A simple web application for a OpenAI-enabled document search. This repo uses Azure OpenAI Service for creating embeddings vectors from documents. For answering the question of a user, it retrieves the most relevant document and then uses GPT-3, GPT-3.5 or GPT-4 to extract the matching answer for the question.
Hi,
Congrats for this amazing demo!
I am facing the following issue:
When I add 66 pdfs in batch, the files are converted but the embeddings are not created. If I add a single document it works properly.
In this screenshot you can see that the first document has embeddings (the file added as a single document), but the rest of them have not embeddings:
Thanks! Angel