jafrank88
jafrank88
Thank you so much! Sorry to have put it in the wrong place. The client is trying to get JSON, but wants it sent back via JSONP but with content-type...
I am seeing this as well, but am unsure if the indexing takes time, or is silent. Is there a way to test this by eliminating all knowledge other than...
Part of the issue might be a change in gpt4all behavior. In the past, when you created a localdocs db, it showed the db and had a bar that showed...
It worked once I deleted the localdocs_v1.db as well as the embeddings_v0.dat
Here is an example of the problem without Q-and-A embedding, 
I posted my logs here and can provide more as needed - https://discord.com/channels/1082486657678311454/1237858420351041576
I am running everything locally.
I am not seeing any text chunks after embedding using Q&A segmentation. Is it possible that feature is broken? When I turn it off and embed files, I can see...
I was able to solve the problem by switching the model to a Chat model and switching it back to a Completion model, but I am not sure that is...
I am seeing this as well. There is some cliff that is hit around 180k vectors maybe. I can upload far more files, but if I try to embed even...