zlacker

>>johnjw+(OP)
I also found pure RAG with vector search to not work. I was creating a bot that could find answers to questions about things by looking at Slack discussions.

At first, I downloaded entire channels, loaded them into a vector DB, and did RAG. The results sucked. Vector searches don't understand things very well, and in this world, specific keywords and error messages are very searchable.

Instead, I take the user's query, ask an LLM (Claude / Bedrock) to find keywords, then search Slack using the API, get results, and use an LLM to filter for discussions that are relevant, then summarize them all in a response.

This is slow, of course, so it's very multi-threaded. A typical response will be within 30 seconds.

>>thefou+G71
When you’re creating your embedding you can store keywords from the content (using an LLM) in the metadata of each chunk which would positively increase the relevancy of results turned from the retrieval.

LlamaIndex does this out of the box.

>>siquic+nb1
That's interesting! I didn't know that