[AUR-401] Disable Haystack telemetry with monkey patching (#1)
Sample Haystack log when running a pipeline. Note: the `pipeline.classname` can leak company information.
```json
{
"hardware.cpus": 16,
"hardware.gpus": 0,
"libraries.colab": false,
"libraries.cuda": false,
"libraries.haystack": "1.20.0rc0",
"libraries.ipython": false,
"libraries.pytest": false,
"libraries.ray": false,
"libraries.torch": false,
"libraries.transformers": "4.31.0",
"os.containerized": false,
"os.family": "Linux",
"os.machine": "x86_64",
"os.version": "6.2.0-26-generic",
"pipeline.classname": "TempPipeline",
"pipeline.config_hash": "07a8eddd5a6e512c0d898c6d9f445ed9",
"pipeline.nodes.PromptNode": 1,
"pipeline.nodes.Shaper": 1,
"pipeline.nodes.WebRetriever": 1,
"pipeline.run_parameters.debug": false,
"pipeline.run_parameters.documents": [
0
],
"pipeline.run_parameters.file_paths": 0,
"pipeline.run_parameters.labels": 0,
"pipeline.run_parameters.meta": 1,
"pipeline.run_parameters.params": false,
"pipeline.run_parameters.queries": true,
"pipeline.runs": 1,
"pipeline.type": "Query",
"python.version": "3.10.12"
}
```
Solution: Haystack telemetry uses the `telemetry` variable, `posthog` library and `HAYSTACK_TELEMETRY_ENABLED` envar. We set the envar to False and make sure the relevant objects are disabled.
This commit is contained in:
Nguyen Trung Duc (john)
GitHub
parent
043209fda7
commit
e9d1d5c118
451
.gitignore
vendored
Normal file
451
.gitignore
vendored
Normal file
|
|
@ -0,0 +1,451 @@
|
|||
# Created by https://www.toptal.com/developers/gitignore/api/python,linux,macos,windows,vim,emacs,visualstudiocode,pycharm
|
||||
# Edit at https://www.toptal.com/developers/gitignore?templates=python,linux,macos,windows,vim,emacs,visualstudiocode,pycharm
|
||||
|
||||
### Emacs ###
|
||||
# -*- mode: gitignore; -*-
|
||||
*~
|
||||
\#*\#
|
||||
/.emacs.desktop
|
||||
/.emacs.desktop.lock
|
||||
*.elc
|
||||
auto-save-list
|
||||
tramp
|
||||
.\#*
|
||||
|
||||
# Org-mode
|
||||
.org-id-locations
|
||||
*_archive
|
||||
|
||||
# flymake-mode
|
||||
*_flymake.*
|
||||
|
||||
# eshell files
|
||||
/eshell/history
|
||||
/eshell/lastdir
|
||||
|
||||
# elpa packages
|
||||
/elpa/
|
||||
|
||||
# reftex files
|
||||
*.rel
|
||||
|
||||
# AUCTeX auto folder
|
||||
/auto/
|
||||
|
||||
# cask packages
|
||||
.cask/
|
||||
dist/
|
||||
|
||||
# Flycheck
|
||||
flycheck_*.el
|
||||
|
||||
# server auth directory
|
||||
/server/
|
||||
|
||||
# projectiles files
|
||||
.projectile
|
||||
|
||||
# directory configuration
|
||||
.dir-locals.el
|
||||
|
||||
# network security
|
||||
/network-security.data
|
||||
|
||||
|
||||
### Linux ###
|
||||
|
||||
# temporary files which can be created if a process still has a handle open of a deleted file
|
||||
.fuse_hidden*
|
||||
|
||||
# KDE directory preferences
|
||||
.directory
|
||||
|
||||
# Linux trash folder which might appear on any partition or disk
|
||||
.Trash-*
|
||||
|
||||
# .nfs files are created when an open file is removed but is still being accessed
|
||||
.nfs*
|
||||
|
||||
### macOS ###
|
||||
# General
|
||||
.DS_Store
|
||||
.AppleDouble
|
||||
.LSOverride
|
||||
|
||||
# Icon must end with two \r
|
||||
Icon
|
||||
|
||||
|
||||
# Thumbnails
|
||||
._*
|
||||
|
||||
# Files that might appear in the root of a volume
|
||||
.DocumentRevisions-V100
|
||||
.fseventsd
|
||||
.Spotlight-V100
|
||||
.TemporaryItems
|
||||
.Trashes
|
||||
.VolumeIcon.icns
|
||||
.com.apple.timemachine.donotpresent
|
||||
|
||||
# Directories potentially created on remote AFP share
|
||||
.AppleDB
|
||||
.AppleDesktop
|
||||
Network Trash Folder
|
||||
Temporary Items
|
||||
.apdisk
|
||||
|
||||
### macOS Patch ###
|
||||
# iCloud generated files
|
||||
*.icloud
|
||||
|
||||
### PyCharm ###
|
||||
# Covers JetBrains IDEs: IntelliJ, RubyMine, PhpStorm, AppCode, PyCharm, CLion, Android Studio, WebStorm and Rider
|
||||
# Reference: https://intellij-support.jetbrains.com/hc/en-us/articles/206544839
|
||||
|
||||
# User-specific stuff
|
||||
.idea/**/workspace.xml
|
||||
.idea/**/tasks.xml
|
||||
.idea/**/usage.statistics.xml
|
||||
.idea/**/dictionaries
|
||||
.idea/**/shelf
|
||||
|
||||
# AWS User-specific
|
||||
.idea/**/aws.xml
|
||||
|
||||
# Generated files
|
||||
.idea/**/contentModel.xml
|
||||
|
||||
# Sensitive or high-churn files
|
||||
.idea/**/dataSources/
|
||||
.idea/**/dataSources.ids
|
||||
.idea/**/dataSources.local.xml
|
||||
.idea/**/sqlDataSources.xml
|
||||
.idea/**/dynamic.xml
|
||||
.idea/**/uiDesigner.xml
|
||||
.idea/**/dbnavigator.xml
|
||||
|
||||
# Gradle
|
||||
.idea/**/gradle.xml
|
||||
.idea/**/libraries
|
||||
|
||||
# Gradle and Maven with auto-import
|
||||
# When using Gradle or Maven with auto-import, you should exclude module files,
|
||||
# since they will be recreated, and may cause churn. Uncomment if using
|
||||
# auto-import.
|
||||
# .idea/artifacts
|
||||
# .idea/compiler.xml
|
||||
# .idea/jarRepositories.xml
|
||||
# .idea/modules.xml
|
||||
# .idea/*.iml
|
||||
# .idea/modules
|
||||
# *.iml
|
||||
# *.ipr
|
||||
|
||||
# CMake
|
||||
cmake-build-*/
|
||||
|
||||
# Mongo Explorer plugin
|
||||
.idea/**/mongoSettings.xml
|
||||
|
||||
# File-based project format
|
||||
*.iws
|
||||
|
||||
# IntelliJ
|
||||
out/
|
||||
|
||||
# mpeltonen/sbt-idea plugin
|
||||
.idea_modules/
|
||||
|
||||
# JIRA plugin
|
||||
atlassian-ide-plugin.xml
|
||||
|
||||
# Cursive Clojure plugin
|
||||
.idea/replstate.xml
|
||||
|
||||
# SonarLint plugin
|
||||
.idea/sonarlint/
|
||||
|
||||
# Crashlytics plugin (for Android Studio and IntelliJ)
|
||||
com_crashlytics_export_strings.xml
|
||||
crashlytics.properties
|
||||
crashlytics-build.properties
|
||||
fabric.properties
|
||||
|
||||
# Editor-based Rest Client
|
||||
.idea/httpRequests
|
||||
|
||||
# Android studio 3.1+ serialized cache file
|
||||
.idea/caches/build_file_checksums.ser
|
||||
|
||||
### PyCharm Patch ###
|
||||
# Comment Reason: https://github.com/joeblau/gitignore.io/issues/186#issuecomment-215987721
|
||||
|
||||
# *.iml
|
||||
# modules.xml
|
||||
# .idea/misc.xml
|
||||
# *.ipr
|
||||
|
||||
# Sonarlint plugin
|
||||
# https://plugins.jetbrains.com/plugin/7973-sonarlint
|
||||
.idea/**/sonarlint/
|
||||
|
||||
# SonarQube Plugin
|
||||
# https://plugins.jetbrains.com/plugin/7238-sonarqube-community-plugin
|
||||
.idea/**/sonarIssues.xml
|
||||
|
||||
# Markdown Navigator plugin
|
||||
# https://plugins.jetbrains.com/plugin/7896-markdown-navigator-enhanced
|
||||
.idea/**/markdown-navigator.xml
|
||||
.idea/**/markdown-navigator-enh.xml
|
||||
.idea/**/markdown-navigator/
|
||||
|
||||
# Cache file creation bug
|
||||
# See https://youtrack.jetbrains.com/issue/JBR-2257
|
||||
.idea/$CACHE_FILE$
|
||||
|
||||
# CodeStream plugin
|
||||
# https://plugins.jetbrains.com/plugin/12206-codestream
|
||||
.idea/codestream.xml
|
||||
|
||||
# Azure Toolkit for IntelliJ plugin
|
||||
# https://plugins.jetbrains.com/plugin/8053-azure-toolkit-for-intellij
|
||||
.idea/**/azureSettings.xml
|
||||
|
||||
### Python ###
|
||||
# Byte-compiled / optimized / DLL files
|
||||
__pycache__/
|
||||
*.py[cod]
|
||||
*$py.class
|
||||
|
||||
# C extensions
|
||||
*.so
|
||||
|
||||
# Distribution / packaging
|
||||
.Python
|
||||
build/
|
||||
develop-eggs/
|
||||
downloads/
|
||||
eggs/
|
||||
.eggs/
|
||||
lib/
|
||||
lib64/
|
||||
parts/
|
||||
sdist/
|
||||
var/
|
||||
wheels/
|
||||
share/python-wheels/
|
||||
*.egg-info/
|
||||
.installed.cfg
|
||||
*.egg
|
||||
MANIFEST
|
||||
|
||||
# PyInstaller
|
||||
# Usually these files are written by a python script from a template
|
||||
# before PyInstaller builds the exe, so as to inject date/other infos into it.
|
||||
*.manifest
|
||||
*.spec
|
||||
|
||||
# Installer logs
|
||||
pip-log.txt
|
||||
pip-delete-this-directory.txt
|
||||
|
||||
# Unit test / coverage reports
|
||||
htmlcov/
|
||||
.tox/
|
||||
.nox/
|
||||
.coverage
|
||||
.coverage.*
|
||||
.cache
|
||||
nosetests.xml
|
||||
coverage.xml
|
||||
*.cover
|
||||
*.py,cover
|
||||
.hypothesis/
|
||||
.pytest_cache/
|
||||
cover/
|
||||
|
||||
# Translations
|
||||
*.mo
|
||||
*.pot
|
||||
|
||||
# Django stuff:
|
||||
*.log
|
||||
local_settings.py
|
||||
db.sqlite3
|
||||
db.sqlite3-journal
|
||||
|
||||
# Flask stuff:
|
||||
instance/
|
||||
.webassets-cache
|
||||
|
||||
# Scrapy stuff:
|
||||
.scrapy
|
||||
|
||||
# Sphinx documentation
|
||||
docs/_build/
|
||||
|
||||
# PyBuilder
|
||||
.pybuilder/
|
||||
target/
|
||||
|
||||
# Jupyter Notebook
|
||||
.ipynb_checkpoints
|
||||
|
||||
# IPython
|
||||
profile_default/
|
||||
ipython_config.py
|
||||
|
||||
# pyenv
|
||||
# For a library or package, you might want to ignore these files since the code is
|
||||
# intended to run in multiple environments; otherwise, check them in:
|
||||
# .python-version
|
||||
|
||||
# pipenv
|
||||
# According to pypa/pipenv#598, it is recommended to include Pipfile.lock in version control.
|
||||
# However, in case of collaboration, if having platform-specific dependencies or dependencies
|
||||
# having no cross-platform support, pipenv may install dependencies that don't work, or not
|
||||
# install all needed dependencies.
|
||||
#Pipfile.lock
|
||||
|
||||
# poetry
|
||||
# Similar to Pipfile.lock, it is generally recommended to include poetry.lock in version control.
|
||||
# This is especially recommended for binary packages to ensure reproducibility, and is more
|
||||
# commonly ignored for libraries.
|
||||
# https://python-poetry.org/docs/basic-usage/#commit-your-poetrylock-file-to-version-control
|
||||
#poetry.lock
|
||||
|
||||
# pdm
|
||||
# Similar to Pipfile.lock, it is generally recommended to include pdm.lock in version control.
|
||||
#pdm.lock
|
||||
# pdm stores project-wide configurations in .pdm.toml, but it is recommended to not include it
|
||||
# in version control.
|
||||
# https://pdm.fming.dev/#use-with-ide
|
||||
.pdm.toml
|
||||
|
||||
# PEP 582; used by e.g. github.com/David-OConnor/pyflow and github.com/pdm-project/pdm
|
||||
__pypackages__/
|
||||
|
||||
# Celery stuff
|
||||
celerybeat-schedule
|
||||
celerybeat.pid
|
||||
|
||||
# SageMath parsed files
|
||||
*.sage.py
|
||||
|
||||
# Environments
|
||||
.env
|
||||
.venv
|
||||
env/
|
||||
venv/
|
||||
ENV/
|
||||
env.bak/
|
||||
venv.bak/
|
||||
|
||||
# Spyder project settings
|
||||
.spyderproject
|
||||
.spyproject
|
||||
|
||||
# Rope project settings
|
||||
.ropeproject
|
||||
|
||||
# mkdocs documentation
|
||||
/site
|
||||
|
||||
# mypy
|
||||
.mypy_cache/
|
||||
.dmypy.json
|
||||
dmypy.json
|
||||
|
||||
# Pyre type checker
|
||||
.pyre/
|
||||
|
||||
# pytype static type analyzer
|
||||
.pytype/
|
||||
|
||||
# Cython debug symbols
|
||||
cython_debug/
|
||||
|
||||
# PyCharm
|
||||
# JetBrains specific template is maintained in a separate JetBrains.gitignore that can
|
||||
# be found at https://github.com/github/gitignore/blob/main/Global/JetBrains.gitignore
|
||||
# and can be added to the global gitignore or merged into this file. For a more nuclear
|
||||
# option (not recommended) you can uncomment the following to ignore the entire idea folder.
|
||||
#.idea/
|
||||
|
||||
### Python Patch ###
|
||||
# Poetry local configuration file - https://python-poetry.org/docs/configuration/#local-configuration
|
||||
poetry.toml
|
||||
|
||||
# ruff
|
||||
.ruff_cache/
|
||||
|
||||
# LSP config files
|
||||
pyrightconfig.json
|
||||
|
||||
### Vim ###
|
||||
# Swap
|
||||
[._]*.s[a-v][a-z]
|
||||
!*.svg # comment out if you don't need vector files
|
||||
[._]*.sw[a-p]
|
||||
[._]s[a-rt-v][a-z]
|
||||
[._]ss[a-gi-z]
|
||||
[._]sw[a-p]
|
||||
|
||||
# Session
|
||||
Session.vim
|
||||
Sessionx.vim
|
||||
|
||||
# Temporary
|
||||
.netrwhist
|
||||
# Auto-generated tag files
|
||||
tags
|
||||
# Persistent undo
|
||||
[._]*.un~
|
||||
|
||||
### VisualStudioCode ###
|
||||
.vscode/*
|
||||
!.vscode/settings.json
|
||||
!.vscode/tasks.json
|
||||
!.vscode/launch.json
|
||||
!.vscode/extensions.json
|
||||
!.vscode/*.code-snippets
|
||||
|
||||
# Local History for Visual Studio Code
|
||||
.history/
|
||||
|
||||
# Built Visual Studio Code Extensions
|
||||
*.vsix
|
||||
|
||||
### VisualStudioCode Patch ###
|
||||
# Ignore all local history of files
|
||||
.history
|
||||
.ionide
|
||||
|
||||
### Windows ###
|
||||
# Windows thumbnail cache files
|
||||
Thumbs.db
|
||||
Thumbs.db:encryptable
|
||||
ehthumbs.db
|
||||
ehthumbs_vista.db
|
||||
|
||||
# Dump file
|
||||
*.stackdump
|
||||
|
||||
# Folder config file
|
||||
[Dd]esktop.ini
|
||||
|
||||
# Recycle Bin used on file shares
|
||||
$RECYCLE.BIN/
|
||||
|
||||
# Windows Installer files
|
||||
*.cab
|
||||
*.msi
|
||||
*.msix
|
||||
*.msm
|
||||
*.msp
|
||||
|
||||
# Windows shortcuts
|
||||
*.lnk
|
||||
|
||||
# End of https://www.toptal.com/developers/gitignore/api/python,linux,macos,windows,vim,emacs,visualstudiocode,pycharm
|
||||
|
|
@ -0,0 +1,25 @@
|
|||
# Disable telemetry with monkey patching
|
||||
import logging
|
||||
|
||||
logger = logging.getLogger(__name__)
|
||||
try:
|
||||
import posthog
|
||||
|
||||
def capture(*args, **kwargs):
|
||||
logger.info("posthog.capture called with args: %s, kwargs: %s", args, kwargs)
|
||||
|
||||
posthog.capture = capture
|
||||
except ImportError:
|
||||
pass
|
||||
|
||||
try:
|
||||
import os
|
||||
|
||||
os.environ["HAYSTACK_TELEMETRY_ENABLED"] = "False"
|
||||
import haystack.telemetry
|
||||
|
||||
haystack.telemetry.telemetry = None
|
||||
except ImportError:
|
||||
pass
|
||||
|
||||
__version__ = "0.0.1"
|
||||
51
setup.py
51
setup.py
|
|
@ -0,0 +1,51 @@
|
|||
import codecs
|
||||
import re
|
||||
from pathlib import Path
|
||||
|
||||
import setuptools
|
||||
|
||||
|
||||
def read(file_path: str) -> str:
|
||||
return codecs.open(file_path, "r").read()
|
||||
|
||||
|
||||
def get_version() -> str:
|
||||
version_file = read(str(Path("kotaemon", "__init__.py")))
|
||||
match = re.search(r"^__version__ = ['\"]([^'\"]*)['\"]", version_file, re.M)
|
||||
if match:
|
||||
return match.group(1)
|
||||
raise RuntimeError("Cannot find verison string")
|
||||
|
||||
|
||||
setuptools.setup(
|
||||
name="kotaemon",
|
||||
version=get_version(),
|
||||
author="john",
|
||||
author_email="john@cinnamon.com",
|
||||
description="Kotaemon core library for AI development",
|
||||
long_description=read("README.md"),
|
||||
long_description_content_type="text/markdown",
|
||||
url="https://github.com/Cinnamon/kotaemon/",
|
||||
packages=setuptools.find_packages(exclude=("tests", "tests.*")),
|
||||
install_requires=[
|
||||
"farm-haystack"
|
||||
],
|
||||
extras_require={
|
||||
"dev": [
|
||||
"pytest",
|
||||
"pre-commit",
|
||||
"black",
|
||||
"flake8",
|
||||
"sphinx",
|
||||
"coverage",
|
||||
]
|
||||
},
|
||||
entry_points={"console_scripts": ["kh=kotaemon.cli:main"]},
|
||||
python_requires=">=3",
|
||||
classifiers=[
|
||||
"Programming Language :: Python :: 3",
|
||||
"License :: OSI Approved :: MIT License",
|
||||
"Operating System :: OS Independent",
|
||||
],
|
||||
include_package_data=True,
|
||||
)
|
||||
21
tests/test_telemetry.py
Normal file
21
tests/test_telemetry.py
Normal file
|
|
@ -0,0 +1,21 @@
|
|||
def test_disable_telemetry_import_haystack_first():
|
||||
"""Test that telemetry is disabled when kotaemon lib is initiated after"""
|
||||
import os
|
||||
import haystack.telemetry
|
||||
assert haystack.telemetry.telemetry is not None
|
||||
assert os.environ.get("HAYSTACK_TELEMETRY_ENABLED", "True") != "False"
|
||||
|
||||
import kotaemon # noqa: F401
|
||||
assert haystack.telemetry.telemetry is None
|
||||
assert os.environ.get("HAYSTACK_TELEMETRY_ENABLED", "True") == "False"
|
||||
|
||||
|
||||
def test_disable_telemetry_import_haystack_after_kotaemon():
|
||||
"""Test that telemetry is disabled when kotaemon lib is initiated before"""
|
||||
import os
|
||||
|
||||
import kotaemon # noqa: F401
|
||||
import haystack.telemetry
|
||||
assert haystack.telemetry.telemetry is None
|
||||
assert os.environ.get("HAYSTACK_TELEMETRY_ENABLED", "True") == "False"
|
||||
|
||||
Loading…
Reference in New Issue
Block a user