feat: add Google embedding integration

[bwook00]

Description

Add Google Embedding provider

@Pouyanpi,

I used langchain-google-genai.

However, if you're worried about the ‘langchain dependency’, I can change the method to directly use from google import genai.

Related Issue(s)

Fixes #1292

Checklist

• I've read the CONTRIBUTING guidelines.
• I've updated the documentation if applicable.
• I've added tests if applicable.
• @mentions of the person or team responsible for reviewing proposed changes.

[github-actions]

Documentation preview

https://nvidia.github.io/NeMo-Guardrails/review/pr-1304

[Copilot]

Pull Request Overview

This PR adds Google embedding integration to the NeMo Guardrails project by implementing a new GoogleEmbeddingModel provider that uses the langchain-google-genai library.

• Implements GoogleEmbeddingModel class with sync/async embedding capabilities
• Adds comprehensive test suite for Google embeddings functionality
• Updates documentation to include Google as a supported embedding provider

Reviewed Changes

Copilot reviewed 6 out of 6 changed files in this pull request and generated 2 comments.

Show a summary per file

File	Description
nemoguardrails/embeddings/providers/google.py	Main implementation of GoogleEmbeddingModel class with encoding methods
nemoguardrails/embeddings/providers/init.py	Registers the Google embedding provider in the system
tests/test_embeddings_google.py	Comprehensive test suite including sync/async tests and live integration tests
tests/test_configs/with_google_embeddings/config.yml	Test configuration for Google embeddings
tests/test_configs/with_google_embeddings/config.co	Test flow configuration
docs/user-guides/configuration-guide.md	Documentation update adding Google to supported providers table

Comments suppressed due to low confidence (1)

tests/test_embeddings_google.py:70

• This function has the same name as the async function on line 52 but different signature. Consider renaming to 'test_sync_live_query' to differentiate from the async version.

def test_live_query(app):

[codecov-commenter]

Codecov Report

❌ Patch coverage is 40.90909% with 13 lines in your changes missing coverage. Please review.
✅ Project coverage is 70.40%. Comparing base (bee719b) to head (4e0cd50).

Files with missing lines	Patch %	Lines
nemoguardrails/embeddings/providers/google.py	35.00%	13 Missing ⚠️

Additional details and impacted files

@@             Coverage Diff             @@
##           develop    #1304      +/-   ##
===========================================
- Coverage    70.45%   70.40%   -0.05%     
===========================================
  Files          161      162       +1     
  Lines        16214    16235      +21     
===========================================
+ Hits         11423    11431       +8     
- Misses        4791     4804      +13     

Flag	Coverage Δ
python	70.40% <40.90%> (-0.05%)	⬇️

Flags with carried forward coverage won't be shown. Click here to find out more.

Files with missing lines	Coverage Δ
nemoguardrails/embeddings/providers/__init__.py	96.42% <100.00%> (+0.13%)	⬆️
nemoguardrails/embeddings/providers/google.py	35.00% <35.00%> (ø)

🚀 New features to boost your workflow:

• ❄️ Test Analytics: Detect flaky tests, report on failures, and find test suite problems.
• 📦 JS Bundle Analysis: Save yourself from yourself by tracking and limiting bundle sizes in JS merges.

[Pouyanpi]

Hi @bwook00, once again thanks for your patience on this PR.

I have one request: could you please use the google-genai SDK directly instead of langchain-google-genai? This keeps our embedding providers consistent with how we handle other external APIs (OpenAI, Cohere, etc.).

How we'll proceed:
0. We'll merge #1446

1. We'll merge feat: add Cohere embedding integration #1305 (Cohere) first
2. Once merged, please rebase your PR onto develop
3. Add mock-based tests following the pattern in tests/test_embeddings_providers_mock.py

In the meantime you can update your implementation to use google-genai directly.

The testing infrastructure is now in place, so once you rebase and make these changes, we should be able to merge quickly.
Definitely we'll include your PRs in 0.18.0 release.

Please let me know if you have any questions!