databases with Pinecone: A Comprehensive Guide

주제

관련

블로그

Advanced RAG Techniques