Skip to content

Add Asset Lifecycle Management (ALM) agent implementation#13

Draft
vikalluru wants to merge 9 commits intoNVIDIA:mainfrom
vikalluru:feature/add-alm-agent
Draft

Add Asset Lifecycle Management (ALM) agent implementation#13
vikalluru wants to merge 9 commits intoNVIDIA:mainfrom
vikalluru:feature/add-alm-agent

Conversation

@vikalluru
Copy link

  • Add complete ALM workflow for predictive maintenance of turbofan engines
  • Include SQL retrieval tools using Vanna AI
  • Add RUL (Remaining Useful Life) prediction tools with XGBoost and MOMENT foundation model
  • Include anomaly detection and visualization tools
  • Add NASA turbofan engine degradation dataset
  • Include comprehensive documentation and evaluation framework
  • Add MOMENT time-series foundation model integration as embedded content

Description

Closes

By Submitting this PR I confirm:

  • I am familiar with the Contributing Guidelines.
  • We require that all contributors "sign-off" on their commits. This certifies that the contribution is your original work, or you have rights to submit it under the same license, or a compatible license.
    • Any contribution which contains commits that are not Signed-Off will not be accepted.
  • When the PR is ready for review, new or existing tests cover these changes.
  • When the PR is ready for review, the documentation is up to date with these changes.

@copy-pr-bot
Copy link

copy-pr-bot bot commented Jan 26, 2026

This pull request requires additional validation before any workflows can run on NVIDIA's runners.

Pull request vetters can view their responsibilities here.

Contributors can view more details about this message here.

- Add complete ALM workflow for predictive maintenance of turbofan engines
- Include SQL retrieval tools using Vanna AI
- Add RUL (Remaining Useful Life) prediction tools with XGBoost and MOMENT foundation model
- Include anomaly detection and visualization tools
- Add NASA turbofan engine degradation dataset
- Include comprehensive documentation and evaluation framework
- Add MOMENT time-series foundation model integration as embedded content

Co-Authored-By: Claude Sonnet 4.5 <noreply@anthropic.com>
@vikalluru vikalluru force-pushed the feature/add-alm-agent branch from 6d4b2ae to 3d36be4 Compare January 26, 2026 05:12
vikalluru and others added 3 commits January 25, 2026 21:15
- Add comprehensive repository overview and architecture documentation
- Include build, test, and linting instructions
- Document NAT component registration pattern
- Add YAML configuration structure examples
- Include dependency management guidelines
- Add Git commit signing requirements (GPG -S flag)
- Document code style, licensing, and security requirements

Co-Authored-By: Claude Sonnet 4.5 <noreply@anthropic.com>
- Remove industries/asset_lifecycle_management/data/ (NASA turbofan datasets)
- Remove industries/asset_lifecycle_management/moment/ (MOMENT foundation model)
- Remove .gitmodules (no longer using submodules)
- Update .gitignore to exclude these folders
- Files remain available locally for development

This reduces repository size while keeping necessary files for local testing.

Co-Authored-By: Claude Sonnet 4.5 <noreply@anthropic.com>
…n files

- Move asset_lifecycle_management from industries/ to examples/
- Remove industries/ directory
- Track only README.md files among markdown files
- Exclude: COMPARISON.md, INSTALLATION.md, MIGRATION_SUMMARY.md, README_MIGRATION.md
- All code, configs, and data files preserved locally
- Update .gitignore with specific file exclusions

This reorganizes the repository structure while keeping all essential documentation.

Co-Authored-By: Claude Sonnet 4.5 <noreply@anthropic.com>
@vikalluru vikalluru force-pushed the feature/add-alm-agent branch from dce5b67 to a74c639 Compare January 26, 2026 05:37
- Add E2B code execution tool implementation
- Add E2B sandbox wrapper with file upload/download
- Add E2B configuration documentation
- Add E2B sandbox test script

E2B provides cloud-hosted code execution without requiring Docker.
Files are automatically uploaded to sandbox and downloaded after execution.

Signed-off-by: Vineeth Kalluru <vikalluru@nvidia.com>
Integration changes:
- Fix code_generation_assistant for async E2B integration
- Add stdout/stderr list-to-string conversion for E2B results
- Update config with E2B usage instructions and commented template
- Consolidate to nat_alm_agent package name

Project reorganization:
- Move SQL tool comparison files to new_sql_tool_exploration/ (deferred)
- Add .gitignore for exploration folder
- Add CLAUDE.md session notes
- Update MOMENT library numpy constraint (>=1.26.2)

Testing:
- E2B integration fully tested and working
- Files successfully created and downloaded from cloud sandbox
- TODO: Verify local Docker sandbox still works with changes

Signed-off-by: Vineeth Kalluru <vikalluru@nvidia.com>
@vikalluru vikalluru force-pushed the feature/add-alm-agent branch from ae839a2 to 9a076a0 Compare January 27, 2026 07:00
Changes:
- Ignore output_data/*.json files (runtime-generated)
- Ignore CLAUDE.md session notes (not for version control)
- Ignore test scripts (test_alm_workflow.py, test_e2b_sandbox.py)
- Consolidate E2B and SSL documentation into configs/README.md
- Update main README.md with E2B cloud sandbox information

Removed from tracking:
- Test scripts (now gitignored for local development)
- Session notes (CLAUDE.md)
- Output data JSON files (runtime artifacts)
- Redundant config documentation (consolidated into README)

Documentation improvements:
- Added E2B vs Local Docker comparison table
- Added E2B setup instructions with SSL troubleshooting
- Added E2B configuration examples
- Consolidated all config-related docs into single README

Signed-off-by: Vineeth Kalluru <vikalluru@nvidia.com>
Removed folders:
- eval_output_old/ (old evaluation artifacts)
- example_eval_output/ (example evaluation outputs)
- test_comparison_output/ (test comparison results)

These folders contain runtime-generated evaluation and test artifacts
that should not be version controlled. Added to .gitignore.

Signed-off-by: Vineeth Kalluru <vikalluru@nvidia.com>
Provides users option to switch between MOMENT-1-Large (default) and
NV Tesseract NIM for anomaly detection in sensor data.

Changes:
- Add nv_tesseract_anomaly_detection_tool.py with NIM-based implementation
- Update register.py to import NV Tesseract tool
- Add NV Tesseract configuration section in config-reasoning.yaml
- Update system prompt to document both anomaly detection options
- Add sensor data retrieval patterns to vanna_training_data.yaml
- Document NV Tesseract setup and comparison in README.md

NV Tesseract advantages: production-grade accuracy, forecasting,
detailed anomaly scores, and specific sensor identification.
MOMENT advantages: local execution, no API key, offline support.

Signed-off-by: Vineeth Kalluru <vikalluru@nvidia.com>
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Labels

None yet

Projects

None yet

Development

Successfully merging this pull request may close these issues.

1 participant