Use pydantic for cache entries and hits #195
Merged
Conversation
This file contains hidden or 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
justin-cechmanek
previously approved these changes
Aug 1, 2024
Collaborator
justin-cechmanek
left a comment
justin-cechmanek
left a comment
There was a problem hiding this comment.
Looks great! Just one note about updating the doc string
| Defaults to "llmcache". | ||
| prefix (Optional[str], optional): The prefix for Redis keys | ||
| associated with the semantic cache search index. Defaults to | ||
| None, and the index name will be used as the key prefix. |
Collaborator
There was a problem hiding this comment.
Add a description for filterable_fields?
And I don't think this raises a Value error if the index name is not provided, so we can drop that comment line.
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Outdated suggestions cannot be applied.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.
This PR handles 2 things:
Uses pydantic for both
CacheEntryandCacheHitmodels. It ended up being better and cleaner to have two separate models.... one for what we write, and the other for what we load.Filtering. @justin-cechmanek I want your feedback on this. I landed on a technique to allow for the user to define a list of
filterable_fieldsas part of the semantic cache class init. What this does is give us a way to support arbitrary filters (scope, permissions, tags, numerics.... anything) within reason. Then you can create anyFilterExpressionand pass through at query time. This extends your initial implementation.