vedana-etl 0.1.0.dev3__tar.gz

vedana_etl-0.1.0.dev3/.gitignore

@@ -0,0 +1,499 @@
+# File created using '.gitignore Generator' for Visual Studio Code: https://bit.ly/vscode-gig
+# Created by https://www.toptal.com/developers/gitignore/api/windows,python,pycharm+iml,pycharm+all,pycharm,macos,linux,visualstudiocode
+# Edit at https://www.toptal.com/developers/gitignore?templates=windows,python,pycharm+iml,pycharm+all,pycharm,macos,linux,visualstudiocode
+
+### 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
+
+### PyCharm+all ###
+# 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
+
+# AWS User-specific
+
+# Generated files
+
+# Sensitive or high-churn files
+
+# Gradle
+
+# 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
+
+# Mongo Explorer plugin
+
+# File-based project format
+
+# IntelliJ
+
+# mpeltonen/sbt-idea plugin
+
+# JIRA plugin
+
+# Cursive Clojure plugin
+
+# SonarLint plugin
+
+# Crashlytics plugin (for Android Studio and IntelliJ)
+
+# Editor-based Rest Client
+
+# Android studio 3.1+ serialized cache file
+
+### PyCharm+all Patch ###
+# Ignore everything but code style settings and run configurations
+# that are supposed to be shared within teams.
+
+.idea/*
+
+!.idea/codeStyles
+!.idea/runConfigurations
+
+### PyCharm+iml ###
+# 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
+
+# AWS User-specific
+
+# Generated files
+
+# Sensitive or high-churn files
+
+# Gradle
+
+# 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
+
+# Mongo Explorer plugin
+
+# File-based project format
+
+# IntelliJ
+
+# mpeltonen/sbt-idea plugin
+
+# JIRA plugin
+
+# Cursive Clojure plugin
+
+# SonarLint plugin
+
+# Crashlytics plugin (for Android Studio and IntelliJ)
+
+# Editor-based Rest Client
+
+# Android studio 3.1+ serialized cache file
+
+### PyCharm+iml Patch ###
+# Reason: https://github.com/joeblau/gitignore.io/issues/186#issuecomment-249601023
+
+*.iml
+modules.xml
+.idea/misc.xml
+*.ipr
+
+### Python ###
+# Byte-compiled / optimized / DLL files
+__pycache__/
+*.py[cod]
+*$py.class
+
+# C extensions
+*.so
+
+# Distribution / packaging
+.Python
+build/
+develop-eggs/
+dist/
+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
+
+### 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/windows,python,pycharm+iml,pycharm+all,pycharm,macos,linux,visualstudiocode
+
+# Custom rules (everything added below won't be overriden by 'Generate .gitignore File' if you use 'Update' option)

vedana_etl-0.1.0.dev3/CHANGELOG.md

@@ -0,0 +1,22 @@
+# WIP
+
+* handle vedana-core's DataModel through ETL
+* move Eval away from ETL, processing tests using JIMS & Backoffice now
+* store embeddings in tables for PGVector
+
+# 2025-09-19
+
+* Refactored evaluation script into a Datapipe pipeline
+
+# 2025-09-04
+
+* Covered get_grist_data / filter_grist_data with tests
+* More fixes in processing "reference" type columns for both links and attrs
+
+# 2025-09-02
+
+* Refactor to var-style Table declaration in pipeline
+
+# 0.2.0
+
+* Initial pipeline

vedana_etl-0.1.0.dev3/PKG-INFO

@@ -0,0 +1,51 @@
+Metadata-Version: 2.4
+Name: vedana-etl
+Version: 0.1.0.dev3
+Summary: Pipeline template for Vedana
+Author-email: Andrey Tatarinov <a@tatarinov.co>, Timur Sheydaev <tsheyd@epoch8.co>
+Requires-Python: >=3.12
+Requires-Dist: alembic>=1.16.1
+Requires-Dist: datapipe-app>=0.5.4
+Requires-Dist: datapipe-core>=0.14.3
+Requires-Dist: grist-api>=0.1.1
+Requires-Dist: neo4j>=5.28.1
+Requires-Dist: openai>=2.8.0
+Requires-Dist: pandas>=1.2.0
+Requires-Dist: pgvector>=0.4.2
+Requires-Dist: pytest>=8.4.1
+Requires-Dist: requests>=2.32.4
+Requires-Dist: sqlalchemy>=2.0.41
+Requires-Dist: vedana-core>=0.5.0
+Description-Content-Type: text/markdown
+
+# Basic pipeline for all vedana projects.
+
+This pipeline:
+
+- Parses Grist Data & Data Model
+- Ensures that Memgraph index/vector index structure is in sync with data model
+- Updates Memgraph database in incremental fashion
+
+To add steps:
+1. Pass extra transformations to [get_pipeline](src/pipeline.py)
+2. Create new app configuration from [app.py](src/app.py)
+
+## Pipeline Labels Hierarchy
+
+### Pipeline
+
+`labels=("pipeline", "pipeline_name")` defines a set of operations as standalone, sort of like a DAG in Airflow
+or a Dagster Job. Its purpose is to be able to render it as a separate tab on the ETL page of Backoffice in order to
+look at it independently of other transformations
+
+### Stage
+
+`labels=("stage", "stage_name")` defines a stage of `pipeline`. Currently, stages are useful for creating and managing
+observability features, such as [main dashboard's](/libs/vedana-backoffice/vedana_backoffice/pages/main_dashboard.py)
+Ingest table, which displays DataTable's of all transformations with `labels=("stage", "extract")`.
+Stages are also useful when running the pipeline manually.
+
+### Flow
+
+`labels=("flow", "flow_name")` helps execute a `pipeline` (or possibly several pipelines) in a nice fashion,
+used in defining cron jobs, etc.

vedana_etl-0.1.0.dev3/README.md

@@ -0,0 +1,31 @@
+# Basic pipeline for all vedana projects.
+
+This pipeline:
+
+- Parses Grist Data & Data Model
+- Ensures that Memgraph index/vector index structure is in sync with data model
+- Updates Memgraph database in incremental fashion
+
+To add steps:
+1. Pass extra transformations to [get_pipeline](src/pipeline.py)
+2. Create new app configuration from [app.py](src/app.py)
+
+## Pipeline Labels Hierarchy
+
+### Pipeline
+
+`labels=("pipeline", "pipeline_name")` defines a set of operations as standalone, sort of like a DAG in Airflow
+or a Dagster Job. Its purpose is to be able to render it as a separate tab on the ETL page of Backoffice in order to
+look at it independently of other transformations
+
+### Stage
+
+`labels=("stage", "stage_name")` defines a stage of `pipeline`. Currently, stages are useful for creating and managing
+observability features, such as [main dashboard's](/libs/vedana-backoffice/vedana_backoffice/pages/main_dashboard.py)
+Ingest table, which displays DataTable's of all transformations with `labels=("stage", "extract")`.
+Stages are also useful when running the pipeline manually.
+
+### Flow
+
+`labels=("flow", "flow_name")` helps execute a `pipeline` (or possibly several pipelines) in a nice fashion,
+used in defining cron jobs, etc.

vedana_etl-0.1.0.dev3/pyproject.toml

@@ -0,0 +1,76 @@
+[project]
+name = "vedana-etl"
+dynamic = ["version"]
+description = "Pipeline template for Vedana"
+readme = "README.md"
+authors = [
+  { name = "Andrey Tatarinov", email = "a@tatarinov.co" },
+  { name = "Timur Sheydaev", email = "tsheyd@epoch8.co" },
+]
+requires-python = ">=3.12"
+dependencies = [
+  "alembic>=1.16.1",
+  "datapipe-core>=0.14.3",
+  "datapipe-app>=0.5.4",
+  "pandas>=1.2.0   ",
+  "requests>=2.32.4",
+  "sqlalchemy>=2.0.41",
+  "pgvector>=0.4.2",
+  "grist-api>=0.1.1",
+  "neo4j>=5.28.1",
+  "openai>=2.8.0",
+  "vedana-core>=0.5.0",
+  "pytest>=8.4.1",
+]
+
+[build-system]
+requires = ["hatchling", "uv-dynamic-versioning"]
+build-backend = "hatchling.build"
+
+[tool.hatch.version]
+source = "uv-dynamic-versioning"
+
+[tool.uv-dynamic-versioning]
+enable = true
+vcs = "git"
+pattern = "default"
+
+[dependency-groups]
+dev = [
+  "mypy>=1.19.0",
+  "pytest>=8.4.1",
+  "ruff>=0.14.10",
+  "types-pyyaml>=6.0.12.20250822",
+]
+
+[tool.ruff]
+line-length = 120
+
+[tool.uv-workspace-codegen]
+generate = true
+template_type = ["lib", "publish"]
+generate_standard_pytest_step = false
+typechecker = "mypy"
+custom_steps = """
+- name: Start infra (Grist + Memgraph)
+  run: |
+    docker compose -f libs/vedana-etl/tests/infra/docker-compose.ci.yml up -d
+    echo "Waiting containers..."
+    docker ps
+
+- name: Run unit + integration tests
+  env:
+    GRIST_SERVER_URL: "http://0.0.0.0:8484"
+    GRIST_API_KEY: "e30d2f274a538c05fecd14510887f8a3b7eab718"
+    GRIST_DATA_MODEL_DOC_ID: "wEEmPY3UiwMD"
+    GRIST_DATA_DOC_ID: "qAxQ1gcBKcW7"
+    GRIST_ORG_IN_PATH: "true"
+    GRIST_DEFAULT_EMAIL: "ci@example.com"
+    GRIST_SESSION_SECRET: "dev-secret"
+    MEMGRAPH_URI: "bolt://localhost:7687"
+    MEMGRAPH_USER: ""
+    MEMGRAPH_PWD: ""
+    EMBEDDINGS_DIM: "1536"
+  run: |
+    uv run pytest libs/vedana-etl/
+"""

vedana_etl-0.1.0.dev3/src/vedana_etl/app.py

@@ -0,0 +1,10 @@
+from datapipe.compute import Catalog
+from datapipe_app import DatapipeAPI
+
+from vedana_etl.config import ds
+from vedana_etl.pipeline import default_custom_steps, get_pipeline
+
+# base app - no extra tables / steps
+pipeline = get_pipeline(custom_steps=default_custom_steps)
+
+app = DatapipeAPI(ds, Catalog({}), pipeline)