File size: 1,899 Bytes
009d93e |
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 |
from typing import Literal
from models import *
from .process import *
# predefined processing logic for routine extraction tasks
TaskType = Literal["NER", "RE", "EE", "Base"]
class DataPoint:
def __init__(self,
task: TaskType = "Base",
instruction: str = "",
text: str = "",
output_schema: str = "",
constraint: str = "",
use_file: bool = False,
file_path: str = "",
truth: str = ""):
"""
Initialize a DataPoint instance.
"""
# task information
self.task = task
self.instruction = instruction
self.text = text
self.output_schema = output_schema
self.constraint = constraint
self.use_file = use_file
self.file_path = file_path
self.truth = extract_json_dict(truth)
# temp storage
self.print_schema = ""
self.distilled_text = ""
self.chunk_text_list = []
# result feedback
self.result_list = []
self.result_trajectory = {}
self.pred = ""
def set_constraint(self, constraint):
self.constraint = constraint
def set_schema(self, output_schema):
self.output_schema = output_schema
def set_pred(self, pred):
self.pred = pred
def set_result_list(self, result_list):
self.result_list = result_list
def set_distilled_text(self, distilled_text):
self.distilled_text = distilled_text
def update_trajectory(self, function, result):
if function not in self.result_trajectory:
self.result_trajectory.update({function: result})
def get_result_trajectory(self):
return {"instruction": self.instruction, "text": self.text, "constraint": self.constraint, "trajectory": self.result_trajectory, "pred": self.pred}
|