Merge pull request 'feat: add production deployment baseline' (#28) from feature/production-deployment-baseline into main

Reviewed-on: #28

CHANGELOG.md

@@ -2,6 +2,8 @@
 
 ## Не выпущено
 
+- Добавлен production deployment baseline для Search API и OpenSearch с
+  постоянными хранилищами и healthcheck.
 - Добавлено восстановление незавершённой разметки из `localStorage` после перезагрузки страницы.
 - Добавлена внутренняя лаборатория проверки поисковой выдачи: просмотр документов,
   оценка релевантности 0–3, комментарии и SQLite-экспорт подписанных снимков.

README.md

@@ -10,13 +10,13 @@ Telegram-бот — только часть рабочего окружения
 ## Текущее состояние
 
 Сейчас реализованы Telegram-бот-секретарь версии `0.2.2` и backend версии
-`0.8.1`: добавлено сохранение черновика разметки в браузере.
+`0.8.2`: добавлен production deployment baseline для Search API и OpenSearch.
 размеченном наборе запросов.
 
 | Компонент | Версия | Состояние |
 |---|---:|---|
 | Telegram-бот | `0.2.2` | на Synology работает `0.2.1`; обновление после слияния |
-| Backend | `0.8.1` | добавлено сохранение черновика разметки |
+| Backend | `0.8.2` | добавлен production deployment baseline |
 | Frontend | — | ещё не создан |
 | Сбор и обработка правовых данных | `0.8.0` | добавлены relevance set и оценка выдачи |
 | RAG и база знаний | — | ещё не созданы |
@@ -59,4 +59,4 @@ python3 -m unittest discover -s tools/telegram-bot -v
 
 ---
 
-Акылдаш · Telegram-бот v0.2.2 · Backend v0.8.1 · Frontend — не создан
+Акылдаш · Telegram-бот v0.2.2 · Backend v0.8.2 · Frontend — не создан

backend/README.md

@@ -1,6 +1,6 @@
 # Backend Акылдаш
 
-Версия: `0.8.1`
+Версия: `0.8.2`
 
 Первая backend-область проекта — загрузка правовых документов из официального
 Open Data API ЦБД Минюста Кыргызской Республики. Код расположен в
@@ -240,4 +240,4 @@ PYTHONPATH=backend python3 -m search.query "ЖЧК ачуу тартиби" --la
 
 ---
 
-Акылдаш · Backend v0.8.1 · Frontend — не создан
+Акылдаш · Backend v0.8.2 · Frontend — не создан

backend/ingestion/minjust_cbd.py

@@ -21,7 +21,7 @@ from datetime import datetime, timezone
 from pathlib import Path
 from typing import Callable, Iterable
 
-APP_VERSION = "0.8.1"
+APP_VERSION = "0.8.2"
 API_BASE_URL = "https://cbd.minjust.gov.kg/api/v1/OpenData/"
 LANGUAGES = {"Rus": "ru", "Kyr": "ky"}
 IMAGE_LANGUAGES = {"Russian": "ru", "Kyrgyz": "ky"}

backend/normalization/minjust_cbd.py

@@ -23,7 +23,7 @@ from pathlib import Path
 from typing import Callable
 from urllib.parse import urlsplit
 
-APP_VERSION = "0.8.1"
+APP_VERSION = "0.8.2"
 SCHEMA_VERSION = "1"
 NORMALIZER_VERSION = "1.0.0"
 LANGUAGES = ("ru", "ky")

backend/search/minjust_opensearch.py

@@ -17,7 +17,7 @@ from typing import Iterator
 
 from search.catalog import authority_codes, source_code
 
-APP_VERSION = "0.8.1"
+APP_VERSION = "0.8.2"
 LANGUAGES = {"ru", "ky"}
 DEFAULT_MAPPING = Path(__file__).with_name("minjust-fragments-index.json")
 

deploy/production/.env.example

@@ -0,0 +1,8 @@
+# Absolute path on the production host containing minjust-normalized/.
+DATA_ROOT=/volume1/docker/akyldash/data
+BACKEND_PORT=8080
+SEARCH_INDEX=akyldash-fragments-current
+OPENSEARCH_MEM_LIMIT=4g
+OPENSEARCH_JAVA_OPTS=-Xms2g -Xmx2g
+# Generate with: openssl rand -hex 32
+REVIEW_SECRET=replace-with-a-random-secret

deploy/production/Dockerfile.backend

@@ -0,0 +1,11 @@
+FROM python:3.12-slim
+
+WORKDIR /app
+COPY backend /app/backend
+
+ENV PYTHONPATH=/app/backend
+EXPOSE 8080
+
+CMD ["python", "-m", "search.api", "--host", "0.0.0.0", "--port", "8080", "--url", "http://opensearch:9200", "--index", "akyldash-fragments-current", "--data", "/app/data/minjust-normalized", "--reviews-db", "/app/data/search-reviews.sqlite3"]
+
+HEALTHCHECK --interval=30s --timeout=5s --start-period=20s CMD ["python", "-c", "import urllib.request; urllib.request.urlopen('http://127.0.0.1:8080/review', timeout=3)"]

deploy/production/Dockerfile.opensearch

@@ -0,0 +1,3 @@
+FROM opensearchproject/opensearch:3.7.0
+
+RUN /usr/share/opensearch/bin/opensearch-plugin install --batch analysis-icu

deploy/production/README.md

@@ -0,0 +1,37 @@
+# Production deployment
+
+This compose project runs the Search API and its private OpenSearch node. It
+binds the API only to `127.0.0.1`; publish it through an authenticated reverse
+proxy or VPN. OpenSearch is not published outside the compose network.
+
+The current compose intentionally disables the OpenSearch security plugin to
+match the existing API client. Keep both services on a private host/network
+until authenticated OpenSearch support is implemented.
+
+## First deployment
+
+1. Copy this directory to the host with the repository source.
+2. Copy `.env.example` to `.env`, set an absolute `DATA_ROOT`, and replace
+   `REVIEW_SECRET` with a random value. Do not commit `.env`.
+3. Put the normalized dataset under `$DATA_ROOT/minjust-normalized/`.
+4. Check the rendered configuration:
+
+   ```bash
+   docker compose --env-file .env -f compose.yaml config
+   ```
+
+5. Start the services:
+
+   ```bash
+   docker compose --env-file .env -f compose.yaml up -d --build
+   docker compose --env-file .env -f compose.yaml ps
+   curl -fsS http://127.0.0.1:${BACKEND_PORT:-8080}/review >/dev/null
+   ```
+
+6. Load the versioned index and switch its alias only after the import and
+   validation succeed. Back up `DATA_ROOT` and the `opensearch-data` volume
+   before the first import.
+
+This is a deployment baseline, not a public internet exposure recipe. TLS,
+authentication, backups, monitoring, and a production OpenSearch security
+configuration must be provided by the host reverse proxy/operations setup.

deploy/production/compose.yaml

@@ -0,0 +1,64 @@
+services:
+  opensearch:
+    build:
+      context: ../..
+      dockerfile: deploy/production/Dockerfile.opensearch
+    restart: unless-stopped
+    environment:
+      discovery.type: single-node
+      bootstrap.memory_lock: "true"
+      DISABLE_SECURITY_PLUGIN: "true"
+      OPENSEARCH_JAVA_OPTS: ${OPENSEARCH_JAVA_OPTS:--Xms2g -Xmx2g}
+    mem_limit: ${OPENSEARCH_MEM_LIMIT:-4g}
+    expose:
+      - "9200"
+    ulimits:
+      memlock:
+        soft: -1
+        hard: -1
+      nofile:
+        soft: 65536
+        hard: 65536
+    volumes:
+      - opensearch-data:/usr/share/opensearch/data
+    healthcheck:
+      test: ["CMD-SHELL", "curl -fsS http://127.0.0.1:9200/_cluster/health || exit 1"]
+      interval: 30s
+      timeout: 10s
+      retries: 10
+
+  backend:
+    build:
+      context: ../..
+      dockerfile: deploy/production/Dockerfile.backend
+    restart: unless-stopped
+    environment:
+      REVIEW_SECRET: ${REVIEW_SECRET:?set REVIEW_SECRET in .env}
+    command:
+      - python
+      - -m
+      - search.api
+      - --host
+      - 0.0.0.0
+      - --port
+      - "8080"
+      - --url
+      - http://opensearch:9200
+      - --index
+      - ${SEARCH_INDEX:-akyldash-fragments-current}
+      - --data
+      - /app/data/minjust-normalized
+      - --reviews-db
+      - /app/data/search-reviews.sqlite3
+      - --review-secret
+      - ${REVIEW_SECRET}
+    ports:
+      - "127.0.0.1:${BACKEND_PORT:-8080}:8080"
+    depends_on:
+      opensearch:
+        condition: service_healthy
+    volumes:
+      - ${DATA_ROOT:?set DATA_ROOT in .env}:/app/data
+
+volumes:
+  opensearch-data: