Feature/global lesser of
* Merge remote-tracking branch 'origin/feature/reimb-primary-updates'
* First try at global "lesser of"
* Generate reimb_ids further upstream
* Implement global lesser of injection and extraction logic in file processing
* Update logic to change LESSER_OF_IND in-place for global affected rows; add docstrings
* Refactor global lesser of injection logic to create new rows for REIMB_IDs lacking lesser of logic; update original rows in place and improve tracking flags.
* Merge remote-tracking branch 'origin/main' into feature/global-lesser-of
* Add logging for global lesser of logic injection and update handling of original rows
* Refactor global lesser of logic: move functions to one_to_one_funcs.py and update inject_global_lesser_of_rows to use new implementations
* Move imports for METHODOLOGY_BREAKOUT_QUESTIONS and REIMB_TERM_BREAKOUT to the top of one_to_one_funcs.py for better organization and to remove prototype comments.
* isort
* Refactor import statement for generate_reimb_ids to use the full module path for clarity
* load field from JSON instead of hardcoded values
* Update logging levels in investment_field_testing notebook
* Merged main into feature/global-lesser-of
* Remove unnecessary comment from investment_postprocessing_funcs import statement for clarity
* Merge branch 'feature/global-lesser-of' of https://bitbucket.org/aarete/doczy.ai into feature/global-lesser-of
* Merge remote-tracking branch 'origin/main' into feature/global-lesser-of
* Remove debug print statement from process_file function
* fix call to Field.load_from_file
* Merge remote-tracking branch 'origin/main' into feature/global-lesser-of
* Add tracking flag for global lesser of logic when none is found
* explicitly sort by FILE_NAME, EXHIBIT_PAGE, and REIMB_LESSER_OF_ID columns
* Add new field type, "full_context_separate", to make sure that we don't run it twice. Also formatting fix
* Fix iteration over separate fields in run_full_context_fields function
Approved-by: Katon Minhas
Feature/further reimb primary improvements
* Refactor identify_reimbursement_exhibits to return both EXPLICIT and IMPLICIT values
* Moving from # Debugging lines to `logger`
* Enhance "lesser of" and exception language instructions in reimbursement terms
* clarify unclear print/logging statements
* Replace debugging print statements with logging in get_reimbursement_primary function
* Add logging for page processing in run_one_to_n_prompts function
Approved-by: Katon Minhas
Don't consider table-subpages each individually for reimbursement exhibit identification
* Refine EXHIBIT_CHECK prompt
* test: rework `get_exhibit_pages` for table subpages
* Fix indentation
* Experimental table de-chunking
* Increase max_tokens for Claude model in exhibit page processing
* fix get_pages_to_process docstring
* refactor: improved docstring for get_exhibit_pages
* move `get_pages_to_process` to `preprocess.py`
* test: add unit tests for get_pages_to_process function
* Comment out debugging lines
* Changed prompt that was breading universal_json_load parsing
* fix: handle "no results" case in get_reimbursement_primary function
* fixed docstring
Approved-by: Katon Minhas
Reimbursement Exhibit Prefiltering
* Add IDENTIFY_REIMBURSEMENT_EXHIBITS function to analyze exhibit headers for reimbursement information
* Add Zone.Identifier to .gitignore to prevent Windows zone information files from being tracked
* Add functionality to identify reimbursement exhibits
* Add functionality to identify reimbursement exhibits in run_one_to_n_prompts
* Output YAML parsing
* Refactor identify_reimbursement_exhibits to improve YAML parsing and error handling
* New reimbursement exhibit logic
* Update IDENTIFY_REIMBURSEMENT_EXHIBITS_PROMPT to return PAGE NUMBERS instead of exhibit headers
* Fix identify_reimbursement_exhibits to return page numbers as strings after YAML parsing
* Remove debugging print statement for reimbursement exhibits in run_one_to_n_prompts
* Remove commented debugging print statements in identify_reimbursement_exhibits
* Increase read_timeout in EC2 configuration from 2000 to 4000
* Merge remote-tracking branch 'origin/main' into feature/reimb-primary-improvements
* Remove debugging print statements in get_reimbursement_primary function
* mypy error
* Fix return type in identify_reimbursement_exhibits to ensure keys are returned as a list
* Merge remote-tracking branch 'origin/main' into feature/reimb-primary-improvements
Approved-by: Katon Minhas
Feature/medicare medicaid postprocess
* Initial test
* add to postprocessing funcs
* Remove from postprocessing
* Merged main into feature/medicare-medicaid-postprocess
Approved-by: Alex Galarce
Bugfix/add name to full context if no identifiers
* Add handling for missing TIN/NPI identifiers in one-to-one results
* Update provider name handling in one-to-one results for group providers
Approved-by: Katon Minhas
DRAFT: Bugfix/effective date fix
* Merged in bugfix/extra-fields (pull request #500)
Do not run Exhibit level prompt if there are no exhibit level fields
* Do not run Exhibit level prompt if there are no exhibit level fields
* Update dynamic test
* Remove test from one-to-n test module
* Update test
* Fix unit test
Approved-by: Alex Galarce
* Merged in bugfix/tin-npi-prompt-fixes (pull request #499)
Bugfix/tin npi prompt fixes
* Change delimiter for other provider information from comma to pipe
* filter out invalid providers
* Update extraction and formatting instructions for provider entities in TIN_NPI_TEMPLATE
* Merged main into bugfix/tin-npi-small-bugfixes
* Refactor deduplication logic to use string_utils for checking empty provider fields
* Merge branch 'bugfix/tin-npi-small-bugfixes' of https://bitbucket.org/aarete/doczy.ai into bugfix/tin-npi-small-bugfixes
* Update deduplication logic to exclude providers with 'UNKNOWN' TIN, NPI, or NAME
* Merge remote-tracking branch 'origin/main' into bugfix/tin-npi-small-bugfixes
* Fix deduplication logic to not drop subsequent names
* Fix formatting of provider names in deduplication logic
* add payer name filtering
* reorder execution order to allow to find payer_name first
* Add handling for previously unfound group providers in identify_group_provider function
* Merge remote-trackin…
* Merged in feature/update-testbed-script (pull request #501)
Feature/update testbed script
* Update preprocessing
* Update preprocessing
* remove quit
* Update date for filename
* Merged main into feature/update-testbed-script
Approved-by: Alex Galarce
* Merged in bugfix/smart-chunks (pull request #503)
missing of text in chunks fixed
* missing of text in chunks fixed
Approved-by: Katon Minhas
* Merged in feature/rework-reimb-tin-npi (pull request #502)
Feature/rework reimb tin npi
* use LLM for reimb_[tin/npi/name]
* Merge remote-tracking branch 'origin/main' into feature/rework-reimb-tin-npi
* Merge remote-tracking branch 'origin/main' into feature/rework-reimb-tin-npi
* deduplicate tin/name/npi before adding to prompt
* Pull out prompt and llm_response in methodology_breakout_single_row for easier debugging
* Refactor reimbursement_tin_npi to handle multiple providers and update valid TIN, NPI, and NAME fields accordingly
* Reorder REIMB_PROV_NAME field in investment_prompts.json
* Update REIMB_PROV_NAME prompt to specify valid values for provider names
* Remove valid_values constraint from prov_name to raise accuracy
* Remove debugging print statements from reimbursement_tin_npi and related functions
* Remove debugging print statements from run_provider_info_fields function
* Merge remote-tracking branch 'origin/main' into feature/rework-reimb-tin-npi
* Remove debugging print statem…
* Merged in feature/preformat-single-quotes-input (pull request #506)
Replace double quotes with single quotes in context strings for parsability
* Replace double quotes with single quotes in context strings for parsability
* Merged main into feature/preformat-single-quotes-input
Approved-by: Katon Minhas
* updated sig pages fnxn
* Merge branch 'main' into bugfix/effective_date_fix
* poetry add pymupdf
* created vision funcs
* Merged main into bugfix/effective_date_fix
* fixed pipeline issue
* updated string_utils_test
* updated test values
* updated extract signature page fxn
* updated test values
* updated test values
* Merged main into bugfix/effective_date_fix
* Prompt template in all-caps
* remove debugging prints
* Merged main into bugfix/effective_date_fix
* Change vision to False by default
* Change vision to False by default
* fix tests
* fix tests
Approved-by: Katon Minhas
Feature/rework reimb tin npi
* use LLM for reimb_[tin/npi/name]
* Merge remote-tracking branch 'origin/main' into feature/rework-reimb-tin-npi
* Merge remote-tracking branch 'origin/main' into feature/rework-reimb-tin-npi
* deduplicate tin/name/npi before adding to prompt
* Pull out prompt and llm_response in methodology_breakout_single_row for easier debugging
* Refactor reimbursement_tin_npi to handle multiple providers and update valid TIN, NPI, and NAME fields accordingly
* Reorder REIMB_PROV_NAME field in investment_prompts.json
* Update REIMB_PROV_NAME prompt to specify valid values for provider names
* Remove valid_values constraint from prov_name to raise accuracy
* Remove debugging print statements from reimbursement_tin_npi and related functions
* Remove debugging print statements from run_provider_info_fields function
* Merge remote-tracking branch 'origin/main' into feature/rework-reimb-tin-npi
* Remove debugging print statements from get_reimbursement_primary function
* Merge remote-tracking branch 'origin/main' into feature/rework-reimb-tin-npi
* Refactor reimbursement_tin_npi to always add providers (when we have any) to reimbursement_level_fields
Approved-by: Katon Minhas
Collect TIN/NPI/Name page-by-page and run a second pass for IS_GROUP
* configure first pass: no providers marked IS_GROUP. Allows simplification of prompt
* Add group provider identification logic in second pass
* group identification: don't take 20% of pages. Take first 3 and last 3
* Refine group provider identification logic to use pipes for JSON formatting and improve error handling
* fix mypy error for `identify_group_provider`
* Merge remote-tracking branch 'origin/main' into feature/tin-npi-prompt-formatting
* Add "PROV_INFO_JSON" to investment column order
* Refactor group provider identification to use signature page extraction and fix JSON format
* move signature page extraction to `string_utils.py` and add unit tests for it
* Update identify_group_provider to return provider name along with TIN and NPI in JSON format
* Update identify_group_provider to always use group-provided name when available
* move out GROUP_TIN_NPI_TEMPLATE to `investment_prompts.py`
* Remove deprecated PROV_GROUP_TIN_CHECK and PROV_GROUP_NPI_CHECK prompts
* Move out provider info fields from `one_to_one_funcs` to `tin_npi_funcs`
* isort
* remove debug print statements
* Remove debug print statements from provider info functions
* add note to regex_utils.py about where functions are used
* Add page_key_sort function and corresponding tests for sorting page keys
* Refactor identify_group_provider to sort pages and avoid duplicates in extracted sections
* Remove debug print statements from identify_group_provider function
* Merge remote-tracking branch 'origin/main' into feature/tin-npi-prompt-formatting
* extract_signature_page function: prioritize Textract marker for signatures and fallback to keyword search
* fix mypy error
* Update test cases to reflect changes in signature extraction logic
Approved-by: Katon Minhas
Field/dynamic codes
* remove test
* Merge branch 'main' into field/dynamic-codes
* Merged main into field/dynamic-codes
* Update test
* Fix unit test
* Merged main into field/dynamic-codes
* Merged main into field/dynamic-codes
* Merged main into field/dynamic-codes
* Update fields with crosswalks
* Update mapping to return empty string if no mapping
* Update dynamic_funcs
* Restructure
* Update file_processing
* Update dynamic primary
* Fix dynamic primary
* Update base fields
* Update one-to-n process
* Merged main into field/dynamic-codes
* genericized get_dynamic_answers
* Update tests
* Remove test file
* dynamic_funcs cleanup
* remove prints
* add exhibit_header
* Fix imports
Approved-by: Alex Galarce
Feature/align tin npi
* Add merge_provider_info function to consolidate provider data into one-to-one results
* Merge remote-tracking branch 'origin/main' into feature/align-tin-npi
* Remove debug print statement from run_one_to_one_prompts function
* turn run_regex_fields into an orchestrator function by breaking parts of it into separate functions
* Remove unused import of get_matches function and add docstring to chunk_on_matches for clarity
* Add docstring to run_regex_fields for improved clarity and documentation
* fix provider name keys in merge_provider_info
* Remove unused functions get_matches, tin_npi_prompt, and clean_tin_npi from tin_npi_funcs.py
* Set provider name to "UNKNOWN" if cleaned name is empty in clean_provider_info
* Add unit tests for clean_provider_info function to validate data processing
* Enhance docstring for get_all_matches function
* Add tests for get_all_matches and chunk_on_matches functions
* Merge remote-tracking branch 'origin/main' into feature/align-tin-npi
* Implement merge_provider_info function to consolidate provider data into one-to-one results
* Refactor merge_provider_info to simplify list conversion for group and other provider information
* Remove unnecessary TIN and NPI postprocessing step from postprocess function
* Remove clean_tin_npi_other function and its invocation from postprocess function
* Use json prompts for TIN/NPI/Name and inject them into TIN_NPI_TEMPLATE
* Rename run_regex_fields to run_provider_info_fields
* Enhance TIN_NPI_TEMPLATE to include detailed instructions for extracting provider entities and their identifying information, including IS_GROUP logic for main contracting parties.
* moved TIN/NPI regexes to regex_patterns.py
* Remove unnecessary blank line in investment_values.py
* Remove debug print statements from run_provider_info_fields and get_provider_info functions
* Enhance clean_provider_info to handle various representations of IS_GROUP as boolean
* Enhance get_provider_info to include error handling for JSON parsing and ensure consistent return format
Approved-by: Katon Minhas
Feature/dynamic one to one
* Pass N/A to one-to-one
* E2E test passed
* Merged main into feature/dynamic-one-to-one
* Pass ANY non N/A answer to reimbursement-level
* Update test
* Remove test
* Merge branch 'main' into feature/dynamic-one-to-one
* Wrap clean_dates
* Revert postprocess
* Merged main into feature/dynamic-one-to-one
* Merged main into feature/dynamic-one-to-one
* Remove prints
Approved-by: Alex Galarce
Hotfix/file errors
* Set up test file
* Fix regex pattern in json.loads
* bug fix No valid JSON object found in the input string
* bug fixes
* moved try statement to parse fn
* invalid literal for int() with base 10 error fixed
* remove test
* remove excess print statements
* Raise error
* Remove todo
* Remove print statement
Approved-by: Katon Minhas
Generate unique IDs for reimbursements
* Add reimbursement ID generation and update function signatures for unique identification
* Merge remote-tracking branch 'origin/main' into feature/unique-identifier-for-reimbursements
Approved-by: Katon Minhas
Fix load_embeddings()
* move datetime_str function to string_utils module
* enhance load_embeddings to create directory structure and handle download errors
* Merged main into feature/reimbursement-primary-optimizization
Approved-by: Katon Minhas
Field/reconfigure prov type
* Run One-To-N before One-To-One
* Switch PROV_TYPE to Exhibit-Level
* Modify PROV_TYPE prompt
* Merge branch 'main' into field/reconfigure-prov-type
Approved-by: Alex Galarce
StopLoss, Outliers, and Sequestration
* changed any method to all method in list handling
* code mapping moved outside to run once
* Merge branch 'feature/daip2-97' into bugfix/proc-code-lists
* merge conflict fixed
* merge conflicts fixed
* incorporated latest changes from main
* Merged main into bugfix/proc-code-lists
* Move load all dataset to io_utils
* Fix list is_empty
* Updated poetry.lock
* Bugfix
* Docstring
* Docstrings
* Merge branch 'main' into bugfix/proc-code-lists
* Merge branch 'bugfix/proc-code-lists' into bugfix/dynamic-assignment-issue
* Add outliers, stop-loss, and sequestration to reimbursement-level primary prompt template
* Add stop loss fields
* Add outlier fields
* Add sequestration fields
* Remove test
* Docstrings
* Update test for no default exhibit_level_answer_dict
* Merge branch 'bugfix/dynamic-assignment-issue' into field/stop-loss
* Merge branch 'main' into field/stop-loss
* Merged main into field/stop-loss
Approved-by: Alex Galarce
Bugfix/proc code lists
* Add admit type code
* add proc mod description
* Add bill type pos mapping
* Merged main into feature/proc-desc
* Uncomment test code
* Bugfix
* script optimisation for codes
* modified is empty function in string utils
* Remove test.py
* bug fix to handle list of proc_codes
* Merged main into bugfix/proc-code-lists
* changed any method to all method in list handling
* code mapping moved outside to run once
* Merge branch 'feature/daip2-97' into bugfix/proc-code-lists
* merge conflict fixed
* merge conflicts fixed
* incorporated latest changes from main
* Merged main into bugfix/proc-code-lists
* Move load all dataset to io_utils
* Fix list is_empty
* Updated poetry.lock
* Docstring
* Docstrings
* Merge branch 'main' into bugfix/proc-code-lists
* bug fix
Approved-by: Mayank Aamseek
Approved-by: Alex Galarce
DRAFT: missing group tin fixed
* missing group tin fixed
* use tin prompt in full context when N/A
* Merged main into feature/daip2-101
Approved-by: Katon Minhas
Initialize Reimbursement-Level TINs
* Initialized Reimbursement-Level TIN and NPI
* Update unit tests
* Docstrings and cleanup
* Update test
Approved-by: Alex Galarce
Initialize 1:1 TIN and NPI Fields (Using CNC methodology)
* 1:1 TIN and NPI fields added (using CNC methodology)
* Merge branch 'main' into field/tin-npi-initialization
* Merged main into field/tin-npi-initialization
* Merged main into field/tin-npi-initialization
* Merged main into field/tin-npi-initialization
Approved-by: Alex Galarce
Fields/document dates further iteration
* add concise date fix prompt
* Refactor and prepare for postprocessing formatting
* Merged main into fields/document-dates-further-iteration
* Merged main into fields/document-dates-further-iteration
* Implement memoization for date postprocessing and add derived termination date calculation
* Merge branch 'fields/document-dates-further-iteration' of https://bitbucket.org/aarete/doczy.ai into fields/document-dates-further-iteration
* fix mypy error
* tweaks to derived termination date
* Add docstring to derived_term_date_prompt and create unit tests for prompt generation
* fix memoization in postprocess.py
* Merged main into fields/document-dates-further-iteration
Approved-by: Katon Minhas
feature/dynamic and generalized branch
* included txt files for nltk_data
* move nltk_data to src
* Fix last upload count
* Last upload count bugfix
* Fixed B processing
* Remove client-specific postprocessing
* split consolidate_output
* Run by file
* Fix output
* Reconfigure smart_chunk fields
* Add Full Context
* Fix merge conflicts
* Regex, Smart-Chunked, and Full working - not adding smart-chunked-->full when necessary
* Modernized run_full_context_fields()
* Switched set to list in field_context
* Move fields from smart_chunked to full_context as part of 'field_context' function
* Working version with placeholders
* Update poetry and pyproject
* Update s3 output
* Remove deprecated unit test
* Updated error messages
* Updated smart chunk ac name to one to one
* Update dependencies - end-to-end test for write s3 functional
* Add basic multithreading
* Send individual output to s3/local
Approved-by: Alex Galarce
Feature/integrate standard and complex
* last edits to merge_tables_draft_v2 before moving to table_funcs
* migrate to table_utils.py
* fix typehint that caused mypy error
* fix mypy errors
* black and isort
* fix error with multi-table pages
* update poetry.lock
* add tests, fix bug when table start marker or table end marker is missing
* added more tests
* tests for get_str_dictionaries_from_text()
* fix edge case in get_str_dictionaries_from_text
* fix mypy error
* more tests
* add tests, add handling for invalid dictionaries
* add tests
* add tests for insert_column_headers()
* update requirements
* add new simple/complex logic to preprocess.py
* remove files used solely for testing
* split pages into sub-pages by tables
* add table split on end marker. Also add tests
* add docstrings, change control flow
* remove unused tests, add TODO for new tests
* get in prompt changes and intermediate decisions
* TODO for future enhancement for get_exhibit_pages
Approved-by: Katon Minhas
feature/simplify b field chunking
* Add chunk_by_exhibit function and unit tests
* Refactor preprocess
* Updated to run BU primary on entire Exhibit
* Makes BU secondary compatible with exhibit chunk mapping
* Added unit tests for get_exhibit_chunk
* Trimmed TD funcs
* Downstream changes to run_top_down
* Removed conditional funcs
* Merged main into feature/simplify-b-field-chunking
* removed conditional funcs import
* Merged main into feature/simplify-b-field-chunking
* Fixed run_bottom_up_primary arguments
* Fixed TD primary input
* Fixed grouped keyword mappings
* Remove filename tracking until postprocessing
* Removed postprocessing for client columns
* Removed col-based postprocessing
* Merged main into feature/simplify-b-field-chunking
* Fixed NoneType
* Add docstrings
* Updated unit tests for removal of 'Filename'
* Updated comments
Approved-by: Alex Galarce
Refactor/split investment and client
* refactor: clean up tests
* Renamed tests/qcqa to tests/qa_qc for consistency
* comment out faulty test - see docstring note at top
* split to client/investment
* add __init__.py to investment and client to avoid mypy confusion
* fix imports
* update imports for consistency across investment module
* move back to one config
* try changing import to relative
* add init.py to src
* try relative import
* try one more sys.path.append
* fix path for client main
* fix imports in file_processing
* make prompts common
* move keywords out to `src`
* move smart_chunking_funcs to `src`
* fix mypy error
* start moving to explicit imports
* remove old keywords and fix imports for keywords and prompts
* change all imports to full paths
* fix unit tests
* add readme for new way of running things
* isort after all that import work
* remove unused sys.path.append from some tests
Approved-by: Katon Minhas
Alex Galarce