Release v0.6.4

# Release Notes

- Fix attachment sending via Telegram interfaces (81673b5)
- Fix PollingTelegramInterface dropping whenever an error occurred while responding (ec19921)
- Fix `Pipeline._run_pipeline` failing when `ctx_id=None` (5c22cc7)
- Docker improvements (#279)
- Various tutorial improvements
- Add release checklist

.github/PULL_REQUEST_TEMPLATE.md

@@ -6,7 +6,7 @@
 
 - [ ] I have performed a self-review of the changes
 
-*List here tasks to do in order to complete this PR.*
+*List here tasks to complete in order to mark this PR as ready for review.*
 
 # To Consider
 

.github/process_github_events.py

@@ -0,0 +1,81 @@
+# flake8: noqa
+import os
+import json
+import requests
+
+GITHUB_ARGS = {
+    "GITHUB_TOKEN": None,
+    "GITHUB_REPOSITORY": None,
+    "GITHUB_EVENT_PATH": None,
+    "GITHUB_EVENT_NAME": None,
+}
+
+for arg in GITHUB_ARGS:
+    GITHUB_ARGS[arg] = os.getenv(arg)
+
+    if GITHUB_ARGS[arg] is None:
+        raise RuntimeError(f"`{arg}` is not set")
+
+
+def post_comment_on_pr(comment: str, pr_number: int):
+    """
+    Leave a comment as `github-actions` bot on a PR.
+    """
+    headers = {
+        "Accept": "application/vnd.github+json",
+        "Authorization": f'Bearer {GITHUB_ARGS["GITHUB_TOKEN"]}',
+        "X-GitHub-Api-Version": "2022-11-28",
+    }
+
+    escaped_comment = comment.replace("\n", "\\n")
+
+    data = f'{{"body": "{escaped_comment}","event": "COMMENT","comments": []}}'
+
+    response = requests.post(
+        f'https://api.github.com/repos/{GITHUB_ARGS["GITHUB_REPOSITORY"]}/pulls/{pr_number}/reviews',
+        headers=headers,
+        data=data,
+    )
+
+    if not response.status_code == 200:
+        raise RuntimeError(response.__dict__)
+
+
+RELEASE_CHECKLIST = """It appears this PR is a release PR (change its base from `master` if that is not the case).
+
+Here's a release checklist:
+
+- [ ] Update package version
+- [ ] Change PR merge option
+- [ ] Test modules without automated testing:
+  - [ ] Requiring telegram `api_id` and `api_hash`
+  - [ ] Requiring `HF_API_KEY`
+- [ ] Search for objects to be deprecated
+"""
+
+
+def post_release_checklist(pr_payload: dict):
+    pr_number = pr_payload["number"]
+    pr_base = pr_payload["base"]
+
+    if pr_base["ref"] == "master":
+        print("post_release_checklist")
+        post_comment_on_pr(RELEASE_CHECKLIST, pr_number)
+
+
+def on_opened_pull_request(event_info: dict):
+    print("on_opened_pull_request")
+
+    post_release_checklist(event_info["pull_request"])
+
+
+def main():
+    with open(GITHUB_ARGS["GITHUB_EVENT_PATH"], "r", encoding="utf-8") as fd:
+        event_info = json.load(fd)
+    print(f"event info: {event_info}")
+    if GITHUB_ARGS["GITHUB_EVENT_NAME"] == "pull_request_target" and event_info["action"] == "opened":
+        on_opened_pull_request(event_info)
+
+
+if __name__ == "__main__":
+    main()

.github/workflows/event_handler.yml

@@ -0,0 +1,28 @@
+on:
+  pull_request_target:
+    types: [ opened ]
+
+jobs:
+  event_handler:
+    strategy:
+      fail-fast: false
+
+    runs-on: ubuntu-latest
+
+    steps:
+      - uses: actions/checkout@v4
+
+      - name: set up python 3.10
+        uses: actions/setup-python@v4
+        with:
+          python-version: "3.10"
+
+      - name: install dependencies
+        run: python -m pip install requests
+        shell: bash
+
+      - name: handle event
+        env:
+          GITHUB_TOKEN: ${{ secrets.GITHUB_TOKEN }}
+        run: python .github/process_github_events.py
+        shell: bash

CONTRIBUTING.md

@@ -106,7 +106,7 @@ To execute all tests, including integration with DBs and APIs tests, run
 ```bash
 make test_all
 ```
-for successful execution of this command `Docker` and `docker-compose` are required.
+for successful execution of this command `Docker` and `docker compose` are required.
 
 To make sure that the code satisfies only the style requirements, run
 ```bash
@@ -127,22 +127,22 @@ DFF uses docker images for two purposes:
 The first group can be launched via
 
 ```bash
-docker-compose --profile context_storage up
+docker compose --profile context_storage up
 ```
 
 This will download and run all the databases (`mysql`, `postgres`, `redis`, `mongo`, `ydb`).
 
 The second group can be launched via
 
 ```bash
-docker-compose --profile stats up
+docker compose --profile stats up
 ```
 
 This will download and launch Superset Dashboard, Clickhouse, OpenTelemetry Collector.
 
 To launch both groups run
 ```bash
-docker-compose --profile context_storage --profile stats up
+docker compose --profile context_storage --profile stats up
 ```
 or
 ```bash

README.md

@@ -46,7 +46,7 @@ pip install dff[benchmark]  # dependencies for benchmarking
 For example, if you are going to use one of the database backends,
 you can specify the corresponding requirements yourself. Multiple dependencies can be installed at once, e.g.
 ```bash
-pip install dff[postgresql, mysql]
+pip install dff[postgresql,mysql]
 ```
 
 ## Basic example

docker-compose.yml → compose.yml

@@ -1,5 +1,6 @@
 version: "3.9"
 services:
+
   mysql:
     env_file: [.env_file]
     image: mysql:latest
@@ -10,6 +11,13 @@ services:
       - 3307:3306
     volumes:
       - mysql-data:/var/lib/mysql
+    healthcheck:
+      test: mysql -u $${MYSQL_USERNAME} -p$${MYSQL_PASSWORD} -e "select 1;"
+      interval: 5s
+      timeout: 10s
+      retries: 5
+      start_period: 30s
+
   psql:
     env_file: [.env_file]
     image: postgres:latest
@@ -20,6 +28,13 @@ services:
       - 5432:5432
     volumes:
       - postgres-data:/var/lib/postgresql/data
+    healthcheck:
+      test: psql pg_isready -U $${POSTGRES_USERNAME} -d $${POSTGRES_DB}
+      interval: 5s
+      timeout: 10s
+      retries: 5
+      start_period: 30s
+
   redis:
     env_file: [.env_file]
     image: redis:latest
@@ -31,6 +46,13 @@ services:
       - 6379:6379
     volumes:
       - redis-data:/data
+    healthcheck:
+      test: redis-cli --raw incr ping
+      interval: 5s
+      timeout: 10s
+      retries: 5
+      start_period: 30s
+
   mongo:
     env_file: [.env_file]
     image: mongo:latest
@@ -41,6 +63,13 @@ services:
       - 27017:27017
     volumes:
       - mongo-data:/data/db
+    healthcheck:
+      test: mongosh --norc --quiet --eval 'db.runCommand("ping").ok' localhost:27017/test
+      interval: 5s
+      timeout: 10s
+      retries: 5
+      start_period: 30s
+
   ydb:
     env_file: [.env_file]
     image: cr.yandex/yc/yandex-docker-local-ydb:latest
@@ -55,6 +84,13 @@ services:
     volumes:
       - ydb-data:/ydb_data
       - ydb-certs:/ydb_certs
+    healthcheck:
+      test: sh ./health_check
+      interval: 5s
+      timeout: 10s
+      retries: 5
+      start_period: 30s
+
   dashboard:
     env_file: [.env_file]
     build:
@@ -70,6 +106,7 @@ services:
       - stats
     ports:
       - "8088:8088"
+
   dashboard-metadata:
     env_file: [.env_file]
     image: postgres:latest
@@ -83,11 +120,13 @@ services:
     command: -p 5433
     healthcheck:
       test: pg_isready -p 5433 --username=$${POSTGRES_USERNAME}
-      interval: 4s
-      timeout: 3s
-      retries: 3
+      interval: 5s
+      timeout: 10s
+      retries: 5
+      start_period: 30s
     volumes:
       - dashboard-data:/var/lib/postgresql/data
+
   clickhouse:
     env_file: [.env_file]
     image: clickhouse/clickhouse-server:latest
@@ -101,10 +140,12 @@ services:
     volumes:
       - ch-data:/var/lib/clickhouse/
     healthcheck:
-      test: wget --no-verbose --tries=1 --spider http://localhost:8123/ping || exit 1
+      test: wget --no-verbose --tries=1 --spider http://localhost:8123/ping
       interval: 5s
-      timeout: 4s
+      timeout: 10s
       retries: 5
+      start_period: 30s
+
   otelcol:
     image: otel/opentelemetry-collector-contrib:latest
     profiles:
@@ -121,6 +162,7 @@ services:
     ports:
       - "4317:4317"    # OTLP over gRPC receiver
       - "4318:4318"    # OTLP over HTTP receiver
+
 volumes:
   ch-data:
   dashboard-data:

dff/__init__.py

@@ -3,7 +3,7 @@
 
 __author__ = "Denis Kuznetsov"
 __email__ = "[email protected]"
-__version__ = "0.6.3"
+__version__ = "0.6.4"
 
 
 import nest_asyncio