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>
64 lines
2.7 KiB
Python
64 lines
2.7 KiB
Python
import uuid
|
|
|
|
from django.db import models
|
|
|
|
|
|
class LessonChunk(models.Model):
|
|
"""
|
|
یک تکه‌ی درسیِ خلاصه‌شده که هم در همین جدول (منبعِ حقیقت) و هم به‌صورتِ
|
|
یک نقطه در Qdrant (فقط index، قابلِ بازسازی) ذخیره می‌شه.
|
|
|
|
برداشتِ پاک‌سازی‌شده از subjects.LessonChunk مخزنِ Rag_backend، با این
|
|
تفاوت‌ها طبق معماریِ این پروژه:
|
|
- هیچ FK بین‌اپی نداره؛ lesson_id فقط یک ارجاعِ سبک به content.Lesson است
|
|
(دقیقاً مثل Conversation.lesson_id در ai_tutor).
|
|
- subject/grade به‌صورتِ رشته/عدد نگه‌داری می‌شن چون مدلِ content ما مدلِ
|
|
Subject نداره و نامِ collectionِ تیمِ دیگه بر پایه‌ی همین رشته‌هاست.
|
|
- embedding_vector هم ذخیره می‌شه تا collectionِ Qdrant بدونِ فراخوانیِ
|
|
دوباره‌ی embedding قابلِ بازسازی باشه.
|
|
"""
|
|
|
|
lesson_id = models.IntegerField(db_index=True) # ارجاع سبک به content.Lesson
|
|
grade_id = models.IntegerField(null=True, blank=True) # ارجاع سبک به content.Grade
|
|
subject = models.CharField(max_length=100)
|
|
lesson_number = models.IntegerField()
|
|
chapter = models.IntegerField(null=True, blank=True)
|
|
|
|
order = models.PositiveIntegerField()
|
|
title = models.CharField(max_length=255)
|
|
original_text = models.TextField()
|
|
summary = models.TextField()
|
|
embedding_vector = models.JSONField(null=True, blank=True)
|
|
|
|
collection = models.CharField(max_length=200, db_index=True)
|
|
qdrant_point_id = models.UUIDField(default=uuid.uuid4, editable=False)
|
|
|
|
created_at = models.DateTimeField(auto_now_add=True)
|
|
|
|
class Meta:
|
|
ordering = ['lesson_id', 'order']
|
|
constraints = [
|
|
models.UniqueConstraint(
|
|
fields=['collection', 'qdrant_point_id'],
|
|
name='uniq_lesson_chunk_qdrant_point',
|
|
),
|
|
]
|
|
indexes = [
|
|
models.Index(fields=['subject', 'lesson_number']),
|
|
]
|
|
|
|
def __str__(self):
|
|
return f"chunk-lesson{self.lesson_id}-{self.order} ({self.subject})"
|
|
|
|
|
|
class LessonChunkImage(models.Model):
|
|
"""تصویرِ پیوست به یک chunk (برای محتوای چندوجهیِ آینده)."""
|
|
|
|
chunk = models.ForeignKey(LessonChunk, on_delete=models.CASCADE, related_name='images')
|
|
img_url = models.TextField()
|
|
description = models.TextField(blank=True)
|
|
created_at = models.DateTimeField(auto_now_add=True)
|
|
|
|
def __str__(self):
|
|
return f"image-chunk{self.chunk_id}"
|