Image OCR index using vision model #5642
vccler
started this conversation in
Suggestion
Replies: 1 comment
-
working on this as part of our RAG pipeline restructure! |
Beta Was this translation helpful? Give feedback.
0 replies
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
-
some pptx,docx,pdf documents might have images embeded inside. Could we discuss about the implementation of parsing the image via vision model to extract to text format and index into vector database. In this way, it will provide better answer when user ask question about the images.
Beta Was this translation helpful? Give feedback.
All reactions