6a62a43d61
Generation Page (complete rebuild): - Full production-parity exam generation wizard with 4 IELTS modules - Reading: AI passage gen, 5 exercise types (MCQ, Fill, Write, T/F, Match) - Listening: 4 section types, AI context gen, TTS audio gen (ElevenLabs) - Writing: Task 1/2, AI instruction gen, word limits, marks - Speaking: 3 parts, AI script gen, avatar video gen (7 avatars) - Per-module config: timer, CEFR difficulty, access, approval, rubrics - Exam submission workflow (draft/published) Exam Structures: - New encoach.exam.structure model + CRUD controller - ExamStructuresPage wired to real API AI Module (encoach_ai): - OpenAI service, ElevenLabs TTS, AWS Polly, ELAI avatars - AI settings model with Odoo config parameters - 7 generation endpoints (passage, exercises, instructions, scripts, context) Vector Module (encoach_vector): - pgvector integration for RAG-based content search - Embedding service with sentence-transformers Exam Session Fixes: - Fixed ExamSession.tsx field mapping (question_type→type, exam_title→title) - Fixed submit payload to include attempt_id and answers - Fixed normalizeType to handle null/undefined Tested: 12/12 API tests passed, browser-verified with real OpenAI calls Made-with: Cursor
128 lines
3.6 KiB
Python
128 lines
3.6 KiB
Python
"""Indexer — batch-indexes existing Odoo records into the vector store."""
|
|
|
|
import logging
|
|
|
|
_logger = logging.getLogger(__name__)
|
|
|
|
MODEL_CONFIG = [
|
|
{
|
|
'model': 'op.course',
|
|
'content_type': 'course',
|
|
'text_field': 'name',
|
|
'description_field': 'description',
|
|
'metadata_fields': [],
|
|
},
|
|
{
|
|
'model': 'encoach.resource',
|
|
'content_type': 'resource',
|
|
'text_field': 'name',
|
|
'description_field': 'content',
|
|
'metadata_fields': ['type', 'cefr_level', 'difficulty'],
|
|
},
|
|
{
|
|
'model': 'encoach.question',
|
|
'content_type': 'question',
|
|
'text_field': 'name',
|
|
'description_field': None,
|
|
'metadata_fields': ['question_type', 'difficulty', 'skill'],
|
|
},
|
|
{
|
|
'model': 'encoach.course.module',
|
|
'content_type': 'module',
|
|
'text_field': 'name',
|
|
'description_field': 'description',
|
|
'metadata_fields': ['skill'],
|
|
},
|
|
{
|
|
'model': 'encoach.ai.generation.log',
|
|
'content_type': 'generation_log',
|
|
'text_field': 'brief',
|
|
'description_field': 'generated_content',
|
|
'metadata_fields': ['course_type', 'status'],
|
|
},
|
|
]
|
|
|
|
|
|
def _get_text(record, config):
|
|
"""Extract indexable text from a record."""
|
|
parts = []
|
|
text_field = config.get('text_field', 'name')
|
|
if hasattr(record, text_field):
|
|
val = getattr(record, text_field)
|
|
if val:
|
|
parts.append(str(val))
|
|
|
|
desc_field = config.get('description_field')
|
|
if desc_field and hasattr(record, desc_field):
|
|
val = getattr(record, desc_field)
|
|
if val:
|
|
parts.append(str(val)[:2000])
|
|
|
|
return ' '.join(parts).strip()
|
|
|
|
|
|
def _get_metadata(record, config):
|
|
"""Extract metadata dict from a record."""
|
|
meta = {}
|
|
for f in config.get('metadata_fields', []):
|
|
if hasattr(record, f):
|
|
val = getattr(record, f)
|
|
if val:
|
|
meta[f] = str(val) if not isinstance(val, (int, float, bool)) else val
|
|
return meta
|
|
|
|
|
|
def index_model(env, config, batch_size=100):
|
|
"""Index all records of a single model."""
|
|
model_name = config['model']
|
|
Model = env.get(model_name)
|
|
if Model is None:
|
|
_logger.warning("Model %s not found, skipping", model_name)
|
|
return 0
|
|
|
|
Model = Model.sudo()
|
|
|
|
from .embedding_service import EmbeddingService
|
|
svc = EmbeddingService(env)
|
|
|
|
total = Model.search_count([])
|
|
indexed = 0
|
|
offset = 0
|
|
|
|
while offset < total:
|
|
records = Model.search([], limit=batch_size, offset=offset, order='id')
|
|
batch_data = []
|
|
for rec in records:
|
|
text = _get_text(rec, config)
|
|
if text:
|
|
batch_data.append({
|
|
'id': rec.id,
|
|
'text': text,
|
|
'metadata': _get_metadata(rec, config),
|
|
})
|
|
if batch_data:
|
|
indexed += svc.bulk_index(config['content_type'], batch_data)
|
|
offset += batch_size
|
|
env.cr.commit()
|
|
|
|
_logger.info("Indexed %d/%d records for %s", indexed, total, model_name)
|
|
return indexed
|
|
|
|
|
|
def index_all(env, batch_size=100):
|
|
"""Index all configured models."""
|
|
total = 0
|
|
for config in MODEL_CONFIG:
|
|
try:
|
|
total += index_model(env, config, batch_size)
|
|
except Exception:
|
|
_logger.exception("Failed to index %s", config['model'])
|
|
_logger.info("Total records indexed: %d", total)
|
|
return total
|
|
|
|
|
|
def cron_reindex(env):
|
|
"""Cron entry point for periodic re-indexing."""
|
|
_logger.info("Starting scheduled vector re-index")
|
|
return index_all(env)
|