Find answers from the community

Updated 2 months ago

I am building a RAG with llamaindex and

I am building a RAG with llamaindex and I need to connect multiple modules to get this working. I want to have a;
  1. SQL query engine
  2. Vector Search
  3. Keyword search
  4. Image search (OpenAI ClIP)
How can I build a system like this? I have seen examples but till now i couldn't find any examples having more than 2 retrievers.
W
H
2 comments
Maybe a combination of different query engines handled with RouterQueryengine ?
I just had a look at RouterQueryengine and I want to use LLMMultiSelector as I want to do all the searches simultaneously and then pass the results from each retriever to cohere reranker to get the final top_k results.

Is there any way to use multiple workers with RouterQueryEngine to speed up the process?
Add a reply
Sign up and join the conversation on Discord