Katon Minhas
afb6d5185d
Feature/lesser table caching refactor hybrid * chore: Remove unused duplicate main.py from shared pipeline * fix: Correct crosswalk paths in aarete_derived.py * chore: Remove unused documentation files from fieldExtraction * docs: Add documentation files to documentation folder * docs: Update README with uv setup, expanded project structure, and branching conventions * docs: Add uv installation steps with Ubuntu/WSL emphasis * Enable prompt caching for all remaining LLM calls - Add _INSTRUCTION() functions for: EXHIBIT_HEADER, EXHIBIT_LINKAGE, EXHIBIT_TITLE_MATCH, DATE_FIX, DERIVED_TERM_DATE, CHECK_PROVIDER_NAME_MATCH, SPECIAL_CASE_ASSIGNMENT - Update all invoke_claude() calls in saas and clover pipelines to use cache=True with corresponding _INSTRUCTION() functions - Add new instructions to get_cacheable_instructions() for cache warming - Update tests for new instruction functions Functions now using caching: - prompt_exhibit_level - prompt_exhibit_lesser (EXHIBIT_LEVEL_LESSER_OF) - prompt_fee_schedule_breakout - prompt_grouper_breakout - prompt_special_case_assignment - prompt_exhibit_linkage - prompt_exhibit_header - prompt_smart_chunked (ONE_TO_ONE templates) - prompt_date_fix - prompt_derived_term_date - prompt_exhibit_title_match - provider_name_match_check 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com> * Reorder * feat: Add bcbs_promise client pipeline with OFFSET_TERM extraction - Add new bcbs_promise client with HSC-based OFFSET_TERM field extraction - Extract full paragraph text of offset/recoupment provisions from contracts - Derive OFFSET_INDICATOR (Y/N) from OFFSET_TERM presence - Fix reorder_columns to preserve extra columns not in COLUMN_ORDER - Update QC/QA output path to outputs/qc_qa/ * fix: Update dev deps and test assertions for QC/QA output path - Add pytest/pytest-mock to dev dependencies for mypy type checking - Update test assertions to expect outputs/qc_qa instead of qa_qc_output * style: Apply black formatting to prompt_templates.py * Merge main, move scripts * Archive some scripts * update py version * remove .py version file * Remove ASCII characters * Restore testbed code * restore tracking * Update testbed metrics * Enable prompt caching for CODE_LAST_CHECK, FILL_BILL_TYPE, DUAL_LOB_CHECK, and GROUPER_BREAKOUT - Add CODE_LAST_CHECK_INSTRUCTION() for service specificity classification - Add FILL_BILL_TYPE_INSTRUCTION() for bill type code determination - Add DUAL_LOB_CHECK_INSTRUCTION() for Medicare/Medicaid classification - Update code_funcs.py to use caching for CODE_LAST_CHECK, FILL_BILL_TYPE, GROUPER_BREAKOUT - Update postprocessing_funcs.py to use caching for DUAL_LOB_CHECK - Add new instructions to get_cacheable_instructions() for cache warming - Add unit tests for new instruction functions 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com> * Fix postprocessing_funcs to remove invalid columns * Merge branch 'main' into feature/lesser-table-caching-refactor-hybrid * Revert prompt caching changes from aed1b73c * update formatting * Update imports Approved-by: Sha Brown Approved-by: Praneel Panchigar
66 lines
1.8 KiB
SQL
66 lines
1.8 KiB
SQL
-- Create staging table for results
|
|
CREATE TABLE IF NOT EXISTS STG.TRAINING_RESULTS
|
|
(
|
|
CONTRACT_NAME VARCHAR,
|
|
CONTRACT_ID NUMERIC,
|
|
ACTUAL_VALUE_STORED VARCHAR,
|
|
NEW_EXTRACTED_VALUE VARCHAR,
|
|
CONFIDENCE_LEVEL NUMERIC,
|
|
SNIPPET VARCHAR,
|
|
ORIGINAL_PAGE_NUMBER VARCHAR,
|
|
NEW_PAGE_NUMBER VARCHAR,
|
|
REVISED_PROMPT VARCHAR,
|
|
RESULT BOOLEAN,
|
|
LOAD_DT TIMESTAMP
|
|
);
|
|
|
|
|
|
-- Create file format
|
|
CREATE FILE FORMAT IF NOT EXISTS STG.CSV_HEADER
|
|
TYPE = 'CSV'
|
|
FIELD_DELIMITER = ','
|
|
FILE_EXTENSION = '.csv'
|
|
RECORD_DELIMITER = '\\n'
|
|
DATE_FORMAT = AUTO
|
|
TRIM_SPACE = TRUE
|
|
NULL_IF = ('NULL', '', 'N/A','?','~','\\N')
|
|
SKIP_HEADER = 1
|
|
EMPTY_FIELD_AS_NULL = TRUE
|
|
FIELD_OPTIONALLY_ENCLOSED_BY = '"'
|
|
SKIP_BLANK_LINES = TRUE;
|
|
|
|
|
|
-- Create staging table for attempt logs
|
|
CREATE TABLE IF NOT EXISTS STG.TRAINING_ATTEMPT_LOGS
|
|
(
|
|
FIELD_NAME VARCHAR,
|
|
CONTRACTS_TESTED NUMERIC,
|
|
USERNAME VARCHAR,
|
|
DATE_TIME TIMESTAMP,
|
|
ACCURACY NUMERIC,
|
|
ATTEMPT_NUM NUMERIC,
|
|
LOAD_DT TIMESTAMP
|
|
);
|
|
|
|
|
|
|
|
-- Create table for column config that will be used by SP to create raw training data table
|
|
CREATE TABLE IF NOT EXISTS STG.TRAINING_DATA_COLUMN_CONFIG(
|
|
COLUMN_NAME VARCHAR,
|
|
COLUMN_DATATYPE VARCHAR
|
|
);
|
|
|
|
-- Creating a separate file format for the training data
|
|
CREATE FILE FORMAT IF NOT EXISTS STG.TRAINING_DATA_FILE_FORMAT
|
|
TYPE = 'CSV'
|
|
FIELD_DELIMITER = ','
|
|
FILE_EXTENSION = '.csv'
|
|
RECORD_DELIMITER = '\\n'
|
|
DATE_FORMAT = AUTO
|
|
TRIM_SPACE = TRUE
|
|
NULL_IF = ('NULL', '', 'N/A','?','~','\\N')
|
|
SKIP_HEADER = 1
|
|
EMPTY_FIELD_AS_NULL = TRUE
|
|
FIELD_OPTIONALLY_ENCLOSED_BY = '"'
|
|
error_on_column_count_mismatch=false
|
|
SKIP_BLANK_LINES = TRUE; |