can u save openai embedding. Im working with Langchain and i dont want to keep emedding the same 300pg book over and over. Can i save it to disk like and index some how?

is there better control for indexing. Some of my data got dropped and doesnt match outside documentation any more

so if im trying to do a QA on 150 page book i should learn pinecone too?

Not really, the library is under active construction. They keep adding new features regularly, so the community just hasn't had enough time make guides and tutorials. At least thats what I tell my self as cant find anything and am confused. Fun fact its not in GPT3 either its so new... This Discord is very active and incredibly helpful for me so far, also look at LangChain and its resources. Looking at both together has really helped me.

i am trying to make a QA model over news articles with meta data. Right now the best option looks like to use the composable Indices on each article then tie those index them

What format of data is the best for loading them into a a model. I currently have them as a csv. Is it better to keep them as csv or convert to json , Knowledge Graph, let the model scrape them from the URL on its own or is there a better option not listed?

Im working on a news project and got GPTSimpleVectorIndex to work on 100news articles in a csv. I have no idea where to start on a prompt to start asking questions on what s in those 100 articles. Any suggestions or resources would be greatly appreciated