new app — cleaned-up RAG pipeline (Qdrant retrieval + GPT), ported from Rag_backend

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>

rag/services/generation.py

@@ -0,0 +1,98 @@
+"""
+مرحله‌ی generation: پرسش + context بازیابی‌شده → پاسخِ فارسی + چند پیشنهادِ
+ادامه.
+
+اگه context خالی باشه، مدل به‌عنوانِ معلمِ عمومی جواب می‌ده (بدونِ ادعای
+استناد به کتاب) — این حالت وقتی پیش می‌آد که subject/lessonNumber ارسال
+نشده یا اون درس هنوز در Qdrant نیست.
+"""
+import logging
+from collections.abc import Iterator
+
+from django.conf import settings
+
+from . import clients
+
+logger = logging.getLogger(__name__)
+
+_DEFAULT_FOLLOW_UPS = ['یک مثال دیگه بزن', 'بیشتر توضیح بده']
+
+_SYSTEM = 'تو یک معلمِ فارسی‌زبانِ دبستانی هستی و پاسخ‌ها را روشن، ساده و کوتاه می‌دهی.'
+
+
+def _prompt_with_context(question: str, contexts: list[str]) -> str:
+    joined = '\n\n---\n\n'.join(contexts)
+    return f"""
+    تو معلمِ دبستانی هستی. با تکیه بر «متنِ درس» زیر و با زبانِ خودت، به سوالِ
+    دانش‌آموز پاسخِ روشن و ساده بده. لازم نیست پاسخ عیناً در متن باشد؛ می‌توانی
+    از اطلاعاتِ متن نتیجه‌گیری و توضیح بدهی.
+    فقط اگر متنِ درس آشکارا درباره‌ی موضوعِ دیگری‌ست و هیچ ربطی به سوال ندارد،
+    بنویس: «این موضوع در این درس پوشش داده نشده است.»
+
+    متنِ درس:
+    {joined}
+
+    سوالِ دانش‌آموز: {question}
+    """
+
+
+def _prompt_without_context(question: str) -> str:
+    return f"""
+    به این سوالِ یک دانش‌آموزِ دبستانی به فارسی، ساده و کوتاه پاسخ بده.
+
+    سوال: {question}
+    """
+
+
+def generate_answer(question: str, context_chunks: list[dict] | None) -> tuple[str, list[str]]:
+    """
+    context_chunks: خروجیِ retrieve_context ([{title, summary, score}, ...]) یا None/[].
+    خروجی: (answer, follow_ups)
+    """
+    contexts = [c['summary'] for c in (context_chunks or []) if c.get('summary')]
+    prompt = _prompt_with_context(question, contexts) if contexts else _prompt_without_context(question)
+
+    client = clients.get_openai_client()
+    completion = client.chat.completions.create(
+        model=settings.OPENAI_CHAT_MODEL,
+        messages=[
+            {'role': 'system', 'content': _SYSTEM},
+            {'role': 'user', 'content': prompt},
+        ],
+        temperature=0.3,
+    )
+    answer = (completion.choices[0].message.content or '').strip()
+    if not answer:
+        answer = 'متأسفم، الان نتونستم پاسخِ مناسبی بسازم. لطفاً دوباره بپرس.'
+    return answer, list(_DEFAULT_FOLLOW_UPS)
+
+
+def stream_answer(question: str, context_chunks: list[dict] | None) -> Iterator[str]:
+    """
+    همون generate_answer ولی توکن‌به‌توکن (برای SSE). فقط قطعه‌های متنِ پاسخ
+    را yield می‌کند؛ follow_upها ثابت‌اند (_DEFAULT_FOLLOW_UPS) و caller خودش
+    اضافه‌شان می‌کند.
+    """
+    contexts = [c['summary'] for c in (context_chunks or []) if c.get('summary')]
+    prompt = _prompt_with_context(question, contexts) if contexts else _prompt_without_context(question)
+
+    client = clients.get_openai_client()
+    stream = client.chat.completions.create(
+        model=settings.OPENAI_CHAT_MODEL,
+        messages=[
+            {'role': 'system', 'content': _SYSTEM},
+            {'role': 'user', 'content': prompt},
+        ],
+        temperature=0.3,
+        stream=True,
+    )
+    for event in stream:
+        if not event.choices:
+            continue
+        delta = event.choices[0].delta.content or ''
+        if delta:
+            yield delta
+
+
+def default_follow_ups() -> list[str]:
+    return list(_DEFAULT_FOLLOW_UPS)