Relax llama-parse version

[cbornet]

Description

Llama-index pulls llama-parse through llama-index-readers-llama-parse.
The llama-index code doesn't use llama-parse so there is no reason to limit the version of llama-parse that can be used.
The only limitation would be on the version of llama-core but that will be resolved by the package manager.
For instance it's currently not possible to use llama-parse 0.4 with llama-index 0.10.23 although there is no reason for that.

Type of Change

Enhancement

How Has This Been Tested?

Please describe the tests that you ran to verify your changes. Provide instructions so we can reproduce. Please also list any relevant details for your test configuration

• Added new unit/integration tests
• Added new notebook (that tests end-to-end)
• I stared at the code and made sure it makes sense

Suggested Checklist:

• I have performed a self-review of my own code
• I have commented my code, particularly in hard-to-understand areas
• I have made corresponding changes to the documentation
• I have added Google Colab support for the newly added notebooks.
• My changes generate no new warnings
• I have added tests that prove my fix is effective or that my feature works
• New and existing unit tests pass locally with my changes
• I ran make format; make lint to appease the lint gods

[logan-markewich]

Hey @cbornet thanks for the heads up. I actually just merged a similar fix -- should be published and good to go
#12236

[cbornet]

Yes I’ve seen the other fix from my co-worker Nicolo 😄.
The problem is that we’ll face the same issue at the next release of llama-parse.
So I think it’s better to really relax the version range.

[logan-markewich]

The next releases would only be a patch, x.y.z only changing z

Generally if we change y, that's a more major change that may require code changes to work, and should be a bit more careful around