search

infiniflow / ragflow

RAGFlow is an open-source RAG (Retrieval-Augmented Generation) engine based on deep document understanding.
https://ragflow.io
Apache License 2.0
22.88k stars 2.24k forks source link

[Bug]: Can not parse docs on V0.13 #3182

Closed galen1980guo closed 1 week ago

galen1980guo commented 1 week ago

Is there an existing issue for the same bug?

Branch name

main

Commit ID

latest

Other environment information

No response

Actual behavior

image

Expected behavior

No response

Steps to reproduce

Can not parse docs on V0.13, always stuck.

Additional information

No response

KevinHuSh commented 1 week ago

Check the status of both redis and task executor.

galen1980guo commented 1 week ago

Check the status of both redis and task executor.

I found that it was very slow and not really stuck, but it was really stuck until the knowledge graph was used to parse it. like below:

galen1980guo commented 1 week ago

截屏2024-11-04 17 28 00

wbhob commented 1 week ago

CleanShot 2024-11-04 at 09 49 24@2x Services show as available, but I am facing the same problem, can not figure out why I am unable to ingest

KevinHuSh commented 1 week ago

There's yellow bar which means Task executor seems not well conditioned. Watch the memory usage. It's usually caused by lack of RAM.

wbhob commented 1 week ago

For some reason, a clean install and erasing the db actually fixed it. Thanks for the help here!

glowzz commented 1 week ago

how to delete db?

KevinHuSh commented 1 week ago

docker compose down -v All the data will be erased.

wbhob commented 1 week ago

in my case I went into docker desktop and deleted the corresponding volumes as well, if that helps