I am trying to make a RAG-based chatbot application that lets the user prompt in natural language and receive relevant information that can be retrieved a collection of from multiple tables, all of which are independent of each other. These tables range from either > 300 documents to 1000–10000 documents. Each table includes a “Part Number” attribute, along with information about that Part Number relating to whatever table it is in (for example: all repair logs of a part are on that repairlogs table). I am having trouble accurately searching through my vector database and returning the relevant rows that the user might be looking for.