Add DATA_PATH support for agent data loading #27
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
- Add DATA_PATH parameter to aws-single-agent-deployment.sh - Implement data loading in nanda_agent.py (CSV and JSON support) - Add pandas dependency to setup.py - Create sample test data (tests/sample_hr.csv) - Add documentation for deployment flow and data loading
- Add DATA_PATH parameter to aws-single-agent-deployment.sh (12th parameter) - Implement data loading in nanda_agent.py (CSV and JSON support) - Add pandas dependency to setup.py for CSV support - Update README.md with DATA_PATH documentation - Include data directory with sample HR dataset
…er system - Merge upstream LLM provider changes (anthropic, openai, gemini) - Preserve DATA_PATH functionality as 14th parameter in deployment script - Integrate data tools with Anthropic provider when data is available - Keep pandas dependency in setup.py for CSV support
- Fix DATA_PATH parameter position (14th, not 12th) - Add data-backed agent examples to Quick Start - Expand DATA_PATH section with detailed usage, S3 support, and examples - Update Key Features to highlight data-backed agents and multi-LLM support - Add comprehensive environment variables documentation - Include testing examples for data-backed agents - Update architecture diagram with new structure - Improve overall clarity and completeness
- Enhanced _lookup_agent to support prefix matching (e.g., 'menu-agent' finds 'menu-agent-be4f9e') - Added fallback to known deployed agent URLs when registry lookup fails - Improved _send_to_agent with fallback logic for better reliability - Added update scripts for deploying fixes to EC2 agents
- Added data_facts_url support to registry and adapter (core NEST framework) - Created Finance Feed Agent with Data Facts endpoint and stock price API - Created Consumer Agent with dataset discovery via registry and Data Facts - Implemented freshness validation and checksum verification - Added comprehensive test suite with 6 test scenarios - Created deployment scripts for AWS EC2 - Built React demo UI with 10 interactive components - Added complete demo documentation and presentation guide - All agents tested and deployed successfully to AWS
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
2 participants
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 PR adds support for attaching datasets to NEST agents via the
DATA_PATHenvironment variable. Agents can now load CSV or JSON data files at startup and use them in their responses.