Use env vars to db's connections

vacancies/conf/settings.py

@@ -14,8 +14,6 @@ import os
 from pathlib import Path
 
 import sentry_sdk
-import clickhouse_connect
-from qdrant_client import QdrantClient
 
 # Build paths inside the project like this: BASE_DIR / 'subdir'.
 BASE_DIR = Path(__file__).resolve().parent.parent.parent
@@ -165,6 +163,7 @@ LOGGING = {
     },
 }
 
-CLICKHOUSE_CLIENT = clickhouse_connect.create_client(host=os.getenv("CLICKHOUSE_HOST", "127.0.0.1"), port=int(os.getenv("CLICKHOUSE_PORT", "18123")))
+CLICKHOUSE_HOST = os.getenv("CLICKHOUSE_HOST", "127.0.0.1")
+CLICKHOUSE_PORT = int(os.getenv("CLICKHOUSE_PORT", "18123"))
 
-QDARNT_CLIENT = QdrantClient(url=os.getenv("QDRANT_URL", "http://localhost:6333"))
+QDRANT_URL = os.getenv("QDRANT_URL", "http://localhost:6333")

vacancies/main/management/commands/collect_vacancies_from_telegram_messages.py

@@ -1,7 +1,9 @@
 from django.core.management import BaseCommand
+import clickhouse_connect
 from vacancies.main.vector_store import add_vectors, extract_features, client as qdrant
-from vacancies.conf.settings import CLICKHOUSE_CLIENT
+from vacancies.conf.settings import CLICKHOUSE_HOST, CLICKHOUSE_PORT
 
+clickhouse_client = clickhouse_connect.create_client(host=CLICKHOUSE_HOST, port=CLICKHOUSE_PORT)
 
 query = """
 SELECT id, chat_username, telegram_id, message, timestamp
@@ -39,7 +41,7 @@ class Command(BaseCommand):
             next_page_offset = response[1]
         exist_points_set = tuple(set(exist_points_ids))
 
-        result_rows = CLICKHOUSE_CLIENT.query(query, parameters={"exist_points": exist_points_set}).result_rows
+        result_rows = clickhouse_client.query(query, parameters={"exist_points": exist_points_set}).result_rows
         result_rows_len = len(result_rows)
         for index, row in enumerate(result_rows):
             (id, chat_username, telegram_id, message, timestamp) = row

vacancies/main/vector_store.py

@@ -1,10 +1,12 @@
 from qdrant_client import models
 from langchain_openai import OpenAIEmbeddings
 from langchain_openai import ChatOpenAI
+from qdrant_client import QdrantClient
 from qdrant_client.models import Filter
 from vacancies.main.models import VacancyFeatures
-from vacancies.conf.settings import QDARNT_CLIENT
+from vacancies.conf.settings import QDRANT_URL
 
+qdrant_client = QdrantClient(url=QDRANT_URL)
 
 FEATURE_NAMES = [
     "job_title", "employment_type", "work_format", "experience", "position_level", "industry", "tech_stack",
@@ -31,13 +33,13 @@ vectors_config = {
     name: models.VectorParams(size=3072, distance=models.Distance.COSINE) for name in FEATURE_NAMES
 }
 
-if not QDARNT_CLIENT.collection_exists("vacancies"):
-    QDARNT_CLIENT.create_collection(
+if not qdrant_client.collection_exists("vacancies"):
+    qdrant_client.create_collection(
         collection_name="vacancies",
         vectors_config=vectors_config
     )
-if not QDARNT_CLIENT.collection_exists("cvs"):
-    QDARNT_CLIENT.create_collection(
+if not qdrant_client.collection_exists("cvs"):
+    qdrant_client.create_collection(
         collection_name="cvs",
         vectors_config=vectors_config
     )
@@ -70,7 +72,7 @@ def add_vectors(collection_name: str, _id: int, features: dict, payload: dict):
     max_similarities = {}
     for name, vec in vectors.items():
         if any(v != 0 for v in vec):
-            results = QDARNT_CLIENT.query_points(
+            results = qdrant_client.query_points(
                 collection_name="vacancies",
                 query=vec,
                 using=name,
@@ -92,7 +94,7 @@ def add_vectors(collection_name: str, _id: int, features: dict, payload: dict):
     if scored and scored[0]["score"] > 33:  # threshold
         return
 
-    QDARNT_CLIENT.upsert(
+    qdrant_client.upsert(
         collection_name=collection_name,
         points=[
             models.PointStruct(
@@ -105,7 +107,7 @@ def add_vectors(collection_name: str, _id: int, features: dict, payload: dict):
 
 
 def search_similarities(query_filter: Filter, cv_id: int):
-    cv = QDARNT_CLIENT.retrieve(
+    cv = qdrant_client.retrieve(
         collection_name="cvs",
         ids=[cv_id],
         with_vectors=True,
@@ -115,7 +117,7 @@ def search_similarities(query_filter: Filter, cv_id: int):
     vacancies_content = {}
     for name, vec in cv.vector.items():
         if any(v != 0 for v in vec):
-            results = QDARNT_CLIENT.query_points(
+            results = qdrant_client.query_points(
                 collection_name="vacancies",
                 query=vec,
                 using=name,