mirror of
https://github.com/paperless-ngx/paperless-ngx.git
synced 2026-11-01 04:25:44 +00:00
stumpylogandClaude Sonnet 5.5
7fdeb173f5
Document chat searched the vector store twice per question: once explicitly to build the reference list, and again inside RetrieverQueryEngine.query(), which retrieves before synthesizing. That meant two query-embedding calls and two full vector searches each time. The engine added nothing beyond the retriever call (no node postprocessors are configured), so drop it and synthesize directly from the nodes already retrieved. The streaming response is unchanged. Co-Authored-By: Claude Sonnet 5.5 <noreply@anthropic.com> Claude-Session: https://claude.ai/code/session_01SRX1rCtSx62vSDaiFuBFCM
55 lines
1.8 KiB
Python
55 lines
1.8 KiB
Python
from __future__ import annotations
|
|
|
|
from typing import TYPE_CHECKING
|
|
|
|
import pytest
|
|
|
|
from documents.models import Document
|
|
from paperless_ai.chat import stream_chat_with_documents
|
|
from paperless_testing.factories import DocumentFactory
|
|
|
|
if TYPE_CHECKING:
|
|
import pytest_mock
|
|
|
|
|
|
@pytest.mark.django_db
|
|
class TestChatSingleRetrieve:
|
|
def test_question_retrieves_once_and_synthesizes_those_nodes(
|
|
self,
|
|
mocker: pytest_mock.MockerFixture,
|
|
) -> None:
|
|
"""
|
|
GIVEN a document with indexed content
|
|
WHEN a chat question is streamed
|
|
THEN the vector store is searched exactly once
|
|
AND the answer is synthesized from the nodes that search returned
|
|
"""
|
|
document = DocumentFactory.create(title="Test Document", content="ignored")
|
|
top_nodes = [
|
|
mocker.MagicMock(
|
|
metadata={"document_id": str(document.pk), "title": "Test Document"},
|
|
),
|
|
]
|
|
retriever = mocker.MagicMock()
|
|
retriever.retrieve.return_value = top_nodes
|
|
mocker.patch("paperless_ai.chat.AIClient")
|
|
mocker.patch("paperless_ai.chat.load_or_build_index")
|
|
mocker.patch(
|
|
"llama_index.core.retrievers.VectorIndexRetriever",
|
|
return_value=retriever,
|
|
)
|
|
synthesizer = mocker.patch(
|
|
"llama_index.core.response_synthesizers.get_response_synthesizer",
|
|
).return_value
|
|
synthesizer.synthesize.return_value.response_gen = iter(["chunk"])
|
|
|
|
list(
|
|
stream_chat_with_documents(
|
|
"What is this?",
|
|
Document.objects.filter(pk=document.pk),
|
|
),
|
|
)
|
|
|
|
retriever.retrieve.assert_called_once_with("What is this?")
|
|
synthesizer.synthesize.assert_called_once_with("What is this?", top_nodes)
|