Feat: Unified Output Mapping for Actions #965
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
Pouyanpi
changed the base branch from
develop
to
feat/output-rails-streaming-mvp
Pouyanpi
changed the base branch from
feat/output-rails-streaming-mvp
to
develop
|
required by #966 |
Pouyanpi
commented
Feb 3, 2025
Pouyanpi
commented
Feb 3, 2025
add mapping for prompt_secuirty output mapping refactor: change output_mapping name
Pouyanpi
force-pushed
the
feat/guardrails-library-output-mapping
branch
from
7cf2d1a to
608bb45
Compare
cparisien
approved these changes
Feb 3, 2025
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Outdated suggestions cannot be applied.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.
Unified Output Mapping for Action Responses
This PR introduces a unified mechanism for interpreting the outputs of various actions by adding dedicated mapping functions. These mapping functions determine whether an action’s response should trigger a block (e.g., refuse to respond) based on consistent thresholds and criteria.
Why?
Output mapping is essential because our actions currently return heterogeneous result types and semantics, making it challenging to consistently determine whether an action’s output should be blocked or not.
Key Changes:
@actiondecorator has been extended to accept an optionaloutput_mappingparameter. This mapping is stored in the action’s metadata and is used to interpret the result of the action.