James BruntonandGitHub
672e81d286
# Description of Changes Adds storage in the database for full document content alongside the RAG content (and changes the service to `DocumentService` instead of `RagService`). Then adds a generic capability that should be usable by any agent (currently just used by the Question Agent) which allows the agent to pull out the full contents of the doc, chunks it into various sections that will fit in the context window, and then processes them in parallel to create an intermediate result, and then processes the intermediate result into a final answer. It will re-chunk as many times as necessary to get the content small enough for the actual answer to be analysed (I've tested on PDFs ~3500 pages long, which is well above the context limit and requires maybe 3 rounds of compression to get an answer). The new full doc analysis stuff is heavier than the RAG lookup so both remain. The agents should use RAG for targeted info and the chunked reasoner for info that requires reading the full doc.
48 lines
1.5 KiB
Python
48 lines
1.5 KiB
Python
"""Per-request progress emission, plumbed via a ContextVar so deep call stacks
|
|
can publish typed events to the streaming orchestrator endpoint without every
|
|
intermediate layer knowing about it.
|
|
|
|
Outside a streaming request no emitter is bound and ``emit_progress`` is a
|
|
no-op, so callers in agents/services can emit unconditionally.
|
|
"""
|
|
|
|
from __future__ import annotations
|
|
|
|
import asyncio
|
|
import logging
|
|
from collections.abc import Awaitable, Callable
|
|
from contextvars import ContextVar, Token
|
|
|
|
from stirling.contracts import ProgressEvent
|
|
|
|
logger = logging.getLogger(__name__)
|
|
|
|
type ProgressEmitter = Callable[[ProgressEvent], Awaitable[None]]
|
|
|
|
_emitter: ContextVar[ProgressEmitter | None] = ContextVar("stirling_progress_emitter", default=None)
|
|
|
|
|
|
def set_progress_emitter(emitter: ProgressEmitter | None) -> Token[ProgressEmitter | None]:
|
|
return _emitter.set(emitter)
|
|
|
|
|
|
def reset_progress_emitter(token: Token[ProgressEmitter | None]) -> None:
|
|
_emitter.reset(token)
|
|
|
|
|
|
async def emit_progress(event: ProgressEvent) -> None:
|
|
"""Publish ``event`` to the current request's emitter, if any.
|
|
|
|
Failures inside the emitter are logged and swallowed so progress emission
|
|
can never break the work it's reporting on.
|
|
"""
|
|
emitter = _emitter.get()
|
|
if emitter is None:
|
|
return
|
|
try:
|
|
await emitter(event)
|
|
except asyncio.CancelledError:
|
|
raise
|
|
except Exception:
|
|
logger.exception("progress emitter raised; dropping event %r", event.phase)
|