jacob-mathison/doczyai-pipelines
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Activity

Merged in bugfix/dynamic_issues (pull request #832)

Browse Source 
Bugfix/dynamic issues

* Add debug print statements for dynamic primary field discovery and 1:1 escalation tracking

* Add reimb_term to bill type CD determination context

- Updated fill_bill_type() to accept reimb_term parameter
- Modified FILL_BILL_TYPE prompt to include reimbursement term in context
- First attempt now uses: service term + reimbursement term
- Second attempt uses: service term + reimbursement term + exhibit text
- Updated extract_codes_from_service() to pass REIMB_TERM to fill_bill_type()

* Remove debug print statements from dynamic_funcs.py and file_processing.py

- Removed all DEBUG print statements for dynamic primary discovery
- Removed debug prints for field discovery status and 1:1 escalation evaluation
- Removed debug prints for exhibit level answers and final summaries
- Removed debug comment about one_to_one_fields creation
- Cleaned up all temporary debugging code

* Merge branch 'main' into bugfix/dynamic_issues

* Remove duplicate one_to_one_fields FieldSet initialization from process_file


Approved-by: Katon Minhas
This commit is contained in:
Praneel Panchigar
2026-01-08 22:41:52 +00:00
committed by Katon Minhas
parent d97a31aa5b
commit 69f23653a1
4 changed files with 20 additions and 11 deletions
Download Patch File Download Diff File Expand all files Collapse all files
fieldExtraction/src/codes/code_funcs.py
+8 -5
View File
@@ -408,7 +408,7 @@ def code_last_check(service, filename):
return claude_answer_final
def fill_bill_type(service, answer_dict, BILL_TYPE_MAPPING, BILL_TYPE_REVERSE_MAPPING, exhibit_text=None):
def fill_bill_type(service, answer_dict, BILL_TYPE_MAPPING, BILL_TYPE_REVERSE_MAPPING, reimb_term=None, exhibit_text=None):
"""
Fills the BILL_TYPE_CD and BILL_TYPE_CD_DESC fields in the answer dictionary.
@@ -417,6 +417,7 @@ def fill_bill_type(service, answer_dict, BILL_TYPE_MAPPING, BILL_TYPE_REVERSE_MA
answer_dict (dict): The answer dictionary to update.
BILL_TYPE_MAPPING (dict): Mapping from codes to descriptions.
BILL_TYPE_REVERSE_MAPPING (dict): Mapping from descriptions to codes.
reimb_term (str, optional): The reimbursement term for additional context.
exhibit_text (str, optional): Full exhibit text for contextual analysis.
Returns:
@@ -425,18 +426,18 @@ def fill_bill_type(service, answer_dict, BILL_TYPE_MAPPING, BILL_TYPE_REVERSE_MA
valid_bill_type = sorted(list(set(BILL_TYPE_MAPPING.values())))
# First attempt: Service term only
# First attempt: Service term + reimbursement term
claude_answer_raw = llm_utils.invoke_claude(
prompt_templates.FILL_BILL_TYPE(service, valid_bill_type, exhibit_text=None),
prompt_templates.FILL_BILL_TYPE(service, valid_bill_type, reimb_term=reimb_term, exhibit_text=None),
"sonnet_latest",
""
)
claude_answer_final = string_utils.universal_json_load(claude_answer_raw)
# Second attempt: Service term + exhibit context (if first attempt failed and context available)
# Second attempt: Service term + reimbursement term + exhibit context (if first attempt failed and context available)
if not claude_answer_final and exhibit_text:
claude_answer_raw = llm_utils.invoke_claude(
prompt_templates.FILL_BILL_TYPE(service, valid_bill_type, exhibit_text=exhibit_text),
prompt_templates.FILL_BILL_TYPE(service, valid_bill_type, reimb_term=reimb_term, exhibit_text=exhibit_text),
"sonnet_latest",
""
)
@@ -599,11 +600,13 @@ def extract_codes_from_service(answer_dict, constants: Constants):
# Fill Bill Type if not filled
if string_utils.is_empty(bill_type):
exhibit_text = answer_dict.get("EXHIBIT_TEXT", None)
reimb_term = answer_dict.get("REIMB_TERM", None)
answer_dict = fill_bill_type(
service,
answer_dict,
constants.BILL_TYPE_MAPPING,
constants.BILL_TYPE_REVERSE_MAPPING,
reimb_term=reimb_term,
exhibit_text=exhibit_text,
)
fieldExtraction/src/investment/dynamic_funcs.py
-1
View File
@@ -242,7 +242,6 @@ def get_dynamic_one_to_one_fields(answer_dicts: list[dict[str, str]], constants:
one_to_one_fields, field_to_add, answer_dicts, constants
)
return one_to_one_fields
fieldExtraction/src/investment/file_processing.py
-2
View File
@@ -60,7 +60,6 @@ def process_file(file_object, constants: Constants, run_timestamp):
# ONE TO ONE PROCESSING
if process_one_to_one:
one_to_one_results = run_one_to_one_prompts(
filename,
contract_text,
@@ -265,7 +264,6 @@ def run_one_to_n_prompts(text_dict: dict[str, str],
dynamic_one_to_one_fields = dynamic_funcs.get_dynamic_one_to_one_fields(
one_to_n_results, constants
)
################## CONVERT TO DF ##################
one_to_n_df = pd.DataFrame(one_to_n_results)
fieldExtraction/src/prompts/prompt_templates.py
+12 -3
View File
@@ -821,13 +821,22 @@ Briefly explain your answer, then put your final answer in |pipes|.
"""
def FILL_BILL_TYPE(service, choices, exhibit_text=None):
def FILL_BILL_TYPE(service, choices, reimb_term=None, exhibit_text=None):
# Build reimbursement term section conditionally
reimb_term_section = ""
if reimb_term and not string_utils.is_empty(reimb_term):
reimb_term_section = f"""
[REIMBURSEMENT TERM]
Here is the Reimbursement Term associated with the Service Term:
{reimb_term.replace('"', "'")}
"""
# Build exhibit context section conditionally
exhibit_context_section = ""
if exhibit_text:
exhibit_context_section = f"""
[EXHIBIT CONTEXT]
If the Service Term alone does not provide sufficient information, examine the following exhibit text for additional context about where the service is performed:
If the Service Term and Reimbursement Term together do not provide sufficient information, examine the following exhibit text for additional context about where the service is performed:
{exhibit_text.replace('"', "'")}
"""
@@ -852,7 +861,7 @@ Here are the descriptions to choose from:
[CONTEXT]
Here is the Service Term to analyze:
{service.replace('"', "'")}
{exhibit_context_section}
{reimb_term_section}{exhibit_context_section}
[OUTPUT FORMAT]
Briefly explain your answer, then return your final answer in JSON list format.
"""