mirror of
https://github.com/tiennm99/DocsGPT.git
synced 2026-10-03 18:46:54 +00:00
Alex
574f96341e
The backend import package is now docsgpt, the name it will carry on PyPI; application was far too generic to install into anyone's site-packages. git mv plus a mechanical rewrite of every import, dotted string and path reference: 734 Python files, the compose files, Dockerfile, workflows, docs, setup scripts, devcontainer, k8s manifests, vscode config, pytest and coverage config, .gitignore. Behaviour is unchanged. Kept for one release: - A top-level application package whose meta-path finder resolves application.x.y to the already-imported docsgpt.x.y object, so old imports and entry points (celery -A application.app.celery, uvicorn application.asgi:asgi_app) keep working with a FutureWarning. - Celery registers every application.* task name as an alias of its docsgpt.* task on start-up, so messages queued by the previous release still run. The redbeat key prefix moves to redbeat:docsgpt:v2: so schedule entries the previous release wrote are left unread instead of firing twice. The backend image builds from the repository root (docker build -f docsgpt/Dockerfile .) so it can ship the alias package; a root .dockerignore allow-lists docsgpt/ and application/ and keeps caches, local data, .env files, the sample index files and the Dockerfile out. Compose and the image workflows point at the new context.
59 lines
2.0 KiB
Python
59 lines
2.0 KiB
Python
"""An empty retrieval must be visible to both the model and the client.
|
|
|
|
Two independent suppressions made "searched your sources, found nothing"
|
|
indistinguishable from "no source was attached": the ``source`` SSE event was
|
|
skipped when the list was empty, and the prompt said nothing at all. Together
|
|
they let a retrieval failure surface as a confident, ungrounded answer.
|
|
"""
|
|
|
|
from __future__ import annotations
|
|
|
|
from unittest.mock import MagicMock, patch
|
|
|
|
import pytest
|
|
|
|
from docsgpt.agents.classic_agent import ClassicAgent
|
|
|
|
|
|
def _agent(**kwargs):
|
|
with patch("docsgpt.llm.llm_creator.LLMCreator.create_llm"), patch(
|
|
"docsgpt.llm.handlers.handler_creator.LLMHandlerCreator.create_handler"
|
|
):
|
|
return ClassicAgent(
|
|
endpoint="stream",
|
|
llm_name="openai",
|
|
model_id="gpt-4o",
|
|
api_key="k",
|
|
prompt="SYSTEM",
|
|
decoded_token={"sub": "u"},
|
|
tool_executor=MagicMock(),
|
|
**kwargs,
|
|
)
|
|
|
|
|
|
@pytest.mark.unit
|
|
class TestEmptyRetrievalNote:
|
|
def test_searched_sources_with_no_hits_tells_the_model(self):
|
|
agent = _agent(retrieved_docs=[], sources_were_searched=True)
|
|
user = agent._build_messages("SYSTEM", "What is the rebate?")[-1]["content"]
|
|
|
|
assert "were searched" in user
|
|
assert user.rstrip().endswith("What is the rebate?")
|
|
|
|
def test_no_sources_attached_stays_silent(self):
|
|
"""Nothing was searched, so there is nothing to report."""
|
|
agent = _agent(retrieved_docs=[], sources_were_searched=False)
|
|
user = agent._build_messages("SYSTEM", "What is the rebate?")[-1]["content"]
|
|
|
|
assert user == "What is the rebate?"
|
|
|
|
def test_documents_found_suppresses_the_note(self):
|
|
agent = _agent(
|
|
retrieved_docs=[{"filename": "a.pdf", "text": "the rebate is 4250"}],
|
|
sources_were_searched=True,
|
|
)
|
|
user = agent._build_messages("SYSTEM", "What is the rebate?")[-1]["content"]
|
|
|
|
assert "were searched" not in user
|
|
assert "<documents>" in user
|