69 lines
2.8 KiB
Python
69 lines
2.8 KiB
Python
from django.core.management import BaseCommand
|
||
from vacancies.main.models import Vacancy
|
||
import clickhouse_connect
|
||
from vacancies.main.vector_store import add_vectors, extract_features, client as qdrant
|
||
|
||
clickhouse_client = clickhouse_connect.create_client(host="127.0.0.1", port=18123)
|
||
|
||
next_page_offset = 0
|
||
exist_points_ids = []
|
||
while next_page_offset is not None:
|
||
response = qdrant.scroll(
|
||
collection_name="vacancies",
|
||
limit=100_000,
|
||
offset=next_page_offset,
|
||
with_payload=False,
|
||
with_vectors=False,
|
||
timeout=30,
|
||
)
|
||
exist_points_ids.extend([point.id for point in response[0]])
|
||
next_page_offset = response[1]
|
||
exist_points_set = tuple(exist_points_ids)
|
||
print("qdrant vacancies points count:", len(exist_points_set))
|
||
|
||
query = f"""
|
||
SELECT id, chat_username, telegram_id, message, timestamp
|
||
FROM telegram_parser_chatmessage
|
||
WHERE timestamp >= now() - INTERVAL 30 DAY
|
||
AND length(message) > 150
|
||
AND arrayCount(x -> position(message, x) > 0, [
|
||
'вакансия', 'ищем', 'требуется', 'разработчик', 'будет плюсом',
|
||
'зарплата', 'оклад', 'з/п', 'руб', 'опыт работы',
|
||
'требования', 'обязанности', 'условия', 'компания', 'офис',
|
||
'удаленно', 'гибкий график', 'полный день', 'частичная занятость',
|
||
'резюме', 'собеседование', 'junior', 'middle', 'senior'
|
||
]) >= 5 AND position(message, 'О себе') = 0 AND position(message, 'Обо мне') = 0 AND position(message, '#ищу') = 0
|
||
AND id NOT IN {exist_points_set}
|
||
"""
|
||
|
||
|
||
class Command(BaseCommand):
|
||
help = "Collect vacancies from telegram messages"
|
||
|
||
def handle(self, *args, **options):
|
||
import time
|
||
start_time = time.time()
|
||
result_rows = clickhouse_client.query(query).result_rows
|
||
print(f"query time: {time.time() - start_time:.4f}")
|
||
result_rows_len = len(result_rows)
|
||
for index, row in enumerate(result_rows):
|
||
(id, chat_username, telegram_id, message, timestamp) = row
|
||
|
||
link = f"https://t.me/{chat_username}/{telegram_id}"
|
||
print(f"Processing {index}/{result_rows_len} link: {link}")
|
||
start_time = time.time()
|
||
features = extract_features(message)
|
||
print(f"ai time: {time.time() - start_time:.4f}")
|
||
vacancy, created = Vacancy.objects.get_or_create(
|
||
link=link,
|
||
)
|
||
|
||
start_time = time.time()
|
||
add_vectors(
|
||
"vacancies",
|
||
vacancy.id,
|
||
features.model_dump(),
|
||
{'content': message, 'features_json': features.model_dump()},
|
||
)
|
||
print(f"write vector time: {time.time() - start_time:.4f}")
|