SQL retriever enhancements for Dell AIDp

[vikalluru]

SQL Retriever Enhancements for Dell AIDp

Summary

Enhances the Asset Lifecycle Management Agent's SQL retrieval capabilities with improved database connectivity and Dell AIDp sandbox compatibility.

Key Changes

SQL Retriever Improvements:

• Enhanced vanna_manager.py and vanna_util.py with better error handling and database connectivity
• Improved SQL query generation and retrieval tool functionality

Dell AIDp Sandbox Compatibility:

• Fixed database path to use /workspace/database/nasa_turbo.db for sandboxed environments
• Fixed module import paths (sys.path.append("/workspace"))
• Made utils imports conditional (only for RUL transformations)
• Disabled automatic retries in code generation (set to 0 for sandbox stability)

Developer Experience:

• Added comprehensive installation guide (INSTALLATION.md)
• Added detailed configuration documentation (configs/README.md)
• Added utils_template/ with pre-built RUL transformation utilities
• Updated dependencies in pyproject.toml

Testing

Addresses customer-reported issues:

• ModuleNotFoundError for utils and mysql modules
• Database connection failures in sandboxed environments
• Fixed critical embed_query interface compatibility issue between ChromaDB and NVIDIA embeddings

Input format fix: ChromaDB passes ['query text'] (list) but langchain expects string - now extracts string to prevent API 500 errors Output format fix: ChromaDB expects [[embedding]] but langchain returns [embedding] - now wraps result to prevent TypeError: 'float' object cannot be converted to 'Sequence' Resolves embedding failures that prevented SQL query vector search from working