Files
DEMO-AGENT/apps/documents/models.py

128 lines
4.8 KiB
Python

from django.db import models
class SubmissionBatch(models.Model):
"""
资料包主对象,承接导入、会话绑定和目录汇总结果。
Documents 模块负责维护资料包与文件的关系,
不在模型层耦合 Agent 执行细节。
"""
STATUS_PENDING = "pending"
STATUS_PROCESSING = "processing"
STATUS_COMPLETED = "completed"
STATUS_REVIEW_REQUIRED = "review_required"
STATUS_FAILED = "failed"
batch_id = models.CharField(max_length=64, unique=True, db_index=True)
product_name = models.CharField(max_length=255, blank=True, db_index=True)
workflow_type = models.CharField(max_length=64, default="registration")
conversation_id = models.CharField(max_length=64, blank=True, db_index=True)
file_count = models.PositiveIntegerField(default=0)
page_count = models.PositiveIntegerField(default=0)
chapter_summary = models.JSONField(default=list, blank=True)
import_status = models.CharField(max_length=32, default=STATUS_PENDING, db_index=True)
exception_count = models.PositiveIntegerField(default=0)
created_at = models.DateTimeField(auto_now_add=True, db_index=True)
updated_at = models.DateTimeField(auto_now=True)
class Meta:
ordering = ["-created_at"]
def __str__(self) -> str:
return self.product_name or self.batch_id
def get_import_status_display_text(self) -> str:
return {
self.STATUS_PENDING: "待导入",
self.STATUS_PROCESSING: "处理中",
self.STATUS_COMPLETED: "已完成",
self.STATUS_REVIEW_REQUIRED: "待复核",
self.STATUS_FAILED: "失败",
}.get(self.import_status, self.import_status)
class UploadedDocument(models.Model):
"""
保存用户上传文档的元数据和入库状态。
设计上只记录“文件属于哪个场景、当前是否已入库、失败原因是什么”,
不把 RAG 细节耦合进模型层。
"""
# 文档状态用于驱动前端提示和后续可操作项。
STATUS_UPLOADED = "uploaded"
STATUS_INDEXED = "indexed"
STATUS_FAILED = "failed"
batch = models.ForeignKey(
SubmissionBatch,
related_name="documents",
null=True,
blank=True,
on_delete=models.CASCADE,
)
scenario_id = models.CharField(max_length=100, db_index=True)
original_name = models.CharField(max_length=255)
file = models.FileField(upload_to="documents/%Y%m%d/")
file_type = models.CharField(max_length=20)
size = models.PositiveIntegerField(default=0)
relative_path = models.CharField(max_length=500, blank=True)
chapter_code = models.CharField(max_length=32, blank=True)
document_role = models.CharField(max_length=64, blank=True)
page_count = models.PositiveIntegerField(default=0)
page_count_confidence = models.CharField(max_length=32, blank=True)
chapter_match_status = models.CharField(max_length=32, blank=True)
needs_manual_review = models.BooleanField(default=False)
status = models.CharField(max_length=20, default=STATUS_UPLOADED, db_index=True)
error_message = models.TextField(blank=True)
created_at = models.DateTimeField(auto_now_add=True)
updated_at = models.DateTimeField(auto_now=True)
class Meta:
ordering = ["-created_at"]
def __str__(self) -> str:
return self.original_name
def get_status_display_text(self) -> str:
"""为模板提供更适合演示的中文状态文案。"""
return {
self.STATUS_UPLOADED: "已上传,待入库",
self.STATUS_INDEXED: "已入库,可检索",
self.STATUS_FAILED: "入库失败",
}.get(self.status, self.status)
class ExportedDocument(models.Model):
"""
导出文件记录。
该对象属于资料包治理范围:
- Documents 维护导出产物与资料包关系
- Chat 只负责触发导出动作
- Audit 负责回看执行痕迹
"""
batch = models.ForeignKey(
SubmissionBatch,
related_name="export_records",
on_delete=models.CASCADE,
)
conversation_id = models.CharField(max_length=64, db_index=True)
product_name = models.CharField(max_length=255, blank=True, db_index=True)
template_name = models.CharField(max_length=100, blank=True)
template_version = models.CharField(max_length=50, blank=True)
export_mode = models.CharField(max_length=32, db_index=True)
output_type = models.CharField(max_length=100, default="registration_word_export_report")
file_name = models.CharField(max_length=255)
relative_path = models.CharField(max_length=500)
download_url = models.CharField(max_length=500, blank=True)
created_at = models.DateTimeField(auto_now_add=True, db_index=True)
class Meta:
ordering = ["-created_at"]
def __str__(self) -> str:
return self.file_name