Add --pinecone-dataset-limit option #44
Merged
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
daverigby
force-pushed
the
dataset_limit
branch
from
051d20d
to
d8218d2
Compare
Add a new option to limit the number documents which should be loaded from a dataset. This allows a workload to be generated based on a given dataset but at a reduced document count. Note: If the dataset includes an explicit 'queries' set then that queries set is used unchanged, and hence Recall may be significanlty reduced as the vectors the query expects to find nearby may not exist. As such, it may be desirable to ignore the query set and instead randomly sample from the (limited) documents set using the --pinecone-dataset-ignore-queries option.
daverigby
force-pushed
the
dataset_limit
branch
from
d8218d2
to
cd697e3
Compare
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Outdated suggestions cannot be applied.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.
Feature
Add a new option to limit the number documents which should be loaded
from a dataset. This allows a workload to be generated based on a
given dataset but at a reduced document count.
Note: If the dataset includes an explicit 'queries' set then that
queries set is used unchanged, and hence Recall may be significanlty
reduced as the vectors the query expects to find nearby may not
exist. As such, it may be desirable to ignore the query set and
instead randomly sample from the (limited) documents set using the
--pinecone-dataset-ignore-queries option.
Type of Change
Test Plan
New unit and integration tests added.