Show HN: Chat with multiple (100k words) PDFs privately
twitter.com
Embeddings and files stored locally. No Vector databases. Use your own API Key. No login required.
twitter.com
It takes quite abit of time to finish embedding 100k words, thats the most i've tried so far.
After having all the embeddings stored locally, You can begin asking it questions.
Upon asking a question, the question itself is sent to Open Ai for embedding, gets a response, compares against the embedding you stored locally, uses a function called cosine similarity to get the nearest distance of the embeddings (most relevant docs).
Then you link these sources together and send to openai again with the question now in text, to get a reply for your question based on the context.
From OpenAI Docs "Which distance function should I use? We recommend cosine similarity. The choice of distance function typically doesn’t matter much.
OpenAI embeddings are normalized to length 1, which means that:
Cosine similarity can be computed slightly faster using just a dot product Cosine similarity and Euclidean distance will result in the identical rankings"