SQL retriever enhancements for Dell AIDp #357
Open
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
vikalluru
force-pushed
the
vikalluru/sql-retriever-enhancements
branch
from
3586933 to
fbde275
Compare
vikalluru
force-pushed
the
vikalluru/sql-retriever-enhancements
branch
2 times, most recently
from
18001d8 to
6d2cc60
Compare
Signed-off-by: Vineeth Kalluru <vikalluru@nvidia.com> # Conflicts: # industries/asset_lifecycle_management_agent/INSTALLATION.md # industries/asset_lifecycle_management_agent/config_examples.yaml # industries/asset_lifecycle_management_agent/configs/README.md # industries/asset_lifecycle_management_agent/example_eval_output/multimodal_eval_output.json # industries/asset_lifecycle_management_agent/example_eval_output/workflow_output.json # industries/asset_lifecycle_management_agent/frontend/README.md # industries/asset_lifecycle_management_agent/frontend/app.js # industries/asset_lifecycle_management_agent/frontend/package-lock.json # industries/asset_lifecycle_management_agent/frontend/package.json # industries/asset_lifecycle_management_agent/frontend/server.js # industries/asset_lifecycle_management_agent/frontend/styles.css # industries/asset_lifecycle_management_agent/prompts.md
Signed-off-by: Vineeth Kalluru <vikalluru@nvidia.com>
Signed-off-by: Vineeth Kalluru <vikalluru@nvidia.com> # Conflicts: # industries/asset_lifecycle_management_agent/README.md # industries/asset_lifecycle_management_agent/configs/config-reasoning.yml
Signed-off-by: Vineeth Kalluru <vikalluru@nvidia.com>
- Fix database path in code_generation_assistant.py to use '/workspace/database/nasa_turbo.db' - Make utils import conditional and only for RUL transformations - Fix sys.path.append to use '/workspace' instead of '.' - Add utils_template folder with pre-built RUL transformation utilities - Update README with clear setup instructions for workspace utilities - Addresses customer issues: ModuleNotFoundError for utils and mysql modules Signed-off-by: Vineeth Kalluru <vikalluru@nvidia.com>
vikalluru
force-pushed
the
vikalluru/sql-retriever-enhancements
branch
from
2dc01b0 to
e0e67d4
Compare
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
1 participant
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.
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:
vanna_manager.pyandvanna_util.pywith better error handling and database connectivityDell AIDp Sandbox Compatibility:
/workspace/database/nasa_turbo.dbfor sandboxed environmentssys.path.append("/workspace"))Developer Experience:
INSTALLATION.md)configs/README.md)utils_template/with pre-built RUL transformation utilitiespyproject.tomlTesting
Addresses customer-reported issues:
ModuleNotFoundErrorfor utils and mysql modulesInput 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