How jth6-rice/award-set-up-helper works
This repository supports award-document extraction and review through a Streamlit dashboard: users stage PDFs, the batch pipeline groups related documents, AI extracts structured award data, and results are written to Google Sheets for review. It also contains a separate Apps Script pre-submission reconciliation workflow and a standalone extraction prototype. The excerpts establish the main Python pipeline and the Apps Script flow; the README is empty, and the tracker’s relationship to the active pipeline is not shown.
Main entry points: batch_processor.py Batch orchestration · ai_engine.py AI extraction · app.py Review dashboard · Award_Set_Up_Amendment_Helper.js Pre-submit sweep
Components 15
Review dashboard
- Review dashboard
app.py - Award records
sheets_interface.py
Award ingestion
- Batch orchestration
batch_processor.py - PDF grouping
batch_processor.py - ID reconciliation
batch_processor.py - AI extraction
ai_engine.py
Extraction rules
- Registry parsing
core_parser.py - Extraction protocol
1.71.md
Other workflows
- Pre-submit sweep
Award_Set_Up_Amendment_Helper.js - Extraction prototype
google-generativeai.py - Pipeline tracker
tracker.py
Other components
- Reviewer
- PDF submitter
- Gemini API
- Google Drive
Connections 15
- Reviewer → Review dashboard: reviews records
app.py - PDF submitter → Review dashboard: stages PDFs
app.py - Review dashboard → Batch orchestration: starts processing
app.py - Review dashboard → Award records: loads records
app.py - Batch orchestration → PDF grouping: groups PDFs
batch_processor.py - Batch orchestration → AI extraction: requests extraction
batch_processor.py - AI extraction → Registry parsing: loads registries
ai_engine.py - AI extraction → Extraction protocol: loads rules
ai_engine.py - AI extraction → Gemini API: uploads and queries
ai_engine.py - Batch orchestration → ID reconciliation: resolves identifiers
batch_processor.py - Batch orchestration → Award records: writes extracted data
batch_processor.py - Pre-submit sweep → Google Drive: reads PDFs and references
Award_Set_Up_Amendment_Helper.js - Pre-submit sweep → Gemini API: requests reconciliation
Award_Set_Up_Amendment_Helper.js - Pre-submit sweep → Award records: appends results
Award_Set_Up_Amendment_Helper.js - Extraction prototype → Gemini API: extracts award data
google-generativeai.py