New Prompt Method (starting with contract effective date)
* add todos for Siddhant
* moved effective date prompts to prompts.py and added docstring and type hints
* moved effective date prompts to prompts.py and added docstring and type hints
* fixed conflict
Co-authored-by: Alex Galarce <agalarce@aarete.com>
* modified contract effective date logic in existing smart chunking
* Merged main into chore/contract_effective_date
* updated extract_text_from_delimiters function and unit tests for it
* Merge remote-tracking branch 'origin/main' into chore/contract_effective_date
* added comments to preprocessing_funcs
* preprocessing_funcs.py edited online with Bitbucket
* utils.py edited online with Bitbucket
* add debug line
* add NA handling into fix_date_formatting()
* add debug print statements
* worked on review comments
* fixed date checking
* fixed date checking and added unit tests
* Merged main into chore/contract_effective_date
* added logic to handle case when smart chunking returns empty context for effective date
* added comments to file_processing.py
* optimized imports and removed a TODO
* Merged main into chore/contract_effective_date
* made prompt changes for effective date
* keywords.py edited online with Bitbucket
* Removed excess print statements
Approved-by: Katon Minhas
refactored code to add recent health plan state hotfixes into the existing postprocessing pipeline
* refactored code to add recent health plan state hotfixes into the existing postprocessing pipeline
* Merged main into chore/health_plan_state
* Merged main into chore/health_plan_state
* add debug print statement
* debug print statements
* more debug print statements
* print df columns for debug
* move health plan state hotfix functionality to postprocessing_funcs.py
* add better error printing
* add error message for parent agreement code
* remove dots in state abbreviations
* remove unused import
* also look for state abbreviations
* Merged main into chore/health_plan_state
* remove print statements
* Merged main into chore/health_plan_state
Approved-by: Katon Minhas
agreement_name hotfix to main
* agreement_name hotfix to main
* group name changed to AGREEMENT_NAME
* Merged main into feature/agreement_name_chunking
Approved-by: Alex Galarce
Initial top sheet conditional commit
* Initial top sheet conditional commit
* Merged main into feature/topSheetConditional
* preprocessing_funcs.py edited online with Bitbucket
* Updated quick review docstring
Approved-by: Alex Galarce
term group fixed
* term group fixed
* Merged main into bugfix/group_chunk_json_parsing
* file_processing.py edited online with Bitbucket
* Merged main into bugfix/group_chunk_json_parsing
Approved-by: Alex Galarce
Bugfix/clean full context in smart chunking
* move full context bugfix to clean branch
* took out commented code
* black formating
* Add explanatory comments to file_processing.py
Approved-by: Alex Galarce
grouped keywords and IRS regex chunking
* abandon old branch and rebuild
* removed print for field names, prompts
* pushing as part of leftovers
* IRS regex chunking
* Merged in feature/chunk_term_clean (pull request #262)
chunk_log_added
* chunk_log_added
* Merge remote-tracking branch 'remotes/origin/feature_ac_chunking_clean' into feature/chunk_term_clean
Approved-by: Alex Galarce
* added function for regex based IRS chunking
* shifted regex_match_chunk function to utils
* added helper functions for regex based chunking
* replaced tin_regex function to ac_funcs
* removed prompt for irs_others
* added regex chunking for irs
* removed irs group from smart chunking
* testing functionality for regex based irs fields
* updated return N/A condition
* Merged main into feature_ac_chunking_clean
* file_processing.py edited online with Bitbucket
* added back conditional prompts
* minor fixed for PR
* remove install types
* mering clean branch
* with passed test casses
* added flag for regex based tin execution
Approved-by: Michael McGuinness
Cnc fl main
* prov type moved
* comment out invalid prov2 bc it's overly restrictive
* Update prompt template to ensure N/A rather than blanks
* Update AC multi-prompt template. Update prompts to ensure all keys are present and N/As are filled
* Update AC postprocessing
* Update clean_tin() to add N/A for values other than 10 digits
* update tin postprocessing
* Update npi postprocessing
* Add 'Filename:' to the start of all filenames
* Update group TIN/NPI postprocessing
* Update parent agreement code
* fix health plan state mapping
* Update B postprocessing
* Updated indicators, re-ordering
* Update postprocessing - all columns included and reordered
* Ensure Pages is included in AC-only output
* Remove excess print statements
* remove example_test to pass pipeline
* Fix parent agreement code for AC
* Updated postprocessing for NPI/TIN other
* Update prompts for N explicitely on AC prompt-based indicators
* Updated main and utils for more intuitive filtering
* Updated file_counting to match new main process
* update test
* Add example_test
Approved-by: Michael McGuinness
Alex Galarce