[DRAFT] Webhook example with record completed

argilla-server/.env.dev

@@ -2,3 +2,5 @@ OBJC_DISABLE_INITIALIZE_FORK_SAFETY=YES # Needed by RQ to work with forked proce
 ALEMBIC_CONFIG=src/argilla_server/alembic.ini
 ARGILLA_AUTH_SECRET_KEY=8VO7na5N/jQx+yP/N+HlE8q51vPdrxqlh6OzoebIyko= # With this we avoid using a different key every time the server is reloaded
 ARGILLA_DATABASE_URL=sqlite+aiosqlite:///${HOME}/.argilla/argilla.db?check_same_thread=False
+# For mac users only https://github.com/rq/rq/issues/1418
+OBJC_DISABLE_INITIALIZE_FORK_SAFETY=YES

argilla-server/src/argilla_server/contexts/distribution.py

@@ -12,14 +12,13 @@
 # See the License for the specific language governing permissions and
 # limitations under the License.
 
-import backoff
-import sqlalchemy
-
 from typing import List
 from uuid import UUID
 
-from sqlalchemy.orm import selectinload
+import backoff
+import sqlalchemy
 from sqlalchemy.ext.asyncio import AsyncSession
+from sqlalchemy.orm import selectinload
 
 from argilla_server.api.webhooks.v1.enums import RecordEvent
 from argilla_server.api.webhooks.v1.records import notify_record_event as notify_record_event_v1

argilla/src/argilla/_models/_record/_record.py

@@ -39,6 +39,8 @@ class RecordModel(ResourceModel):
  suggestions: Optional[Union[Tuple[SuggestionModel], List[SuggestionModel]]] = Field(default_factory=tuple)
  external_id: Optional[Any] = Field(default=None)
 
+ dataset_id: Optional[uuid.UUID] = Field(default=None)
+
  @field_serializer("external_id", when_used="unless-none")
  def serialize_external_id(self, value: str) -> str:
  return str(value)
@@ -77,3 +79,29 @@ def validate_external_id(cls, external_id: Any) -> Union[str, int, uuid.UUID]:
  if external_id is None:
  external_id = uuid.uuid4()
  return external_id
+
+ @field_validator("vectors", mode="before")
+ @classmethod
+ def empty_vectors_if_none(cls, vectors: Optional[List[VectorModel]]) -> Optional[List[VectorModel]]:
+ """Ensure vectors is None if not provided."""
+ if vectors is None:
+ return []
+ return vectors
+
+ @field_validator("responses", mode="before")
+ @classmethod
+ def empty_responses_if_none(cls, responses: Optional[List[UserResponseModel]]) -> Optional[List[UserResponseModel]]:
+ """Ensure responses is None if not provided."""
+ if responses is None:
+ return []
+ return responses
+
+ @field_validator("suggestions", mode="before")
+ @classmethod
+ def empty_suggestions_if_none(
+ cls, suggestions: Optional[Union[Tuple[SuggestionModel], List[SuggestionModel]]]
+ ) -> Optional[Union[Tuple[SuggestionModel], List[SuggestionModel]]]:
+ """Ensure suggestions is None if not provided."""
+ if suggestions is None:
+ return []
+ return suggestions

examples/webhooks/distilabel_trigger/.gitignore

@@ -0,0 +1,162 @@
+# 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/latest/usage/project/#working-with-version-control
+.pdm.toml
+.pdm-python
+.pdm-build/
+
+# 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/

examples/webhooks/distilabel_trigger/README.md

@@ -0,0 +1,31 @@
+<!--
+This example is based on the work done by Ben on this repo https://github.com/burtenshaw/distilabel_trigger
+-->
+
+
+## Running the app
+
+1. Start argilla server and argilla worker
+```bash
+pdm server start
+pdm worker
+```
+
+2. Add the `localhost.org` alias in the `/etc/hosts` file to comply with the Top Level Domain URL requirement.
+```
+##
+# Host Database
+#
+# localhost is used to configure the loopback interface
+# when the system is booting. Do not change this entry.
+##
+127.0.0.1 localhost localhost.org
+```
+
+2. Start the app
+```bash
+uvicorn webhook:server
+```
+
+## Testing the app
+Annotate some record in the argilla UI and check the logs of the app to see the webhook being triggered.

examples/webhooks/distilabel_trigger/configure_models.py

@@ -0,0 +1,49 @@
+import os
+from typing import List
+
+from distilabel.llms import InferenceEndpointsLLM
+from distilabel.steps.tasks import TextGeneration, Task, UltraFeedback
+
+LLAMA_MODEL_ID = os.environ.get(
+ "LLAMA_MODEL_ID", "meta-llama/Meta-Llama-3.1-8B-Instruct"
+)
+GEMMA_MODEL_ID = os.environ.get("GEMMA_MODEL_ID", "google/gemma-1.1-7b-it")
+ULTRAFEEDBACK_MODEL_ID = os.environ.get(
+ "ULTRAFEEDBACK_MODEL_ID", "meta-llama/Meta-Llama-3.1-70B-Instruct"
+)
+
+
+def initialize_text_generation_models() -> List["Task"]:
+ llama31 = TextGeneration(
+ name="text-generation",
+ llm=InferenceEndpointsLLM(
+ model_id=LLAMA_MODEL_ID,
+ tokenizer_id=LLAMA_MODEL_ID,
+ ),
+ )
+ llama31.load()
+
+ gemma_tiny = TextGeneration(
+ name="text-generation",
+ llm=InferenceEndpointsLLM(
+ model_id=GEMMA_MODEL_ID,
+ tokenizer_id=GEMMA_MODEL_ID,
+ ),
+ )
+ gemma_tiny.load()
+
+ return [llama31, gemma_tiny]
+
+
+def initialize_ultrafeedback():
+ ultrafeedback = UltraFeedback(
+ aspect="overall-rating",
+ llm=InferenceEndpointsLLM(
+ model_id=ULTRAFEEDBACK_MODEL_ID,
+ tokenizer_id=ULTRAFEEDBACK_MODEL_ID,
+ ),
+ )
+
+ ultrafeedback.load()
+
+ return ultrafeedback

examples/webhooks/distilabel_trigger/configure_webhook.py

@@ -0,0 +1,24 @@
+import os
+
+import argilla as rg
+from argilla._api._webhooks import WebhookModel
+from standardwebhooks.webhooks import Webhook
+
+WEBHOOK_BASE_URL = os.getenv("WEBHOOK_BASE_URL", "http://localhost.org:8000")
+
+
+def configure_webhook(client: rg.Argilla, path: str) -> Webhook:
+ # Configure the webhook
+ for wh_model in client.api.webhooks.list():
+ client.api.webhooks.delete(wh_model.id)
+
+ model = WebhookModel(
+ url=f"{WEBHOOK_BASE_URL}{path}",
+ events=["record.completed"],
+ description="Webhook for record completion",
+ )
+
+ webhook_model = client.api.webhooks.create(model)
+ webhook = Webhook(whsecret=webhook_model.secret)
+
+ return webhook