Add Long-Term Memory

[al-yakubovich]

Let's assume my dataframe has a few columns with textual data. I want to ask a question about which LMM model should have domain-specific knowledge to answer this question. This domain-specific knowledge comes in this case from columns with textual information, and the system is able to find the most relevant cells with text and generate an answer based on this information (let's say my question + text from the top 10 most relevant cells from the dataframe). So for such functionality, we need to have those columns, as well as my question, embedded and put into a vector search database. It would be nice if pandas-ai would have such functionality.  So it is essentially how AI assistants with knowledge databases work. I was wondering if it would be possible to add such functionality to Pandas AI as well.