[Issue]: llama-index-core (0.10.65) depends on nltk (>=3.8.2) and tenacity (>=8.2.0,<8.4.0 || >8.4.0,<9.0.0)

[asynchat]

Is there an existing issue for this?

• I have searched the existing issues
• I have checked #657 to validate if my issue is covered by community support

Describe the issue

Because no versions of graphrag match >0.2.1,<0.2.2 || >0.2.2,<0.3.0
and graphrag (0.2.1) depends on nltk (3.8.1), graphrag (>=0.2.1,<0.2.2 || >0.2.2,<0.3.0) requires nltk (3.8.1).
And because graphrag (0.2.2) depends on tenacity (>=9.0.0,<10.0.0)
and llama-index-core (0.10.65) depends on nltk (>=3.8.2), if graphrag (>=0.2.1,<0.3.0) and llama-index-core (0.10.65) then tenacity (>=9.0.0,<10.0.0).
And because llama-index-core (0.10.65) depends on tenacity (>=8.2.0,<8.4.0 || >8.4.0,<9.0.0)
and no versions of llama-index-core match >0.10.65,<0.11.0, graphrag (>=0.2.1,<0.3.0) is incompatible with llama-index-core (>=0.10.65,<0.11.0).

Steps to reproduce

No response

GraphRAG Config Used

# Paste your config here

Logs and screenshots

No response

Additional Information

• GraphRAG Version: v0.2.2 v0.3.0
• Operating System: MACOS
• Python Version: 3.11
• Related Issues:

[RobinBially]

Thanks for the issue! I have the same problem with langchain.

[AlonsoGuevara]

Hi!

We have an open PR to update nltk to 3.8.2 #902 however it introduced some breaking changes we need to dive deeper into.

For Tenacity we are currently at 9.0.0
Since this is for running a model we don't officially support out of the box I would recommend to downgrade trenacity in your local clone, and perhaps keep an eye over the nltk PR. I'll look fwd to merge this soon

Thanks for reporting this!