import openai
import sys

openai.api_key = "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"
upload_file_id = open("upload_key.txt", "rt").read().strip()
print(upload_file_id)


def query_openai():
    question = ("ce ai inteles din documentele citite?")
    response = openai.Answer.create(
        search_model="ada",
        model="curie",
        question=question,
        file=upload_file_id,
        examples_context="In 2017, U.S. life expectancy was 78.6 years.",
        examples=[["What is human life expectancy in the United States?", "78 years."]],
        max_rerank=7,
        max_tokens=90,
        stop=["\n", "<|endoftext|>"],
    )

    for ix in range(len(response.answers)):
        print(f"response: {response.answers[ix]}\n")
    return response.answers[0]
        
##########################################################################

from googlesearch import search


import os
import requests
import shutil

date_time = ("documente")
os.makedirs(date_time, exist_ok=True)
print(f"se cauta {date_time}")

query = query_openai()
num = 10


log_file_path = f'{date_time}/logs.txt'
log_file = open(log_file_path, 'w')
results: list = search(query, num=int(num), start=0, stop=int(num), pause=5)
results_list = []
for url in results:
    log_file.write(f"{url}\n")
    results_list.append(url)
log_file.flush()
log_file.close()

cwd = os.path.curdir
cwd_log_file = os.path.join(cwd, 'logs.txt')
print(cwd_log_file)
shutil.rmtree(cwd_log_file, ignore_errors=True)
shutil.copy2(log_file_path, cwd_log_file)


def download_url(url_to_download, index, folder):
    print(url_to_download)
    local_filename = f'{index}_'+url_to_download.split('/')[-1]
    local_path = os.path.join(folder, local_filename)
    r = requests.get(url_to_download)
    f = open(local_path, 'wb')
    for chunk in r.iter_content(chunk_size=512 * 1024):
        if chunk:  # filter out keep-alive new chunks
            f.write(chunk)
    f.close()
    return


print("am terminat de cautat, acum incep descarcarea documentelor")
ix = 0
for url in results_list:
    try:
        download_url(url, ix, date_time)
    except Exception as ignored:
        pass
    ix += 1



#ada
#curie