43 lines
1.3 KiB
Python
43 lines
1.3 KiB
Python
|
import requests
|
||
|
|
import json
|
||
|
|
from tqdm import tqdm
|
||
|
|
|
||
|
|
with open('questions.json') as f:
|
||
|
|
questions = json.load(f)
|
||
|
|
|
||
|
|
headers = {
|
||
|
|
'Authorization': 'Basic Og==',
|
||
|
|
'Content-Type': 'application/json'
|
||
|
|
}
|
||
|
|
|
||
|
|
|
||
|
|
url = "http://127.0.0.1:5001/get_relevant_documents"
|
||
|
|
|
||
|
|
url_es_get_doc_by_id = "http://127.0.0.1:5001/get_document_by_id"
|
||
|
|
|
||
|
|
top_five_results=[]
|
||
|
|
for question_item in tqdm(questions):
|
||
|
|
question= question_item["question"]
|
||
|
|
payload = json.dumps({
|
||
|
|
"query": question,
|
||
|
|
"index": "ib"
|
||
|
|
})
|
||
|
|
response = requests.request("POST", url, headers=headers, data=payload)
|
||
|
|
results= response.json()
|
||
|
|
ids = [result["meta"]["es_id"] for result in results[:5]]
|
||
|
|
top_five_results=[]
|
||
|
|
|
||
|
|
for id in ids:
|
||
|
|
payload = json.dumps({
|
||
|
|
"id": id
|
||
|
|
})
|
||
|
|
response = requests.request("POST", url_es_get_doc_by_id, headers=headers, data=payload)
|
||
|
|
|
||
|
|
es_docs=response.json()
|
||
|
|
for es_doc in es_docs:
|
||
|
|
score= [result["score"] for result in results if result["meta"]["es_id"] == es_doc["id"]]
|
||
|
|
top_five_results.append({"title": es_doc["meta"]["name_de"], "score":score, "description":es_doc["content"] })
|
||
|
|
question_item["top_results"]= top_five_results
|
||
|
|
|
||
|
|
with open('answered_questions.json', 'w', encoding="utf-8") as outfile:
|
||
|
|
json.dump(questions, outfile, ensure_ascii=False)
|