Retrieval Augmented Generation (RAG) with any LLM using Llama Index and Milvus

preview_player
Показать описание
Fully functional example of Retrieval Augmented Generation (RAG), where a vector database (Milvus) is used to capture embeddings of scraped web content, which can then be 'plugged in' to an LLM like OpenAI GPT4, all done on my Mac laptop via APIs and Llama Index.

#llamaindex #chatgpt #openai #llm #vectordb #milvus
Рекомендации по теме
Комментарии
Автор

Excellent STUFF! new subsribe and i will be watching all your future AI/LLM/ videos. Thanks again!

brookster
Автор

Great intro in to a very interesting topic. I suspect, that crawling PDFs or other documents should be possible to?!

seon