Jerry Liu - Building LlamaIndex, the Data Framework for LLMs
The MaML Podcast - Medicine & Machine Learning
The Pros and Cons of the Lama Index Method
The basic stack is you just have a vector database like a pine cone from a milvis. And then you take in a bunch of documents, store it in the vector database, do like the top K embedding search from the database and send it to the language model. So that's like just a very basic stack of it's called like retrieval augmented generation. But for us, though, we are really trying to generalize this into some framework that really solves a lot of different use cases around like retrieval and synthesis.
00:00
Transcript
Play full episode
Remember Everything You Learn from Podcasts
Save insights instantly, chat with episodes, and build lasting knowledge - all powered by AI.
