
Jerry Liu - Building LlamaIndex, the Data Framework for LLMs
The MaML Podcast - Medicine & Machine Learning
How to Get an Embedding for a Natural Language Question
The idea is that if you have like a question, just like a natural language question, and then you have a set of like relevant documents within your collection that are semantically similar to this question, you can get an embedding for the question. So that's just step one, right? That's like being able to retrieve the relevant documents to the question. And at this point, like you might you haven't even used the language model yet. You send this entire thing to the language model. Hopefully it fits within,. you know, the 4000 token limit. If it doesn't, there's like strategies for dealing with this too. But, you know, assuming it does, then
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.