I want to load a ton of RSS data resources about the technique news, then make it chatgpt as a industry researcher, so he can tell me what is the news of a specific company (from one data resource), what is the advantage of a new technique to another older technique (across a few data resources), what is the technology trending (summarize from a lot of data resources) and so on. I am new to llama_index. I wander which index, query and response mechanisms best suit my expectation. Thanks!
Hi @KeYee ! sounds like an interesting use case. You can define each index as a Tool for use in a langchain agent! https://gpt-index.readthedocs.io/en/latest/guides/building_a_chatbot.html.. for instance, you can define an index for question-answering, an index for summarization, and another index for comparing/contrasting documents
Hi, it's a great honor to get a reply from you directly. May I ask one more question. When I build a tree index based on a folder of hierarchy structure, i.e., a root folder of several subfolders which also have sub-subfolders. Could we make the tree index to build in the same hierarchy as this folder structure?
