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.

Sign up for GitHub

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

Jump to bottom

Add RankGPT support inside RankLLM #12475

Merged
merged 39 commits into from Apr 3, 2024
Merged

Add RankGPT support inside RankLLM #12475

merged 39 commits into from Apr 3, 2024

Conversation

xpbowler
Copy link
Contributor

@xpbowler xpbowler commented Apr 2, 2024

Description

  • Add RankGPT support inside RankLLM
  • Add sliding window example to RankLLM
  • Add parameter for choosing step_size
  • Remove redundant example notebook in docs/docs/examples/node_postprocessor

xpbowler and others added 30 commits March 21, 2024 19:39
@xpbowler
Integrate RankLLM
7015d50
@xpbowler
Fixed integration bugs
9ca7052
@xpbowler
fixed reranker
075fb68
@xpbowler
change documentation md
317f6af
@xpbowler
add llama-index-integrations folder
3fcd6ef
@xpbowler
rankllm integration package
96e9915
@xpbowler
remove core integration file for rankllm
bde7e72
@xpbowler
add pip install rank_llm
fb2ca64
@xpbowler
merge upstream/main
d65ffe8
@xpbowler
add enum type for model type
7b8704f
@xpbowler
Merge remote-tracking branch 'upstream/main'
ac8a8db
@hatianzhang
cr
f6742ec
@hatianzhang
cr
12555c3
@hatianzhang
cr
ed2c901
@hatianzhang
cr
1b1ba7d
@hatianzhang
cr
6d1391f
@hatianzhang
cr
eddfde7
@hatianzhang
cr
9c88f83
@xpbowler
Merge remote-tracking branch 'upstream/main'
e9f5b55
@xpbowler
add rank-llm dependency, update documentation, fix example ipynb
ac09f0e
@xpbowler
Merge remote-tracking branch 'upstream/main'
1226c8a
@hatianzhang
cr
015863b
@hatianzhang
cr
785be73
@hatianzhang
cr
7789bde
@xpbowler
rank_llm pypi package
9644b08
@xpbowler
Merge branch 'main' of https://github.com/xpbowler/llama_index
ae95f31
@xpbowler
Merge remote-tracking branch 'upstream/main'
369bd5b
@xpbowler
add rank-llm dependency locally instead
ae7c028
@xpbowler
add sliding window example, add step_size to api
179f4ab
@xpbowler
resolved merge conflicts
d2b4bb7
@dosubot dosubot bot added the size:XL This PR changes 500-999 lines, ignoring generated files. label Apr 2, 2024
@review-notebook-app Review Notebook App
Copy link

Check out this pull request on  ReviewNB

See visual diffs & provide feedback on Jupyter Notebooks.

Powered by ReviewNB

logan-markewich
logan-markewich reviewed Apr 2, 2024
View reviewed changes
docs/docs/examples/node_postprocessor/rankLLM.ipynb Outdated
Copy link
Collaborator

Choose a reason for hiding this comment

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

Any reason to remove (or move?) this notebook? (now it won't show up in the docs, maybe we should replace it with the one you added below?)

Copy link
Contributor Author

Choose a reason for hiding this comment

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

oh i see, i'll add it back

logan-markewich
logan-markewich reviewed Apr 2, 2024
View reviewed changes
...or/llama-index-postprocessor-rankllm-rerank/llama_index/postprocessor/rankllm_rerank/base.py Outdated
from rank_llm.result import Result

self._result = Result

if model_enum == ModelType.VICUNA:
Copy link
Collaborator

Choose a reason for hiding this comment

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

Curious why we removed the enum? Seemed helpful for validation

Copy link
Contributor Author

Choose a reason for hiding this comment

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

we'd need to add another parameter gpt-type, or continuously update the enums to match the available openai models.

I wanted to keep the API clean. Tho thinking more, i think its ok adding another optional parameter, if that sounds good.

logan-markewich
logan-markewich reviewed Apr 2, 2024
View reviewed changes
Copy link
Collaborator

@logan-markewich logan-markewich left a comment

Choose a reason for hiding this comment

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

A couple of nits, but looks good otherwise

@dosubot dosubot bot added size:M This PR changes 30-99 lines, ignoring generated files. and removed size:XL This PR changes 500-999 lines, ignoring generated files. labels Apr 3, 2024
@xpbowler
Copy link
Contributor Author

xpbowler commented Apr 3, 2024 •
edited

A couple of nits, but looks good otherwise

@logan-markewich fixed, lmk if looks good!

nerdai
nerdai approved these changes Apr 3, 2024
View reviewed changes
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.

Can we also bump the version (patch) number in pyproject.toml?

@dosubot dosubot bot added the lgtm This PR has been approved by a maintainer label Apr 3, 2024
@logan-markewich logan-markewich merged commit 8aa2ea3 into run-llama:main Apr 3, 2024
8 checks passed
chrisalexiuk-nvidia pushed a commit to chrisalexiuk-nvidia/llama_index that referenced this pull request Apr 25, 2024
@xpbowler @chrisalexiuk-nvidia
Add RankGPT support inside RankLLM (run-llama#12475)
2d4648d
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Reviewers

@logan-markewich logan-markewich logan-markewich left review comments

@nerdai nerdai nerdai approved these changes

Assignees
No one assigned
Labels
lgtm This PR has been approved by a maintainer size:M This PR changes 30-99 lines, ignoring generated files.
Projects
None yet
Milestone
No milestone
Development

Successfully merging this pull request may close these issues.

None yet
5 participants
@xpbowler @ronakice @logan-markewich @nerdai @hatianzhang