Files
hatchet/sdks/python/examples/lifespans/worker.py
Matt Kaye 2f33dd4dbd Feat: Misc. Python improvements + Streaming Improvements (#1846)
* fix: contextvars explicit copy

* feat: fix a ton of ruff errors

* fix: couple more ruff rules

* fix: ignore unhelpful rule

* fix: exception group in newer Python versions for improved handling

* fix: workflow docs

* feat: context docs

* feat: simple task counter

* feat: config for setting max tasks

* feat: graceful exit once worker exceeds max tasks

* fix: optional

* fix: docs

* fix: events docs + gen

* chore: gen

* fix: one more dangling task

* feat: add xdist in ci

* fix: CI

* fix: xdist fails me once again

* fix: fix + extend some tests

* fix: test cleanup

* fix: exception group

* fix: ugh

* feat: changelog

* Add Ruff linter callout to post

* refactor: clean up runner error handling

* feat: improved errors

* fix: lint

* feat: hacky serde impl

* fix: improve serde + formatting

* fix: logging

* fix: lint

* fix: unexpected errors

* fix: naming, ruff

* fix: rm cruft

* Fix: Attempt to fix namespacing issue in event waits (#1885)

* feat: add xdist in ci

* fix: attempt to fix namespacing issue in event waits

* fix: namespaced worker names

* fix: applied namespace to the wrong thing

* fix: rm hack

* drive by: namespacing improvement

* fix: delay

* fix: changelog

* fix: initial log work

* fix: more logging work

* fix: rm print cruft

* feat: use a queue to send logs

* fix: sentinel value to stop the loop

* fix: use the log sender everywhere

* fix: make streaming blocking, remove more thread pools

* feat: changelog

* fix: linting issues

* fix: broken test

* chore: bunch more generated stuff

* fix: changelog

* fix: one more

* fix: mypy

* chore: gen

* Feat: Streaming Improvements (#1886)

* Fix: Filter list improvements (#1899)

* fix: uuid validation

* fix: improve filter filtering

* fix: inner join

* fix: bug in workflow cached prop

* chore: bump

* fix: lint

* chore: changelog

* fix: separate filter queries

* feat: improve filter filtering

* fix: queries and the like

* feat: add xdist in ci

* feat: streaming test + gen

* feat: add index to stream event

* fix: rm langfuse dep

* fix: lf

* chore: gen

* feat: impl index for stream on context

* feat: tweak protos

* feat: extend test

* feat: send event index through queue

* feat: first pass + debug logging

* debug: fixes

* debug: more possible issues

* feat: generate new stream event protos

* feat: first pass at using an alternate exchange for replaying incoming stream events

* fix: exchange create timing

* fix: rm unused protos

* chore: gen

* feat: python cleanup

* fix: revert rabbit changes

* fix: unwind a bunch of cruft

* fix: optional index

* chore: gen python

* fix: event index nil handling

* feat: improve test

* fix: stream impl in sdk

* fix: make test faster

* chore: gen a ton more stuff

* fix: test

* fix: sorting helper

* fix: bug

* fix: one more ordering bug

* feat: add some tests for buffering logic

* feat: hangup test

* feat: test no buffering if no index sent

* fix: regular mutex

* fix: pr feedback

* fix: conflicts
2025-06-25 10:11:01 -04:00

94 lines
2.1 KiB
Python

from collections.abc import AsyncGenerator
from typing import cast
from uuid import UUID
from psycopg_pool import ConnectionPool
from pydantic import BaseModel, ConfigDict
from hatchet_sdk import Context, EmptyModel, Hatchet
hatchet = Hatchet(debug=True)
# > Use the lifespan in a task
class TaskOutput(BaseModel):
num_rows: int
external_ids: list[UUID]
lifespan_workflow = hatchet.workflow(name="LifespanWorkflow")
@lifespan_workflow.task()
def sync_lifespan_task(input: EmptyModel, ctx: Context) -> TaskOutput:
pool = cast(Lifespan, ctx.lifespan).pool
with pool.connection() as conn:
query = conn.execute("SELECT * FROM v1_lookup_table_olap LIMIT 5;")
rows = query.fetchall()
for row in rows:
print(row)
print("executed sync task with lifespan", ctx.lifespan)
return TaskOutput(
num_rows=len(rows),
external_ids=[cast(UUID, row[0]) for row in rows],
)
# !!
@lifespan_workflow.task()
async def async_lifespan_task(input: EmptyModel, ctx: Context) -> TaskOutput:
pool = cast(Lifespan, ctx.lifespan).pool
with pool.connection() as conn:
query = conn.execute("SELECT * FROM v1_lookup_table_olap LIMIT 5;")
rows = query.fetchall()
for row in rows:
print(row)
print("executed async task with lifespan", ctx.lifespan)
return TaskOutput(
num_rows=len(rows),
external_ids=[cast(UUID, row[0]) for row in rows],
)
# > Define a lifespan
class Lifespan(BaseModel):
model_config = ConfigDict(arbitrary_types_allowed=True)
foo: str
pool: ConnectionPool
async def lifespan() -> AsyncGenerator[Lifespan, None]:
print("Running lifespan!")
with ConnectionPool("postgres://hatchet:hatchet@localhost:5431/hatchet") as pool:
yield Lifespan(
foo="bar",
pool=pool,
)
print("Cleaning up lifespan!")
worker = hatchet.worker(
"test-worker", slots=1, workflows=[lifespan_workflow], lifespan=lifespan
)
# !!
def main() -> None:
worker.start()
if __name__ == "__main__":
main()