Zareian
52d9694583
Two bugs made self-ingested content useless, both silently: - _payload wrote `chapter_number` (int) while math retrieval filters on `chapter` (the full "فصل ۲: کسر" string), so anything we ingest could never match a search — no error, just permanently invisible content. - ingest_pdf flattened the vision extraction into one text blob and threw away type/keywords/generalSolution/problem/solution. LessonChunk is the source of truth, so rebuilding meant paying for vision again — and the problem/solution pairs are the input for building lesson questions. LessonChunk now stores those fields and _payload emits them under the same keys the other team's collections use, so ours and theirs stay one shape. Also fixes a regression from the whitenoise commit: the Manifest storage variant raises when staticfiles.json is absent, which broke all 23 admin rendering tests (Django forces DEBUG=False in tests, so USE_FINDERS is off) and would have taken the admin panel down entirely the day DEBUG=0 ships without a collectstatic run. Co-Authored-By: Claude Opus 5 <noreply@anthropic.com>
358 lines
16 KiB
Python
358 lines
16 KiB
Python
"""
|
||
تست‌های لایه‌ی RAG. همه‌ی فراخوانی‌های شبکه (OpenAI/GapGPT و Qdrant) mock
|
||
می‌شن؛ این تست‌ها بدونِ کلید و بدونِ اینترنت هم سبز می‌مونن.
|
||
"""
|
||
from types import SimpleNamespace
|
||
from unittest.mock import patch
|
||
|
||
from django.core.cache import cache
|
||
from django.test import TestCase, override_settings
|
||
from rest_framework.test import APIClient
|
||
|
||
from accounts.authentication import issue_access_token
|
||
from accounts.models import User
|
||
|
||
from .models import LessonChunk
|
||
from .services.clients import reset_clients_cache
|
||
|
||
RAG_ON = dict(
|
||
OPENAI_API_KEY='test-openai',
|
||
QDRANT_API_KEY='test-qdrant',
|
||
RAG_FORCE_MOCK=False,
|
||
RAG_GRADE_TITLE_OVERRIDES={1: 'ششم دبستان'},
|
||
)
|
||
|
||
|
||
def _fake_openai(embedding=None, chat_reply='پاسخِ آزمایشیِ مدل.'):
|
||
dim = 1536
|
||
vec = embedding or [0.01] * dim
|
||
|
||
class _Embeddings:
|
||
def create(self, **kwargs):
|
||
return SimpleNamespace(data=[SimpleNamespace(embedding=list(vec))])
|
||
|
||
class _Completions:
|
||
def create(self, **kwargs):
|
||
return SimpleNamespace(
|
||
choices=[SimpleNamespace(message=SimpleNamespace(content=chat_reply))]
|
||
)
|
||
|
||
return SimpleNamespace(
|
||
embeddings=_Embeddings(),
|
||
chat=SimpleNamespace(completions=_Completions()),
|
||
)
|
||
|
||
|
||
class _FakeQdrant:
|
||
def __init__(self, points=None):
|
||
self._collections = set()
|
||
self._points = points or []
|
||
self.upserted = []
|
||
|
||
def get_collections(self):
|
||
return SimpleNamespace(collections=[SimpleNamespace(name=n) for n in self._collections])
|
||
|
||
def create_collection(self, collection_name, **kwargs):
|
||
self._collections.add(collection_name)
|
||
|
||
def upsert(self, collection_name, points, **kwargs):
|
||
self._collections.add(collection_name)
|
||
self.upserted.extend(points)
|
||
|
||
def query_points(self, collection_name, query, limit=4, query_filter=None):
|
||
pts = [SimpleNamespace(score=0.9, payload=p) for p in self._points][:limit]
|
||
return SimpleNamespace(points=pts)
|
||
|
||
|
||
@override_settings(**RAG_ON)
|
||
class AskAIRagPathTests(TestCase):
|
||
def setUp(self):
|
||
cache.clear()
|
||
reset_clients_cache()
|
||
self.client = APIClient()
|
||
self.user = User.objects.create(device_id='dev-rag-1', is_guest=True, name='')
|
||
self.token = issue_access_token(self.user.id)
|
||
|
||
def _ask(self, body):
|
||
return self.client.post(
|
||
'/api/ai/ask', body, format='json',
|
||
HTTP_AUTHORIZATION=f'Bearer {self.token}',
|
||
)
|
||
|
||
def test_ask_with_retrieval_returns_answer_and_used_chunks(self):
|
||
qdrant = _FakeQdrant(points=[
|
||
{'summary': 'چرخه‌ی آب شاملِ تبخیر، تراکم و بارش است.', 'lesson_title': 'آب', 'lesson_number': 3},
|
||
{'summary': 'خورشید آب را گرم می‌کند و بخار می‌شود.', 'lesson_title': 'آب', 'lesson_number': 3},
|
||
])
|
||
with patch('rag.services.clients.get_openai_client', return_value=_fake_openai(chat_reply='آب تبخیر می‌شود.')), \
|
||
patch('rag.services.clients.get_qdrant_client', return_value=qdrant):
|
||
resp = self._ask({
|
||
'userQuestion': 'چرخه‌ی آب چیست؟',
|
||
'gradeId': 1,
|
||
'subject': 'علوم تجربی',
|
||
'lessonNumber': 3,
|
||
})
|
||
self.assertEqual(resp.status_code, 200, resp.content)
|
||
self.assertEqual(resp.data['answer'], 'آب تبخیر می‌شود.')
|
||
self.assertEqual(len(resp.data['usedChunks']), 2)
|
||
self.assertEqual(resp.data['usedChunks'][0]['title'], 'آب')
|
||
|
||
def test_ask_without_subject_skips_retrieval_but_still_answers(self):
|
||
with patch('rag.services.clients.get_openai_client', return_value=_fake_openai(chat_reply='پاسخِ عمومی.')), \
|
||
patch('rag.services.clients.get_qdrant_client', return_value=_FakeQdrant()):
|
||
resp = self._ask({'userQuestion': 'یک سوالِ کلی'})
|
||
self.assertEqual(resp.status_code, 200, resp.content)
|
||
self.assertEqual(resp.data['answer'], 'پاسخِ عمومی.')
|
||
self.assertEqual(resp.data['usedChunks'], [])
|
||
|
||
def test_provider_failure_becomes_503_and_releases_slot(self):
|
||
from ai_tutor.models import Conversation, Message
|
||
|
||
def boom(*a, **k):
|
||
raise ConnectionError('qdrant down')
|
||
|
||
with patch('rag.services.clients.get_openai_client', return_value=_fake_openai()), \
|
||
patch('rag.services.retrieval.search', side_effect=boom):
|
||
resp = self._ask({
|
||
'userQuestion': 'سوال', 'gradeId': 1, 'subject': 'علوم تجربی', 'lessonNumber': 3,
|
||
})
|
||
self.assertEqual(resp.status_code, 503)
|
||
self.assertEqual(Conversation.objects.filter(user_id=self.user.id).count(), 0)
|
||
self.assertEqual(Message.objects.filter(conversation__user_id=self.user.id).count(), 0)
|
||
|
||
|
||
@override_settings(**RAG_ON)
|
||
class IngestTextTests(TestCase):
|
||
def setUp(self):
|
||
cache.clear()
|
||
reset_clients_cache()
|
||
self.client = APIClient()
|
||
|
||
def test_ingest_text_creates_chunks(self):
|
||
qdrant = _FakeQdrant()
|
||
reply = '{"summary": "خلاصه‌ی این تکه."}'
|
||
with patch('rag.services.clients.get_openai_client', return_value=_fake_openai(chat_reply=reply)), \
|
||
patch('rag.services.clients.get_qdrant_client', return_value=qdrant):
|
||
resp = self.client.post(
|
||
'/api/rag/ingest/text',
|
||
{
|
||
'lessonId': 12, 'gradeId': 1, 'subject': 'علوم تجربی',
|
||
'lessonNumber': 3, 'title': 'آب',
|
||
'text': 'الف' * 900,
|
||
},
|
||
format='json',
|
||
HTTP_X_INTERNAL_KEY='dev-internal-service-key-change-me',
|
||
)
|
||
self.assertEqual(resp.status_code, 200, resp.content)
|
||
self.assertGreater(resp.data['chunksCreated'], 0)
|
||
self.assertEqual(LessonChunk.objects.filter(lesson_id=12).count(), resp.data['chunksCreated'])
|
||
self.assertTrue(qdrant.upserted)
|
||
self.assertEqual(resp.data['collection'], 'علوم تجربی ششم دبستان'.lower())
|
||
|
||
def test_ingest_requires_internal_key(self):
|
||
resp = self.client.post(
|
||
'/api/rag/ingest/text',
|
||
{'lessonId': 1, 'subject': 'علوم تجربی', 'lessonNumber': 1, 'text': 'x'},
|
||
format='json',
|
||
)
|
||
# بدونِ X-Internal-Key و بدونِ توکن: DRF بسته به authenticator یا
|
||
# 401 می‌ده یا 403 — هر دو یعنی «رد شد».
|
||
self.assertIn(resp.status_code, (401, 403))
|
||
|
||
|
||
class IngestPayloadContractTests(TestCase):
|
||
"""
|
||
قراردادِ بینِ چیزی که ingest می‌نویسه و چیزی که retrieval دنبالش می‌گرده.
|
||
|
||
این تست‌ها عمداً ریزبینانه‌ان چون شکستنِ این قرارداد هیچ خطایی تولید نمی‌کنه:
|
||
نقطه‌ها سالم در Qdrant می‌شینن، ولی فیلترِ جستجو هیچ‌وقت بهشون نمی‌خوره و
|
||
محتوا بی‌صدا نامرئی می‌مونه.
|
||
"""
|
||
|
||
def test_math_payload_key_matches_the_key_retrieval_filters_on(self):
|
||
from rag.services.ingest import _payload
|
||
from rag.services.known_collections import filter_key_for_subject
|
||
|
||
chunk = LessonChunk(
|
||
lesson_id=1, grade_id=1, subject='ریاضی', lesson_number=2, chapter=2,
|
||
chapter_title='فصل ۲: کسر', order=1, title='کسر',
|
||
original_text='x', summary='x', collection='ریاضی ششم',
|
||
)
|
||
payload = _payload(chunk)
|
||
|
||
# کلیدی که ریاضی روش فیلتر می‌شه باید دقیقاً در payload باشه، با همون مقدار.
|
||
self.assertEqual(filter_key_for_subject('ریاضی'), 'chapter')
|
||
self.assertIn('chapter', payload)
|
||
self.assertEqual(payload['chapter'], 'فصل ۲: کسر')
|
||
|
||
def test_text_subject_payload_keeps_lesson_number_filter(self):
|
||
from rag.services.ingest import _payload
|
||
from rag.services.known_collections import filter_key_for_subject
|
||
|
||
chunk = LessonChunk(
|
||
lesson_id=1, grade_id=1, subject='علوم تجربی', lesson_number=3, chapter=None,
|
||
order=1, title='آب', original_text='x', summary='x', collection='علوم تجربی سوم',
|
||
)
|
||
payload = _payload(chunk)
|
||
|
||
self.assertEqual(filter_key_for_subject('علوم تجربی'), 'lesson_number')
|
||
self.assertEqual(payload['lesson_number'], 3)
|
||
# فصل نداره، پس نباید کلیدِ خالیِ chapter بنویسه.
|
||
self.assertNotIn('chapter', payload)
|
||
|
||
def test_structured_fields_survive_into_payload(self):
|
||
"""
|
||
استخراجِ vision گرونه؛ اگه ساختارش فقط به متنِ صاف تبدیل بشه، برای
|
||
ساختِ سؤال‌های مسیرِ درس باید دوباره همون هزینه داده بشه.
|
||
"""
|
||
from rag.services.ingest import _payload
|
||
|
||
chunk = LessonChunk(
|
||
lesson_id=1, grade_id=1, subject='ریاضی', lesson_number=2, chapter=2,
|
||
chapter_title='فصل ۲: کسر', grade_title='ششم دبستان',
|
||
problem_type='مقایسه کسرها', keywords=['کسر', 'مقایسه'],
|
||
general_solution='مخرج مشترک بگیرید.',
|
||
problem='کدام کسر بزرگ‌تر است؟', solution='۳/۴ بزرگ‌تر است.',
|
||
order=1, title='کسر', original_text='x', summary='x', collection='ریاضی ششم',
|
||
)
|
||
payload = _payload(chunk)
|
||
|
||
self.assertEqual(payload['type'], 'مقایسه کسرها')
|
||
self.assertEqual(payload['keywords'], ['کسر', 'مقایسه'])
|
||
self.assertEqual(payload['generalSolution'], 'مخرج مشترک بگیرید.')
|
||
self.assertEqual(payload['problem'], 'کدام کسر بزرگ‌تر است؟')
|
||
self.assertEqual(payload['solution'], '۳/۴ بزرگ‌تر است.')
|
||
self.assertEqual(payload['grade'], 'ششم دبستان')
|
||
|
||
def test_payload_text_reads_what_ingest_writes(self):
|
||
"""پلِ نهایی: متنی که retrieval از payload درمی‌آره نباید خالی باشه."""
|
||
from rag.services.ingest import _payload
|
||
from rag.services.retrieval import _payload_text
|
||
|
||
chunk = LessonChunk(
|
||
lesson_id=1, grade_id=1, subject='ریاضی', lesson_number=2, chapter=2,
|
||
chapter_title='فصل ۲: کسر', general_solution='مخرج مشترک بگیرید.',
|
||
order=1, title='کسر', original_text='متنِ اصلی', summary='خلاصه‌ی تکه',
|
||
collection='ریاضی ششم',
|
||
)
|
||
self.assertTrue(_payload_text(_payload(chunk)))
|
||
|
||
|
||
class RagConfigTests(TestCase):
|
||
def test_rag_disabled_without_keys(self):
|
||
from rag.services.config import rag_is_configured
|
||
|
||
with override_settings(OPENAI_API_KEY='', QDRANT_API_KEY=''):
|
||
self.assertFalse(rag_is_configured())
|
||
with override_settings(OPENAI_API_KEY='a', QDRANT_API_KEY='b', RAG_FORCE_MOCK=True):
|
||
self.assertFalse(rag_is_configured())
|
||
with override_settings(OPENAI_API_KEY='a', QDRANT_API_KEY='b', RAG_FORCE_MOCK=False):
|
||
self.assertTrue(rag_is_configured())
|
||
|
||
|
||
def _parse_sse(streaming_content):
|
||
"""bytes iterator → [(event, data_str), ...]"""
|
||
raw = b''.join(streaming_content).decode('utf-8')
|
||
events = []
|
||
for block in raw.split('\n\n'):
|
||
block = block.strip()
|
||
if not block:
|
||
continue
|
||
ev, data = None, None
|
||
for line in block.splitlines():
|
||
if line.startswith('event: '):
|
||
ev = line[7:]
|
||
elif line.startswith('data: '):
|
||
data = line[6:]
|
||
events.append((ev, data))
|
||
return events
|
||
|
||
|
||
@override_settings(**RAG_ON)
|
||
class AskAIStreamTests(TestCase):
|
||
def setUp(self):
|
||
cache.clear()
|
||
reset_clients_cache()
|
||
self.client = APIClient()
|
||
self.user = User.objects.create(device_id='dev-stream-1', is_guest=True, name='')
|
||
self.token = issue_access_token(self.user.id)
|
||
|
||
def _ask_stream(self, body):
|
||
return self.client.post(
|
||
'/api/ai/ask', {**body, 'stream': True}, format='json',
|
||
HTTP_AUTHORIZATION=f'Bearer {self.token}',
|
||
)
|
||
|
||
def test_stream_emits_chunks_then_done_and_persists(self):
|
||
from ai_tutor.models import Message
|
||
|
||
chunks_out, meta = [{'title': 'کسر', 'summary': 'خلاصه‌ی کسر'}], {'collection': 'ریاضی ششم'}
|
||
with patch('rag.services.retrieval.retrieve_context', return_value=(chunks_out, meta)), \
|
||
patch('rag.services.generation.stream_answer', return_value=iter(['برای ', 'جمع ', 'کسرها...'])):
|
||
resp = self._ask_stream({
|
||
'userQuestion': 'جمع کسر؟', 'subject': 'ریاضی', 'grade': 'ششم', 'lessonNumber': 2,
|
||
})
|
||
self.assertEqual(resp.status_code, 200)
|
||
self.assertEqual(resp['content-type'], 'text/event-stream')
|
||
events = _parse_sse(resp.streaming_content)
|
||
kinds = [e for e, _ in events]
|
||
self.assertEqual(kinds.count('chunk'), 3)
|
||
self.assertEqual(kinds[-1], 'done')
|
||
import json as _json
|
||
done = _json.loads(events[-1][1])
|
||
self.assertIn('messageId', done)
|
||
self.assertEqual(done['usedChunks'][0]['title'], 'کسر')
|
||
# پیامِ کاربر و دستیار هر دو ثبت شده و کوتا مصرف شده
|
||
self.assertEqual(Message.objects.filter(conversation__user_id=self.user.id, role='assistant').count(), 1)
|
||
msg = Message.objects.get(conversation__user_id=self.user.id, role='assistant')
|
||
self.assertEqual(msg.text, 'برای جمع کسرها...')
|
||
|
||
def test_stream_provider_failure_emits_error_and_releases_slot(self):
|
||
from ai_tutor.models import Conversation, Message
|
||
|
||
def boom(*a, **k):
|
||
raise ConnectionError('provider down')
|
||
|
||
with patch('rag.services.retrieval.retrieve_context', side_effect=boom):
|
||
resp = self._ask_stream({'userQuestion': 'x', 'subject': 'ریاضی', 'grade': 'ششم', 'lessonNumber': 2})
|
||
events = _parse_sse(resp.streaming_content)
|
||
self.assertEqual(events[-1][0], 'error')
|
||
self.assertEqual(Conversation.objects.filter(user_id=self.user.id).count(), 0)
|
||
self.assertEqual(Message.objects.filter(conversation__user_id=self.user.id).count(), 0)
|
||
|
||
|
||
@override_settings(**RAG_ON, RAG_ANSWER_CACHE_TTL=300)
|
||
class AskAIAnswerCacheTests(TestCase):
|
||
def setUp(self):
|
||
cache.clear()
|
||
reset_clients_cache()
|
||
self.client = APIClient()
|
||
self.user = User.objects.create(device_id='dev-cache-1', is_guest=True, name='')
|
||
self.token = issue_access_token(self.user.id)
|
||
|
||
def _ask(self, body):
|
||
return self.client.post(
|
||
'/api/ai/ask', body, format='json', HTTP_AUTHORIZATION=f'Bearer {self.token}',
|
||
)
|
||
|
||
def test_identical_question_second_time_skips_generation_but_still_persists(self):
|
||
from ai_tutor.models import Message
|
||
|
||
qdrant = _FakeQdrant(points=[{'summary': 'خلاصه', 'lesson_title': 'کسر', 'lesson_number': 2}])
|
||
body = {'userQuestion': 'سوال یکسان', 'subject': 'ریاضی', 'grade': 'ششم', 'lessonNumber': 2}
|
||
|
||
with patch('rag.services.clients.get_openai_client', return_value=_fake_openai(chat_reply='پاسخ ۱')) as oai, \
|
||
patch('rag.services.clients.get_qdrant_client', return_value=qdrant):
|
||
r1 = self._ask(body)
|
||
calls_after_first = oai.call_count
|
||
r2 = self._ask(body)
|
||
|
||
self.assertEqual(r1.status_code, 200)
|
||
self.assertEqual(r2.status_code, 200)
|
||
self.assertEqual(r1.data['answer'], r2.data['answer'])
|
||
# درخواستِ دوم نباید کلاینتِ OpenAI رو دوباره صدا بزنه (کش)
|
||
self.assertEqual(oai.call_count, calls_after_first)
|
||
# ولی پیام و کوتا برای هر دو درخواست ثبت/مصرف شده
|
||
self.assertEqual(Message.objects.filter(conversation__user_id=self.user.id, role='user').count(), 2)
|
||
self.assertGreater(r1.data['remainingQuota'], r2.data['remainingQuota'])
|