Closed Quantisan closed 1 year ago
this PR includes 15 journal PDFs and loading them into an in-memory vector store using Llama Index.
note that the default OpenAI embedding keeps throwing me rate limiting errors. So just using a default rudimentary model on localhost to move along.
this PR includes 15 journal PDFs and loading them into an in-memory vector store using Llama Index.
note that the default OpenAI embedding keeps throwing me rate limiting errors. So just using a default rudimentary model on localhost to move along.