Spaces:
Running
on
T4
Running
on
T4
File size: 3,828 Bytes
2e2dda5 c2c6e99 2e2dda5 c2c6e99 2e2dda5 c2c6e99 2e2dda5 c2c6e99 2e2dda5 c2c6e99 2e2dda5 |
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 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 |
import boto3
from botocore.exceptions import ClientError
import pprint
import time
import streamlit as st
from sentence_transformers import CrossEncoder
model = CrossEncoder("cross-encoder/ms-marco-MiniLM-L-6-v2", max_length=512)
####### Add this Kendra Rescore ranking
#kendra_ranking = boto3.client("kendra-ranking",region_name = 'us-east-1')
#print("Create a rescore execution plan.")
# Provide a name for the rescore execution plan
#name = "MyRescoreExecutionPlan"
# Set your required additional capacity units
# Don't set capacity units if you don't require more than 1 unit given by default
#capacity_units = 2
# try:
# rescore_execution_plan_response = kendra_ranking.create_rescore_execution_plan(
# Name = name,
# CapacityUnits = {"RescoreCapacityUnits":capacity_units}
# )
# pprint.pprint(rescore_execution_plan_response)
# rescore_execution_plan_id = rescore_execution_plan_response["Id"]
# print("Wait for Amazon Kendra to create the rescore execution plan.")
# while True:
# # Get the details of the rescore execution plan, such as the status
# rescore_execution_plan_description = kendra_ranking.describe_rescore_execution_plan(
# Id = rescore_execution_plan_id
# )
# # When status is not CREATING quit.
# status = rescore_execution_plan_description["Status"]
# print(" Creating rescore execution plan. Status: "+status)
# time.sleep(60)
# if status != "CREATING":
# break
# except ClientError as e:
# print("%s" % e)
# print("Program ends.")
#########################
def re_rank(self_, rerank_type, search_type, question, answers):
print("start")
print()
ans = []
ids = []
ques_ans = []
query = question[0]['question']
for i in answers[0]['answer']:
if(self_ == "search"):
ans.append({
"Id": i['id'],
"Body": i["desc"],
"OriginalScore": i['score'],
"Title":i["desc"]
})
ids.append(i['id'])
ques_ans.append((query,i["desc"]))
else:
ans.append({'text':i})
ques_ans.append((query,i))
re_ranked = [{}]
####### Add this Kendra Rescore ranking
# if(rerank_type == 'Kendra Rescore'):
# rescore_response = kendra_ranking.rescore(
# RescoreExecutionPlanId = 'b2a4d4f3-98ff-4e17-8b69-4c61ed7d91eb',
# SearchQuery = query,
# Documents = ans
# )
# re_ranked[0]['answer']=[]
# for result in rescore_response["ResultItems"]:
# pos_ = ids.index(result['DocumentId'])
# re_ranked[0]['answer'].append(answers[0]['answer'][pos_])
# re_ranked[0]['search_type']=search_type,
# re_ranked[0]['id'] = len(question)
# return re_ranked
if(rerank_type == 'Cross Encoder'):
scores = model.predict(
ques_ans
)
index__ = 0
for i in ans:
i['new_score'] = scores[index__]
index__ = index__+1
ans_sorted = sorted(ans, key=lambda d: d['new_score'],reverse=True)
def retreive_only_text(item):
return item['text']
if(self_ == 'rag'):
return list(map(retreive_only_text, ans_sorted))
re_ranked[0]['answer']=[]
for j in ans_sorted:
pos_ = ids.index(j['Id'])
re_ranked[0]['answer'].append(answers[0]['answer'][pos_])
re_ranked[0]['search_type']= search_type,
re_ranked[0]['id'] = len(question)
return re_ranked
|