File size: 2,452 Bytes
b417154 782700e 5f575ac 6530227 b417154 5f575ac b417154 782700e 5f575ac b417154 5f575ac e4aa4ec b417154 | 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 | from typing import List, Dict, Any
from transformers import AutoTokenizer, AutoModelForSeq2SeqLM
class EndpointHandler():
def __init__(self, path=""):
self.model = model = AutoModelForSeq2SeqLM.from_pretrained(path)
self.tokenizer = AutoTokenizer.from_pretrained(path)
self.bos_instruction = "Definition: The output will be the aspects (both implicit and explicit) the corresponding opinion/describing terms and the sentiment polarity (positive, negative, neutral) of the opinion term . In cases where there are no aspects the output should be noaspectterm:none:none.\n Positive example 1-\n input: Faan 's got a great concept but a little rough on the delivery .\n output: delivery:rough:positive\n Positive example 2- \n input: I just wonder how you can have such a delicious meal for such little money .\n output: meal:delicious:positive, money:little:positive\n Now complete the following example-\n input: "
self.eos_instruct = ' \noutput:'
self.delim_instruct = ''
def preprocess(self, inputs: List[str]):
processed_inputs = []
for text in inputs:
processed_inputs.append(self.bos_instruction + text + self.delim_instruct + self.eos_instruct)
return self.tokenizer(processed_inputs, return_tensors="pt", truncation=True, padding=True)
def postprocess(self, outputs):
output = self.tokenizer.decode(outputs[0], skip_special_tokens=True)
aspects = []
opinions = []
sentiments = []
for triplet in output.split(','):
triplet = triplet.strip()
if triplet == '':
continue
aos = triplet.split(':') # aos = aspect - opinion - sentiment
aspects.append(aos[0])
opinions.append(aos[1])
sentiments.append(aos[2])
result = ""
for i in range(len(aspects)): # or opinions/aspects because they have the same length
result += f"Aspect: {aspects[i]} - Opinion: {opinions[i]} - Sentiment: {sentiments[i]}\n"
result = result.strip()
return result
def __call__(self, data: Dict[str, Any]):
inputs = data.pop('inputs', data)
parameters = data.pop("parameters", None)
model_inputs = self.preprocess(inputs)
model_outputs = self.model.generate(model_inputs.input_ids)
return self.postprocess(model_outputs) |