I have pdf file consisting of many tabular unstructured data only. I have to summarise the every table separately. I have used RAG on it. can you tell me other methods that I can use for this use case.
Maybe you would like to elaborate more on the architecture and the flow of the use case. Eg. Vector databas. Are you using LangChain or ? Etc. Cheers
So I am extracting text from pdf and splitting it into chunks. These chunks are converted into embeddings and these embedding are stored in vector database FAISS.I am using langchain for my use case.