-
Notifications
You must be signed in to change notification settings - Fork 4.5k
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
add nvidia nim rerank support #13178
Conversation
Signed-off-by: Zenodia Charpy <zcharpy@nvidia.com>
Signed-off-by: Zenodia Charpy <zcharpy@nvidia.com>
Signed-off-by: Zenodia Charpy <zcharpy@nvidia.com>
Signed-off-by: Zenodia Charpy <zcharpy@nvidia.com>
Signed-off-by: Zenodia Charpy <zcharpy@nvidia.com>
Signed-off-by: Zenodia Charpy <zcharpy@nvidia.com>
Signed-off-by: Zenodia Charpy <zcharpy@nvidia.com>
…list Signed-off-by: Zenodia Charpy <zcharpy@nvidia.com>
…works Signed-off-by: Zenodia Charpy <zcharpy@nvidia.com>
… verify batching works Signed-off-by: Zenodia Charpy <zcharpy@nvidia.com>
Signed-off-by: Zenodia Charpy <zcharpy@nvidia.com>
Signed-off-by: Zenodia Charpy <zcharpy@nvidia.com>
Signed-off-by: Zenodia Charpy <zcharpy@nvidia.com>
Signed-off-by: Zenodia Charpy <zcharpy@nvidia.com>
Signed-off-by: Zenodia Charpy <zcharpy@nvidia.com>
Signed-off-by: Zenodia Charpy <zcharpy@nvidia.com>
Signed-off-by: Zenodia Charpy <zcharpy@nvidia.com>
Check out this pull request on See visual diffs & provide feedback on Jupyter Notebooks. Powered by ReviewNB |
ids = [DEFAULT_MODEL] | ||
return [Model(id=id) for id in ids] | ||
|
||
def mode( |
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
yea again, this feels like a function that isn't needed? It could be just part of the init right?
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
i agree, this could be part of init. there's low potential for a user to want to create an instance and then mode switch it more than once. this is the design flow we're using consistently across communities. it's also up for review.
Description
this adds the llama-index-postprocessor-nvidia-rerank package for interacting w/ ranking models hosted on ai.nvidia.com.
New Package?
Did I fill in the
tool.llamahub
section in thepyproject.toml
and provide a detailed README.md for my new integration or package?Version Bump?
Did I bump the version in the
pyproject.toml
file of the package I am updating? (Except for thellama-index-core
package)Type of Change
Please delete options that are not relevant.
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
Suggested Checklist:
make format; make lint
to appease the lint godsNote
Co-authored with Zenodia Charpy