Replies: 4 comments
-
![]() |
Beta Was this translation helpful? Give feedback.
0 replies
-
I re-run for about an hour and can process more than 700 chunks, but I have about 40,000 chunks, so this time cost is unbearable. |
Beta Was this translation helpful? Give feedback.
0 replies
-
Or does it support multiple processes inserting into the same workdir? |
Beta Was this translation helpful? Give feedback.
0 replies
-
I've verified it, it's very slow, it doesn't seem feasible |
Beta Was this translation helpful? Give feedback.
0 replies
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Uh oh!
There was an error while loading. Please reload this page.
Uh oh!
There was an error while loading. Please reload this page.
-
Do you need to ask a question?
Your Question
Due to the large amount of data, I divided the data into multiple copies. In order to prevent conflicts, I chose different workdirs for processing. Does LightRAG support merging different workdirs or unified query processing so that I don’t have to make the same query request in different workdirs? This is my ultimate appeal.
Now what I do is merge the kv_store_llm_response_cache.json in different workdirs, then delete other files and rerun (as mentioned in the link #1280). Even with the cache, I found that the speed is much slower than I expected.
Additional Context
No response
Beta Was this translation helpful? Give feedback.
All reactions