The community member is trying to figure out the right combination of index types for their chatbot use case. They have already got a streaming chat client and basic QA working with LlamaIndex and GPTSimpleVectorIndex. They need to support two use cases: 1) Translate a long document without summarizing, and 2) Summarize a document. They are unsure if they need to use GPTSimpleVectorIndex with response_mode = 'tree_summary' or create both a GPTListIndex and a GPTSimpleVectorIndex to achieve the summarization use case.
In the comments, a community member suggests checking out a notebook that demonstrates a QA and summary graph. Another community member mentions that the creator of LlamaIndex, Jerry, has been tweeting out some updates. The community members also praise Jerry and the original poster for their work.
There is a discussion about whether a response_mode = 'accumulate' could be a useful feature, and the creator of LlamaIndex indicates that they could add it to their todo list if the community member thinks it's valuable.
Hey, I'm trying to figure out the right combination of index types for our chatbot usecase (we have already got streaming chat client + basic QA with LlamaIndex working beautifully via GPTSimpleVectorIndex). I need to support two use cases basically: 1) Translate -> I need to iterate through a long doc and translate the whole thing without summarising - is this possible? 2) Summarise -> I want to figure out what index / combination of indexes I need to achieve this. I'm not clear if I need to just use GPTSimpleVectorIndex with response_mode = 'tree_summary' or whether I need to create both a GPTListIndex & a GPTSimpleVectorIndex to achieve this? (Note this is for a single document for now). Any points welcome! I can see I can do all these things but it's not clear what combination is optimal for a workflow where I index (upload) and then query ideally in a sort of summary mode or a Q&A mode.
