sts-llm-backend / test.py
ayushsinghal1510's picture
Init COmmit
cc65c1f
import requests
import json
from tqdm import tqdm
from requests import Response
def scrape_url_and_save_in_json_file(url : str , json_file_path : str) -> None :
response : Response = requests.post(
'http://localhost:8002/scrape-url' ,
json = {'url' : url}
)
with open(json_file_path , 'w') as json_file : json.dump(response.json() , json_file)
def scrape_pdfs(json_file_path : str , api_key : str) -> None :
with open(json_file_path) as json_file : links = json.load(json_file)
pdf_links = links['pdf_links']
for link in tqdm(pdf_links , total = len(pdf_links)) :
response : Response = requests.post(
'http://localhost:8002/scrape-pdf' ,
json = {
'url' : link ,
'api_key' : api_key ,
'scrape-images' : False
}
)
def scrape_page(json_file_path : str , api_key : str) -> None :
with open(json_file_path) as json_file : links = json.load(json_file)
all_links = links['all_links']
for link in tqdm(all_links , total = len(all_links)) :
response : Response = requests.post(
'http://localhost:8002/scrape-page' ,
json = {
'url' : link ,
'api_key' : api_key ,
'scrape-images' : False
}
)
def ask(query , session_id , api_key) -> dict :
response : Response = requests.post(
'http://localhost:8002/ask' ,
json = {
'query' : query ,
'session_id' : session_id ,
'api_key' : api_key
}
)
print(json.dumps(response.json() , indent = 4))
return response.json()
# scrape_url_and_save_in_json_file('https://www.thetravellerdmc.com/' , 'temp.json')
scrape_pdfs('temp.json' , 'vk_LANm5E0tSA3bWdN46wW4DVOlJWAMbNoa874BiNSXz7dFIddNzp5I04BNoG2mlI4N')
scrape_page('temp.json' , 'vk_LANm5E0tSA3bWdN46wW4DVOlJWAMbNoa874BiNSXz7dFIddNzp5I04BNoG2mlI4N')