مهم‌ترین خواسته‌ی سینیور این بود که بسنجیم پاسخِ AI واقعاً یاد می‌دهد یا نه.
برای سنجیدن، اول باید پاسخ‌ها قابلِ ردیابی می‌شدند.
پرامپت‌ها پایه‌آگاه شدند: تا پیش از این «معلمِ دبستانی» برای پایه نهم هاردکد
بود، هم در تولیدِ پاسخ و هم در vision — یعنی دانش‌آموزِ نهم لحنِ ابتدایی
می‌گرفت. PROMPT_VERSION حالا روی هر پیام ذخیره می‌شود.
هر پاسخ حاشیه‌نویسی می‌شود: مدل، نسخه‌ی پرامپت، پایه، collection، مقدارِ
فیلتر، تعداد chunk، توکن، تأخیر و from_cache. فیدبک reason اختیاری گرفت تا
لایک/دیسلایک بعداً قابلِ تحلیل باشد («بشه چک کرد کدوم بهتر بوده»).
ai_feedback_report --by prompt_version نسبتِ رضایت را کنارِ مصرف/هزینه
می‌گذارد. rag_eval سوال‌های واقعی را از مسیرِ واقعی می‌پرسد، با
--retrieval-only برای اجرای ارزان.
rag/services/lesson_context.py از lessonId تنها پایه و فصل را درمی‌آورد؛
normalize_grade_title هم اختلافِ «پایه نهم» در دیتابیس با «ریاضی نهم» در
نامِ collection را می‌بندد — بدونِ آن مسیرِ gradeId بی‌سروصدا خالی برمی‌گشت.
Co-Authored-By: Claude Opus 5 <noreply@anthropic.com>
نقشه‌ی فیزیکیِ کتاب‌ها (افستِ صفحه، بازه‌ی هر فصل، درس‌های داخلِ فصل از
فهرستِ خودِ کتاب) در rag/services/textbooks.py ثبت شد تا عنوانِ فصل از
کتاب بیاید نه از حدسِ مدل — رشته‌ی فصل باید دقیقاً بینِ ingest و retrieval
یکی باشد وگرنه نتیجه بی‌سروصدا خالی برمی‌گردد.
rag_ingest_book کتاب را فصل‌به‌فصل ingest می‌کند و قابلِ ازسرگیری است:
rag.IngestedPage نشانه‌ی «این صفحه پردازش شد» را نگه می‌دارد حتی وقتی
صفحه chunkی نساخته، وگرنه هر بار اجرای دوباره بابتِ صفحه‌های بی‌مسئله
دوباره پول می‌گرفت. --plan هزینه را رایگان برآورد می‌کند.
rag_import_collection نقاطِ موجودِ Qdrant را در LessonChunk می‌ریزد —
فقط می‌خواند، رایگان و idempotent، برای پایه‌هایی که تیمِ دیگر ingest
کرده بود.
Co-Authored-By: Claude Opus 5 <noreply@anthropic.com>
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>
rag/services/tutor.py
- deleted: answer_question() had no callers (AskAIView calls
retrieve_context + generate_answer directly) and carried an unused
import.
rag/services/config.py
- docstring: drop the claim that the lesson-filter key is settings-driven
(it is auto-selected per subject in known_collections.py).
.env.example
- drop the leftover note about the removed RAG_QDRANT_LESSON_FILTER_KEY.
Co-Authored-By: Claude Sonnet 5 <noreply@anthropic.com>
progress/views.py
- GuestAwareReadThrottle (same guest-by-IP pattern as the other apps);
throttle_scope='read' on UserSummaryView, StreakCalendarView,
LeaderboardView.
notifications/views.py
- GuestAwareReadThrottle + throttle_scope='read' on NotificationListView.
- list capped at NOTIFICATIONS_MAX=100 newest (Meta.ordering already
newest-first); unreadCount still counted over the full set.
notifications/tests.py
- 150 rows -> 100 returned newest-first, unreadCount = 75.
rag/views.py
- ChunkListView: explicit order_by('-id') before the existing [:200] cap.
ai_tutor/views.py
- ConversationMessagesView: return the newest 200 messages in
chronological order instead of the whole conversation.
Co-Authored-By: Claude Sonnet 5 <noreply@anthropic.com>
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>
