Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Created an integration to use llms built for Apple's MLX library #13231

Merged
merged 12 commits into from May 13, 2024

Conversation

dwight-foster
Copy link
Contributor

Description

I created an integration to use llms built for or converted to Apples MLX library. I use my mac often to do machine learning prototyping and wanted to be able to use llama index tools with llms that are optimized to run on it. It uses mlx-lm specifically. I referenced the anthropic and huggingface llm integrations to create this one.

Fixes # (issue)

New Package?

Did I fill in the tool.llamahub section in the pyproject.toml and provide a detailed README.md for my new integration or package?

  • Yes
  • No

Version Bump?

Did I bump the version in the pyproject.toml file of the package I am updating? (Except for the llama-index-core package)

  • Yes
  • No

Type of Change

Please delete options that are not relevant.

  • Bug fix (non-breaking change which fixes an issue)
  • New feature (non-breaking change which adds functionality)
  • Breaking change (fix or feature that would cause existing functionality to not work as expected)
  • This change requires a documentation update

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

@dosubot dosubot bot added the size:XXL This PR changes 1000+ lines, ignoring generated files. label May 2, 2024
Copy link

Check out this pull request on  ReviewNB

See visual diffs & provide feedback on Jupyter Notebooks.


Powered by ReviewNB

Copy link
Contributor

@nerdai nerdai left a comment

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Thanks @dwight-foster! Taking an initial first pass on it. Looks like we need to tailor pants BUILD files as well.

Could you run pants tailor :: in the root of this project and commit/push changes?

If you don't have pants installed, then you can alternatively provide me access to your fork and I can commit changes to your fork/main-branch.

Copy link
Contributor

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Please do write a detailed README for this integration. This appears in our llamahub.ai where a lot of our users will discover our integration packages.

license = "MIT"
name = "llama-index-llms-mlx"
readme = "README.md"
version = "0.1.11"
Copy link
Contributor

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

nit: should we start this at 0.1.0?

Copy link
Contributor

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

@dwight-foster
Copy link
Contributor Author

Thank you for the help @nerdai. I am not really sure why it is still failing. The error log does not give a clear reason. Can you infer anything from it. This is my first time contributing a large integration to this repo so sorry if any of this stuff is obvious.

docs/BUILD Outdated
@@ -1 +1,9 @@
python_sources()

poetry_requirements(
Copy link
Contributor

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Hi @dwight-foster,
Could you share some insights into why this change is required?

Copy link
Contributor Author

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

It was not required. I was trying to figure out why the build failed the first time and so I tried a bunch of ways at the same time. This was what other build files in llm integrations looked like so I changed it to that.

Copy link
Contributor

@ovuruska ovuruska left a comment

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Hi @dwight-foster, I left two comments.


import logging

from typing import Any, Callable, Optional, Union
Copy link
Contributor

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

This import can be extended with Sequence. Sequence was imported in the first line.

Copy link
Contributor Author

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Ok

@dwight-foster
Copy link
Contributor Author

dwight-foster commented May 6, 2024

My tests locally are succeeding. I have run pants test :: and pytest. I am not sure why these are failing. I feel like I missed something obvious but any help would be appreciated thank you.

@logan-markewich
Copy link
Collaborator

@dwight-foster maybe it was overkill, but since this package depends on specific hardware, I don't think it makes sense to run tests for this in our CICD

Since the existing test wasn't really doing anything, I just deleted it for now

@dwight-foster
Copy link
Contributor Author

Ok thank you

@dosubot dosubot bot added the lgtm This PR has been approved by a maintainer label May 13, 2024
@logan-markewich logan-markewich enabled auto-merge (squash) May 13, 2024 15:20
@logan-markewich logan-markewich merged commit b82fe84 into run-llama:main May 13, 2024
8 checks passed
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
lgtm This PR has been approved by a maintainer size:XXL This PR changes 1000+ lines, ignoring generated files.
Projects
None yet
Development

Successfully merging this pull request may close these issues.

None yet

4 participants