Spaces:

amra-ai
/

summary

Build error

summary / application.py

Roland Ding

10.9.26.75 updated ui, data, features, and backend

004db8a almost 3 years ago

2.93 kB

import os
import json

'''
shared environment variables
'''

aws_access_key_id = os.getenv('AMRA_AWS_ACCESS_KEY_ID')
aws_secret_access_key = os.getenv('AMRA_AWS_SECRET_ACCESS_KEY')
openai_api_key = os.getenv('AMRA_OPENAI_API_KEY')

default_region = "Spine"

device_options={
    "secondary extraction":False,
    "secondary extraction count":0
}

default_s3_bucket = "amra-studies"

'''
ui equivalent environment variables
'''
ec_options={
    "Equivalent Comparator":False,
    "Equivalent Comparator require SD":False,
    "Equivalent Comparator count":0
}

anatomic_domains=[
    # "Dental/CMF",
    "Extremity",
    "Spine"
]

'''
dynamodb tables structure
'''

logic_keywords = {
        "groups":["group"],
        "preoperatives":["preoperative","preop","pre-op"]
    }

source_format = "<column 1 field>\n<value 1>\n<value 2>...<value n>\n<column 2 field>\n<value 1>\n<value 2>...<value n>\n...<column n field>\n<value 1>\n<value 2>...<value n>\n"

anatomic_list = ["Spinal","Extremities"]

tables_inst=[
    f"extract tables from the system text. the tables are mostly in the following format: {source_format}",
    f"reformat the returned tables into a markdown table syntax.",
    f"if applicable, remove the standard deviation after the mean and round all the numbers to one decimal places.",
    f"include all table titles."
]

article_prompts = {
    "Authors": '''extract all of the authors of the article from the above text.\n
    Return the results on the same line separated by commas as Authors: Author A, Author B...
    ''',
    "Acceptance Year": '''extract the acceptance year of the article from the above text.\n
    Return the results on a single line as Accepted Year: <year>.
    ''',

    "Acceptance Month":'''extract the acceptance month of the article from the above text.\n
    Return the results on a single line as Accepted Month: <month>.
    '''
}

# overview_prompts = clinical_prompts = radiological_prompts = other_prompts = {}

# # populate the prompts from .prompt/overview/ folder
# def update_prompts_from_dir(prompts,path):
#     for file in os.listdir(path):
#         with open(f"{path}/{file}","r") as f:
#             prompts[file.split(".")[0]] = f.read()

# update_prompts_from_dir(overview_prompts,".prompts/overview")
# update_prompts_from_dir(clinical_prompts,".prompts/clinical")
# update_prompts_from_dir(radiological_prompts,".prompts/radiologic")
# update_prompts_from_dir(other_prompts,".prompts/other")


'''
application default data
'''
app_data = {
    "current article":{},
    "articles":{},
    "prompts":{},
    "terms":[],
    "summary":{},
    "user":{
        "summary":{"articles":[]},
        "performance outcome #1":{"assessment_step":"Clinical"},
        "performance outcome #2":{"assessment_step":"Clinical"},
        "safety outcome #1":{},
        "safety outcome #2":{},
    }
}

with open(".data/defaults.json","r") as f:
    defaults = json.load(f)

	import os
	import json

	'''
	shared environment variables
	'''

	aws_access_key_id = os.getenv('AMRA_AWS_ACCESS_KEY_ID')
	aws_secret_access_key = os.getenv('AMRA_AWS_SECRET_ACCESS_KEY')
	openai_api_key = os.getenv('AMRA_OPENAI_API_KEY')

	default_region = "Spine"

	device_options={
	"secondary extraction":False,
	"secondary extraction count":0
	}

	default_s3_bucket = "amra-studies"

	'''
	ui equivalent environment variables
	'''
	ec_options={
	"Equivalent Comparator":False,
	"Equivalent Comparator require SD":False,
	"Equivalent Comparator count":0
	}

	anatomic_domains=[
	# "Dental/CMF",
	"Extremity",
	"Spine"
	]

	'''
	dynamodb tables structure
	'''

	logic_keywords = {
	"groups":["group"],
	"preoperatives":["preoperative","preop","pre-op"]
	}

	source_format = "<column 1 field>\n<value 1>\n<value 2>...<value n>\n<column 2 field>\n<value 1>\n<value 2>...<value n>\n...<column n field>\n<value 1>\n<value 2>...<value n>\n"

	anatomic_list = ["Spinal","Extremities"]

	tables_inst=[
	f"extract tables from the system text. the tables are mostly in the following format: {source_format}",
	f"reformat the returned tables into a markdown table syntax.",
	f"if applicable, remove the standard deviation after the mean and round all the numbers to one decimal places.",
	f"include all table titles."
	]

	article_prompts = {
	"Authors": '''extract all of the authors of the article from the above text.\n
	Return the results on the same line separated by commas as Authors: Author A, Author B...
	''',
	"Acceptance Year": '''extract the acceptance year of the article from the above text.\n
	Return the results on a single line as Accepted Year: <year>.
	''',

	"Acceptance Month":'''extract the acceptance month of the article from the above text.\n
	Return the results on a single line as Accepted Month: <month>.
	'''
	}

	# overview_prompts = clinical_prompts = radiological_prompts = other_prompts = {}

	# # populate the prompts from .prompt/overview/ folder
	# def update_prompts_from_dir(prompts,path):
	# for file in os.listdir(path):
	# with open(f"{path}/{file}","r") as f:
	# prompts[file.split(".")[0]] = f.read()

	# update_prompts_from_dir(overview_prompts,".prompts/overview")
	# update_prompts_from_dir(clinical_prompts,".prompts/clinical")
	# update_prompts_from_dir(radiological_prompts,".prompts/radiologic")
	# update_prompts_from_dir(other_prompts,".prompts/other")


	'''
	application default data
	'''
	app_data = {
	"current article":{},
	"articles":{},
	"prompts":{},
	"terms":[],
	"summary":{},
	"user":{
	"summary":{"articles":[]},
	"performance outcome #1":{"assessment_step":"Clinical"},
	"performance outcome #2":{"assessment_step":"Clinical"},
	"safety outcome #1":{},
	"safety outcome #2":{},
	}
	}

	with open(".data/defaults.json","r") as f:
	defaults = json.load(f)