In this video, I use 2 state of the art vision models to explore how they do on tasks such as answering questions based on charts and tables. Plus, 2 other cool use-cases for leveraging these vision models.
Please LIKE and SUBSCRIBE.

Links:
Code: https://github.com/mktaop/qna_vision
Langchain CLIP multimodal embeddings: https://python.langchain.com/docs/int...