Zareian
ac93e17305
Self-contained app; wired into settings/urls in the next commit. Data
stays in the parallel team's live Qdrant — nothing is copied into our DB.
apps.py
- RagConfig.
models.py
- LessonChunk: DB-of-record for one summarized lesson chunk
(original_text + summary + embedding_vector) mirrored as a single
Qdrant point; loose lesson_id/grade_id ints, no cross-app FK.
LessonChunkImage for future multimodal lessons.
migrations/0001_initial.py
- initial tables for the two models.
services/clients.py
- lazy, lru_cache'd OpenAI + Qdrant clients (Rag_backend builds them at
import time and crashes without keys). RagNotConfigured raised when a
key/lib is missing; Qdrant client uses check_compatibility=False for
the 1.19-client / 1.17-server minor version gap.
services/config.py
- rag_is_configured(), collection-name template, grade-title resolution
(RAG_GRADE_TITLE_OVERRIDES -> content.Grade.title), retrieval top-k.
services/known_collections.py
- exact live Qdrant catalog: 6 collection names, math chapter-number ->
exact "فصل N: ..." string tables per (subject, grade), and the
علوم/اجتماعی lesson-number -> title maps. filter_key_for_subject()
picks `chapter` for math, `lesson_number` otherwise;
resolve_math_chapter() maps a plain chapter number (Persian or Latin
digits) to the stored string.
services/embedding.py
- embed_text() pinned to OPENAI_EMBEDDING_MODEL (text-embedding-3-small,
1536d) so vectors match the other team's existing collections.
services/chunking.py
- split_text_into_chunks(), summarize_chunk() (gpt-4o-mini, JSON out);
plain exceptions instead of ninja HttpError.
services/qdrant_store.py
- ensure_collection(), upsert_points(), search(): the lesson filter
matches the value both as str and native, since Qdrant stores
lesson_number as int and chapter as string.
services/retrieval.py
- resolve_target() -> (collection, filter_key, filter_value), reused by
the cache key and debug block.
- retrieve_context() -> (chunks, meta): embed -> Qdrant search scoped to
one lesson/chapter -> top-k. Math payloads (no `summary`) fall back to
generalSolution/problem/solution; a 404 collection returns empty.
services/generation.py
- generate_answer() and stream_answer() (token iterator for SSE);
context-grounded Persian prompt that explains from retrieved text
rather than refusing.
services/pdf.py
- textbook PDF -> page images -> gpt-4o vision problem-type extraction
(adapted from Rag_backend mathapp); returns dicts, no on-disk JSON.
pymupdf/pdf2image optional — missing libs raise RagNotConfigured.
services/ingest.py
- ingest_text() / ingest_pdf(): chunk -> summarize -> embed -> persist
LessonChunk + upsert Qdrant, in one transaction.
services/answer_cache.py
- short-TTL cache of the final answer keyed by
sha1(collection | filter_value | normalized-question).
services/tutor.py
- thin answer_question() (retrieve -> generate) for direct callers.
serializers.py, urls.py, views.py
- POST /api/rag/ingest/text, POST /api/rag/ingest/pdf (HasInternalServiceKey,
throttle scope rag_ingest), GET /api/rag/chunks review list.
RagProviderUnavailable -> clean 503.
admin.py
- LessonChunk admin with an inline for its images.
management/commands/rag_catalog.py
- read-only live Qdrant listing (--values, --json); never writes.
tests.py
- mocked-client tests: ask-with-retrieval, ingest, SSE stream, answer
cache, and rag_is_configured() gating.
Co-Authored-By: Claude Sonnet 5 <noreply@anthropic.com>
45 lines
1.8 KiB
Python
45 lines
1.8 KiB
Python
"""
|
|
هم‌خوانیِ نامِ collection و کلیدِ فیلترِ Qdrant با دادهٔ موجودِ تیمِ دیگر.
|
|
|
|
در Rag_backend نامِ collection این‌طور ساخته می‌شه:
|
|
f"{subject.name} {subject.grade.title}".lower()
|
|
و فیلترِ درس با کلیدِ payloadِ "lesson_number" (برای درس‌های متنی) یا
|
|
"chapter" (برای ریاضی) انجام می‌شه. اینجا هر دو از settings قابلِ تنظیم‌ان
|
|
چون اسمِ دقیقِ گرید حساسه (کاربر قبلاً با اسمِ نادرست به مشکل خورده بود).
|
|
"""
|
|
from django.conf import settings
|
|
|
|
|
|
def rag_is_configured() -> bool:
|
|
return bool(
|
|
settings.OPENAI_API_KEY
|
|
and settings.QDRANT_API_KEY
|
|
and not settings.RAG_FORCE_MOCK
|
|
)
|
|
|
|
|
|
def resolve_grade_title(grade_id, fallback: str = '') -> str:
|
|
"""gradeId → عنوانِ گرید همان‌طور که در نامِ collectionِ تیمِ دیگه اومده."""
|
|
overrides = getattr(settings, 'RAG_GRADE_TITLE_OVERRIDES', {}) or {}
|
|
if grade_id in overrides:
|
|
return str(overrides[grade_id])
|
|
if grade_id is not None:
|
|
try:
|
|
from content.models import Grade
|
|
|
|
grade = Grade.objects.filter(pk=grade_id).only('title').first()
|
|
if grade is not None:
|
|
return grade.title
|
|
except Exception:
|
|
pass
|
|
return fallback
|
|
|
|
|
|
def build_collection_name(subject: str, grade_title: str) -> str:
|
|
template = getattr(settings, 'RAG_COLLECTION_NAME_TEMPLATE', '{subject} {grade}')
|
|
return template.format(subject=(subject or '').strip(), grade=(grade_title or '').strip()).lower()
|
|
|
|
|
|
def retrieval_top_k() -> int:
|
|
return int(getattr(settings, 'RAG_RETRIEVAL_TOP_K', 4))
|