app/jobs/summarise.py is a ModelTask beside extract: about 60 words per role
from title, company, place and the fetched page else the description (capped
at 8000 characters). The pull cascade gains a summarise stage after score that
takes only roles without a summary in the top summarise.per_agent of an
enabled agent's ungated scores, and finds nothing when summarise.enabled is
false or no model is reachable. A reply that leaves a role unanswered is
counted in the state table and the role is given up after three.
POST /api/roles/{uid}/text scrapes original_url once and stores
article_text; POST /api/roles/{uid}/summarise queues a summarise_batch for
that uid alone, deduped per role.
Co-Authored-By: Claude Fable 5.1 <noreply@anthropic.com>
40 lines
1.7 KiB
Python
40 lines
1.7 KiB
Python
"""The work roledesk queues. Importing this package registers every job, every
|
|
task in `pipeline.TASKS` and the default schedule in `pipeline.SCHEDULES`.
|
|
|
|
pull.py read every board and search and store the roles they yield
|
|
extract.py title and description into the gate columns, on Haiku
|
|
embed.py one vector per open role, for fit
|
|
score.py every open role scored for every enabled search agent
|
|
summarise.py about 60 words on each of the best roles, on Haiku
|
|
cascade.py pull → extract → embed → score → summarise, what `TASKS`
|
|
offers, the `pull` job a schedule fires, and that schedule
|
|
sources.py what a pull reads, changed by hand: boards and searches
|
|
added, switched on or off, pruned by region
|
|
"""
|
|
|
|
from __future__ import annotations
|
|
|
|
from typing import Any
|
|
|
|
from app.jobs import cascade, embed, extract, pull, score, sources, summarise
|
|
from app.jobs.pull import search_target, seed_searches
|
|
from app.jobs.score import seed_agents
|
|
|
|
#: What `JobQueue(bootstrap=...)` and `pipeline.worker --bootstrap` are given.
|
|
BOOTSTRAP = "app.jobs:bootstrap"
|
|
|
|
|
|
def bootstrap(config_path: str = "") -> tuple[Any, Any]:
|
|
"""`(config, store)` from the config file alone, for a job run in its own
|
|
process or by `python -m pipeline.worker`. Importing this module is what
|
|
fills `JOBS`, which is why the worker is handed a name rather than a queue."""
|
|
from app import config as config_mod
|
|
from app.storage import Store
|
|
|
|
config = config_mod.load(config_path or None)
|
|
return config, Store(config.database)
|
|
|
|
|
|
__all__ = ["BOOTSTRAP", "bootstrap", "cascade", "embed", "extract", "pull", "score",
|
|
"search_target", "seed_agents", "seed_searches", "sources", "summarise"]
|