Bootstrap KNN with Random Search #1825
Open
Conversation
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
CyrusNuevoDia
force-pushed
the
bootstrap-knn-few-shot-with-random-search
branch
from
fb2c355 to
c8d3d98
Compare
- Implement `__init__` method in `Embedding` class to accept an optional `api_key`. - Update embedding call to include `api_key` parameter when invoking the embedding model. - Enhance `BootstrapKNN` demo selection process by creating a list of dynamic demos. - Add new dependencies in requirements file for project requirements.
…om-search' into bootstrap-knn-few-shot-with-random-search # Conflicts: # dspy/predict/predict.py # dspy/teleprompt/bootstrap.py # dspy/teleprompt/random_search.py # testing/playbook.ipynb
…m:stanfordnlp/dspy into bootstrap-knn-few-shot-with-random-search
|
Excited to see this merge. |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Add this suggestion to a batch that can be applied as a single commit.
This suggestion is invalid because no changes were made to the code.
Suggestions cannot be applied while the pull request is closed.
Suggestions cannot be applied while viewing a subset of changes.
Only one suggestion per line can be applied in a batch.
Add this suggestion to a batch that can be applied as a single commit.
Applying suggestions on deleted lines is not supported.
You must change the existing code in this line in order to create a valid suggestion.
Outdated suggestions cannot be applied.
This suggestion has been applied or marked resolved.
Suggestions cannot be applied from pending reviews.
Suggestions cannot be applied on multi-line comments.
Suggestions cannot be applied while the pull request is queued to merge.
Suggestion cannot be applied right now. Please check back later.
Current KNNFewShot
Compile Time: Vectorize trainset examples
Test Time:
New BootstrapKNN
Compile Time: Run BootstrapFewShot to collect traces and generate end-to-end demo sets
Test Time:
When a predictor is called, KNN of the input are few-shotted using the augmented demos for that predictor
New BootstrapKNNWithRandomSearch
Compile Time:
Test Time:
When a predictor is called, KNN of the input are few-shotted using the augmented demos for that predictor. If
num_static_demos ≠ 0, then that predictor's demos are shuffled(static demos + knn demos) such thatlen(static demos + knn demos) == max_labeled_demos