Implementing personalization with Gorilla #56
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Outdated suggestions cannot be applied.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.
Personalization with Bash history
Leveraging the synthesis of user's bash history to see if we can personalize the responses from Gorilla. We also use Microsoft Presidio to anonymize their bash history as well just in case. This is to prevent the model from processing a user's private information. An example synthesis of bash history looks like:
"The user appears to be working with Python and AWS. They have used pip to install several Python packages, specifically 'presidio_analyzer' and 'presidio_anonymizer'. They have also used python commands to execute URLs. Most notably for the context of the query, user ran 'gorilla' commands relating to AWS, such as listing all files in the current directory, moving a file from one bucket to another, and listing all AWS instances. Finally, they executed an 'export' command possibly setting an AWS location. The user is now interested in their AWS history. This context suggests that the user may be doing some data analysis on AWS and wants to retrace their steps or review their activities on AWS."