LlamaIndex
Log in

Find answers from the community

s
F
Y
a
P
Updated last month

Does anyone have any ideas around best

HHABBYMAN
·
Does anyone have any ideas around best practices to ingest documents with Slack?

I want to retain as much metadata as possible for individual messages, but I want the document retrieval to maintain context of the entire conversation. I've tried this two ways:

  1. Each message is its own document, can sucessfully store permalink, timestamp, user in the metadata, but conversational context is lost.
  1. Store multiple messages in documents, cannot link to individual messages, user, timestamp metadata isn't stored due to multiple messages in the doc.
Any ideas how to solve this problem?
L
H
3 comments
LLogan M
Theres an example of at least one approach here
https://www.llamaindex.ai/blog/building-a-slack-bot-that-learns-with-llamaindex-qdrant-and-render-c88d4aa72840
HHABBYMAN
This is basically what I have now - the limitation of it is that it can't take entire conversation threads into account as it handles each message as "fact". If someone were to ask a question in a slack channel, and another user were to respond to the answer without directly mentioning the problem, it wouldn't be relevant in a similarity search. Does that make sense?
LLogan M
yea makes sense. Its a tough problem, I don't think theres a single "good" solution here
Add a reply
Sign up and join the conversation on Discord