feat: add GuardrailsAI community integration #1298
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
force-pushed
the
feat/guardrailsai-integration
branch
2 times, most recently
from
ab11205 to
71b4a0b
Compare
Pouyanpi
force-pushed
the
feat/guardrailsai-integration
branch
from
71b4a0b to
a12dc8a
Compare
Pouyanpi
changed the title
Codecov Report❌ Patch coverage is Additional details and impacted files@@ Coverage Diff @@
## develop #1298 +/- ##
===========================================
- Coverage 71.68% 71.62% -0.07%
===========================================
Files 168 171 +3
Lines 16862 17020 +158
===========================================
+ Hits 12088 12191 +103
- Misses 4774 4829 +55
Flags with carried forward coverage won't be shown. Click here to find out more.
🚀 New features to boost your workflow:
|
|
Hi Pouyan! This looks great, happy to work on it here. I think I just need to pull down/test through |
|
tested this out, it looks great! |
zsimjee
approved these changes
Aug 26, 2025
Pouyanpi
force-pushed
the
feat/guardrailsai-integration
branch
from
ef55f83 to
c03679a
Compare
|
Thank you @zsimjee, merged. It will be part of 0.16.0 release. |
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Outdated suggestions cannot be applied.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 pull request introduces a new integration for Guardrails AI validators into the NeMo Guardrails framework. It adds support for configuring, registering, and invoking Guardrails AI validators on both input and output text, along with robust error handling and dynamic validator loading. The changes span configuration, core logic, error handling, flow definitions, and registry management.
The most important changes are:
Guardrails AI Validator Integration & Core Logic:
GuardrailsAIRailConfigandGuardrailsAIValidatorConfiginnemoguardrails/rails/llm/config.pyto allow users to specify and configure multiple Guardrails AI validators, including parameters and metadata. Added a method for retrieving validator configs by name. [1] [2]nemoguardrails/library/guardrails_ai/actions.py, including caching, error handling, and mapping of validation results to the NeMo Guardrails format. Added two main actions:validate_guardrails_ai_inputandvalidate_guardrails_ai_output.Configuration & Flow Integration:
examples/configs/guardrails_ai/config.ymldemonstrating how to specify models and set up input/output validation flows using Guardrails AI validators.flows.coandflows.v1.co) to check input and output text with the specified validators, handling failures by either raising exceptions or refusing to respond. [1] [2]Validator Registry & Error Handling:
nemoguardrails/library/guardrails_ai/registry.pyfor mapping validator names to their module/class/hub paths, and logic to fetch validator info from Guardrails Hub if not found in the local registry.nemoguardrails/library/guardrails_ai/errors.pyfor handling configuration and validation errors, with graceful fallback if Guardrails is not installed.Miscellaneous:
__init__.py, actions, errors, registry) [1] [2] [3] [4]These changes collectively enable seamless integration of Guardrails AI validators into the NeMo Guardrails ecosystem, with flexible configuration, dynamic loading, and robust flow control.