AWP handingling in Methodology prompt

src/config.py

@@ -8,7 +8,7 @@ from llama_index.llms.bedrock import Bedrock
 # General Settings
 TEST = False # True to run test prompt - just for testing model connection
 VERBOSE = True
-CLIENT_NAME = 'Priority Health'
+CLIENT_NAME = ''
 TODAY = datetime.now().strftime("%Y%m%d")
 
 # Valid values
@@ -30,7 +30,7 @@ UNPROCESSED_RESULTS_NAME = 'combined_results_unprocessed.csv'
 PROCESSED_RESULTS_NAME = 'combined_results_post_processed.csv'
 
 # Multithread Settings
-MAX_WORKERS = 20
+MAX_WORKERS = 5
 
 # Prompt Debugging
 RUN_PRIMARY = True # Always True
@@ -45,12 +45,12 @@ RUN_CODES = True
 FUZZY_MATCH_THRESHOLD = 0.8
 
 # AWS Keys
-AWS_ACCESS_KEY_ID="ASIAZTMXAXNXEBLXGWPZ"
-AWS_SECRET_ACCESS_KEY="kysOCZMQMY6LhAaG8yOqePxipD7E/xCgQ65PAyru"
-AWS_SESSION_TOKEN="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"
+AWS_ACCESS_KEY_ID="ASIAZTMXAXNXGPEZJ5OW"
+AWS_SECRET_ACCESS_KEY="PelB1A6KB6HnbBrdUeLgnf0Ii+dMpXCG5JLs4BUS"
+AWS_SESSION_TOKEN="IQoJb3JpZ2luX2VjEKz//////////wEaCXVzLWVhc3QtMiJIMEYCIQCxTs5XXRBybkfcptcaSQUN+2JvUa/dimXyxX31+CQeeAIhAL3NRuwIU+MxkVQBDon2BbGTZawkwF4NVvdcUEElGtxEKoMDCEUQABoMNjYwMTMxMDY4NzgyIgwLOdI9PpnuoefEZTMq4AJqQn9q4Uq3WQEK6Wg2iQNPaPTLbaBKLx8TtWwlS6wcIlhFNA+nPyaxew3boex97eYM4uzHiwU2MQ4OTbW+aOphdsWACU4jlaTM6Z0VWlJ+W+OKpMwajDIj7SQnfrDQSGwJ9Ewth3+uxBKqPtXXZmUe5WRCz7G4cIjYxEqdjtj0ZO6ll6zZozPEGVik1+DZoPMbh4Y4qczMDdpW3xXUlalYJBu6CaNqGIb6O1ocl4nhLSmamsKoiXLqGU853Loq0A3b+u+J7w48iPLhXWnuN0GXuN7gBc2C1lzPs/aABM2bU3LBlDqGxKGUDVPRHttg8HRNGwIkEr9LieGjheKvcvLQroi6DhTRkKnV6WEQ1wGzN9wCteXSL7DIktSsddnwX3ffvg7G5WhPN0xYc4F78Sw9gan50wmmebiHrc5lP+yQDJ7J6gvo4a3NsxCE5opV/hgJUjPUgJ7tCPZ+bf+kqKJqMNLem7MGOqUBjmMAY7Vvqp4pBdORFWTZkOHcmZ1UsmJmNYrS69btqyYQbwg79sCIaVR/wiJDn9T5v9vziyv0n98XD7dV6UEuyW97EKv/OWwnqZ7zJwHAa4vwJ09zCruIgT4hCctpzDAAfTYtkacb0PRrxa3pjQZy7pXQC0BvliocPY5fvR5f5QOa/mZGwhjUcih9LfvNWj0BsRW65pPcJoy6Wy3G0EgwsH+VW1h5"
 
 # File Paths
-LOCAL_PATH = 'data/test/' # Replace with local
+LOCAL_PATH = 'data/all_txt_updated/' # Replace with local
 
 # S3 Settings
 S3_CLIENT = boto3.client('s3',

src/prompts.py

@@ -107,7 +107,7 @@ Methodology: {d['FULL_METHODOLOGY']}
 Your job is to identify if the reimbursement is based on a Fee Schedule.
 
 Read and analyze the Methodology, then populate a JSON dictionary with the following fields (descriptions provided):
-REIMBURSEMENT_FEE_SCHEDULE : If the Methodology is based on a Fee Schedule, what is the name of the fee schedule on which it is based? It could be something like Medicaid, Medicare, CMS, DRG, or similar. Do not answer with a complete sentence. If the Methodology is not based on a Fee Schedule, just return 'N/A'
+REIMBURSEMENT_FEE_SCHEDULE : If the Methodology is based on a Fee Schedule, what is the name of the fee schedule on which it is based? It could be something like Medicaid, Medicare, CMS, DRG, AWP, ASP, or similar. Do not answer with a complete sentence. If the Methodology is not based on a Fee Schedule, just return 'N/A'
 REIMBURSEMENT_FEE_SCHEDULE_VERSION : If the Methodology is based on a Fee Schedule, what specific version of the Fee Schedule is it based on. It could be something like 'Current', 'Prevailing', 'at the date of service', a specific year, or similar. If there is no answer, return 'N/A'
 
 Only return the dictionary, with no other commentary or explanation. Ensure you abide by proper JSON formatting.
@@ -120,7 +120,7 @@ def BOTTOM_UP_METHODOLOGY(d):
 Your job is to identify what the concise methodology is based on the full methodology.
 
 Choose the closest option from the following:
-Allowed Amount, Allowable Charges, Fee Schedule, Medicare Fee Schedule, Medicare Allowed Amount, Medicaid Fee Schedule, Medicaid Allowed Amount, Provider's Charges, Billed Charges, IME/DME Amount, MSRP, Per Unit, Per Diem, Per Visit, Per Member, Per Member Per Month, Per Hour, Case Rate
+Allowed Amount, Allowable Charges, Fee Schedule, Medicare Fee Schedule, Medicare Allowed Amount, Medicaid Fee Schedule, Medicaid Allowed Amount, Provider's Charges, Billed Charges, IME/DME Amount, Cost to Charge Ratio, MSRP, Per Unit, Per Diem, Per Visit, Per Member, Per Member Per Month, Per Hour, Case Rate
 
 For 'Allowed Amount' and 'Fee Schedule', use the more specific answer (Medicare/Medicaid) if applicable.
 For the 'Per ___' values, note that this list is not necessarily exhaustive. It could be anything like 'Per ___'.