96 lines
2.8 KiB
Python
96 lines
2.8 KiB
Python
import json
|
|
import logging
|
|
import time
|
|
import uuid
|
|
|
|
import jsonschema
|
|
from django.core.cache import cache
|
|
from pathlib import Path
|
|
|
|
from config.exceptions import AppError
|
|
from . import deepseek_client
|
|
from .pdf_reader import extract_text_from_pdfs
|
|
from prompts.loader import load_prompt
|
|
|
|
logger = logging.getLogger(__name__)
|
|
audit = logging.getLogger('audit')
|
|
|
|
_SCHEMA_PATH = Path(__file__).resolve().parent.parent / 'schemas' / 'case_full.json'
|
|
PARSE_RESULT_TTL = 300 # 5 minutes
|
|
|
|
|
|
def parse_pdf(files, case_type: str, user) -> dict:
|
|
"""C1: PDF 解析 → DeepSeek → 结构化数据（不落库，不含评分规则）。"""
|
|
if case_type not in ('traditional', 'teaching'):
|
|
raise AppError('CASE_TYPE_NOT_SUPPORTED', f'case_type 不支持: {case_type}', status_code=400)
|
|
|
|
t0 = time.time()
|
|
|
|
text = extract_text_from_pdfs(files)
|
|
|
|
prompt_name = f'case_{case_type}_full'
|
|
system_prompt, prompt_version = load_prompt(prompt_name)
|
|
|
|
result = deepseek_client.call_deepseek(system_prompt, text)
|
|
data = result['data']
|
|
|
|
data.pop('scoring_rules', None)
|
|
data.pop('stages', None)
|
|
|
|
data['case_type'] = case_type
|
|
|
|
_strip_unknown_fields(data)
|
|
_validate_schema(data)
|
|
|
|
parse_id = uuid.uuid4().hex[:12]
|
|
cache.set(f'parse_result:{parse_id}', json.dumps(data, ensure_ascii=False), PARSE_RESULT_TTL)
|
|
|
|
source = {
|
|
'files': [f.name for f in files],
|
|
'total_bytes': sum(f.size for f in files),
|
|
}
|
|
|
|
audit.info(
|
|
'CASE_PARSE user=%s files=%d parse_id=%s tokens=%s prompt_version=%s',
|
|
user.id, len(files), parse_id,
|
|
result.get('usage', {}), prompt_version,
|
|
)
|
|
|
|
return {
|
|
'parse_id': parse_id,
|
|
'case_type': case_type,
|
|
'source': source,
|
|
'ai_usage': result.get('usage', {}),
|
|
'prompt_version': prompt_version,
|
|
'parsing_seconds': round(time.time() - t0, 1),
|
|
'data': data,
|
|
}
|
|
|
|
|
|
_SCHEMA_ALLOWED_KEYS = {
|
|
'title', 'case_type', 'difficulty', 'chief_complaint', 'description',
|
|
'patient_age', 'patient_gender', 'tags', 'symptom_tags', 'disease_tags',
|
|
'competency_tags', 'guideline_tags', 'knowledge_points', 'icd_codes',
|
|
'estimated_minutes', 'osce_enabled', 'department_name',
|
|
'traditional', 'teaching',
|
|
}
|
|
|
|
|
|
def _strip_unknown_fields(data):
|
|
for key in list(data.keys()):
|
|
if key not in _SCHEMA_ALLOWED_KEYS:
|
|
data.pop(key)
|
|
|
|
|
|
def _validate_schema(data):
|
|
schema = json.loads(_SCHEMA_PATH.read_text(encoding='utf-8'))
|
|
try:
|
|
jsonschema.validate(instance=data, schema=schema)
|
|
except jsonschema.ValidationError as e:
|
|
logger.error('AI parse output schema violation: %s', e.message)
|
|
raise AppError(
|
|
'AI_SCHEMA_VIOLATION',
|
|
f'AI 输出字段不合法: {e.message}',
|
|
status_code=500,
|
|
)
|