-
-
Notifications
You must be signed in to change notification settings - Fork 325
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
Allows specifying chunk size and overlap with /learn #267
Conversation
We need to document chunk size and overlap, including the default, in both the user docs and the user interface. As a user, why would I need to modify these values? |
@JasonWeill |
Can you please add something about these new options to the docs for the |
9138ed0
to
21aae4f
Compare
for more information, see https://pre-commit.ci
* Allows specifying chunk size and overlap with /learn * [pre-commit.ci] auto fixes from pre-commit.com hooks for more information, see https://pre-commit.ci * Refactored as per PR review comments * [pre-commit.ci] auto fixes from pre-commit.com hooks for more information, see https://pre-commit.ci * Documents -c and -o options * Update docs/source/users/index.md --------- Co-authored-by: pre-commit-ci[bot] <66853113+pre-commit-ci[bot]@users.noreply.github.com> Co-authored-by: Jason Weill <jweill@amazon.com>
* Allows specifying chunk size and overlap with /learn * [pre-commit.ci] auto fixes from pre-commit.com hooks for more information, see https://pre-commit.ci * Refactored as per PR review comments * [pre-commit.ci] auto fixes from pre-commit.com hooks for more information, see https://pre-commit.ci * Documents -c and -o options * Update docs/source/users/index.md --------- Co-authored-by: pre-commit-ci[bot] <66853113+pre-commit-ci[bot]@users.noreply.github.com> Co-authored-by: Jason Weill <jweill@amazon.com>
Summary
Current implementation of
/learn
has fixed values for chunk size and overlap which is impractical for all document types and models. Adding options for specifying these attributes will allow power users to quickly experiment and select the options that work best for their document types and model selected. This PR adds these new options to the/learn
command and stores these values in the metadata, so that relearn works when embedding models are switched.Usage