From 60997cc3952bbf6f810660d8edbb635113e3b1d0 Mon Sep 17 00:00:00 2001 From: Felix Date: Fri, 19 Dec 2025 17:17:09 +0800 Subject: [PATCH] add sentence --- .gitignore | 1 - backend/.env.example | 7 +- backend/alembic.ini | 12 +- .../0001_recording_add_fields_and_indexes.py | 21 + .../versions/0002_add_ref_to_audit_log.py | 29 ++ .../0003_add_ref_to_image_processing_task.py | 37 ++ backend/app/admin/crud/audit_log_crud.py | 3 + backend/app/admin/model/audit_log.py | 5 +- backend/app/admin/schema/audit_log.py | 4 +- backend/app/admin/schema/wx.py | 6 +- backend/app/admin/service/dict_service.py | 13 +- backend/app/admin/tasks.py | 28 +- backend/app/ai/api/image_text.py | 21 +- backend/app/ai/api/router.py | 4 +- backend/app/ai/api/scene.py | 72 +++ backend/app/ai/crud/image_chat_crud.py | 27 + backend/app/ai/crud/image_chat_msg_crud.py | 33 ++ backend/app/ai/crud/recording_crud.py | 26 +- backend/app/ai/crud/scene_sentence_crud.py | 63 +++ backend/app/ai/crud/sentence_card_crud.py | 38 ++ backend/app/ai/model/__init__.py | 4 +- backend/app/ai/model/image_chat.py | 50 ++ backend/app/ai/model/image_task.py | 10 +- backend/app/ai/model/recording.py | 5 +- backend/app/ai/model/scene_sentence.py | 50 ++ backend/app/ai/model/sentence_card.py | 28 ++ backend/app/ai/schema/image_chat.py | 18 + backend/app/ai/schema/image_task.py | 6 +- backend/app/ai/schema/sentence.py | 70 +++ backend/app/ai/service/image_chat_service.py | 54 ++ backend/app/ai/service/image_service.py | 17 +- backend/app/ai/service/recording_service.py | 74 ++- .../app/ai/service/scene_sentence_service.py | 74 +++ backend/app/ai/service/sentence_service.py | 464 ++++++++++++++++++ backend/common/const.py | 5 + backend/core/conf.py | 4 + backend/core/registrar.py | 2 +- backend/main.py | 4 +- backend/middleware/qwen.py | 79 +-- backend/middleware/tencent_hunyuan.py | 177 +++++++ backend/middleware/test.py | 6 +- deploy/app_server.conf | 18 +- requirements.txt | 4 +- 43 files changed, 1571 insertions(+), 102 deletions(-) create mode 100644 backend/alembic/versions/0001_recording_add_fields_and_indexes.py create mode 100644 backend/alembic/versions/0002_add_ref_to_audit_log.py create mode 100644 backend/alembic/versions/0003_add_ref_to_image_processing_task.py create mode 100644 backend/app/ai/api/scene.py create mode 100644 backend/app/ai/crud/image_chat_crud.py create mode 100644 backend/app/ai/crud/image_chat_msg_crud.py create mode 100644 backend/app/ai/crud/scene_sentence_crud.py create mode 100644 backend/app/ai/crud/sentence_card_crud.py create mode 100644 backend/app/ai/model/image_chat.py create mode 100644 backend/app/ai/model/scene_sentence.py create mode 100644 backend/app/ai/model/sentence_card.py create mode 100644 backend/app/ai/schema/image_chat.py create mode 100644 backend/app/ai/schema/sentence.py create mode 100644 backend/app/ai/service/image_chat_service.py create mode 100644 backend/app/ai/service/scene_sentence_service.py create mode 100644 backend/app/ai/service/sentence_service.py create mode 100644 backend/middleware/tencent_hunyuan.py diff --git a/.gitignore b/.gitignore index 1741fdf..8ef256a 100755 --- a/.gitignore +++ b/.gitignore @@ -3,7 +3,6 @@ __pycache__/ backend/static backend/log/ backend/.env -backend/alembic/versions/ backend/app/admin/cert/ .venv/ .vscode/ diff --git a/backend/.env.example b/backend/.env.example index a04fc75..4845a47 100755 --- a/backend/.env.example +++ b/backend/.env.example @@ -11,4 +11,9 @@ REDIS_PORT=6379 REDIS_PASSWORD='' REDIS_DATABASE=0 # Token -TOKEN_SECRET_KEY='1VkVF75nsNABBjK_7-qz7GtzNy3AMvktc9TCPwKczCk' +TOKEN_SECRET_KEY='1VkVF75nsNABBjK_7-qz7GtzNy3AMvktc9TCPwKczCk' +# Hunyuan +HUNYUAN_MODLE='hunyuan-lite' +HUNYUAN_APP_ID='' +HUNYUAN_SECRET_ID='' +HUNYUAN_SECRET_KEY='' diff --git a/backend/alembic.ini b/backend/alembic.ini index a08f379..cc1e320 100755 --- a/backend/alembic.ini +++ b/backend/alembic.ini @@ -33,7 +33,7 @@ prepend_sys_path = . # sourceless = false # version number format -version_num_format = %04d +version_num_format = %%04d # version path separator; As mentioned above, this is the character used to split # version_locations. The default within new alembic.ini files is "os", which uses @@ -50,7 +50,7 @@ version_path_separator = os # are written from script.py.mako # output_encoding = utf-8 -sqlalchemy.url = mysql+asyncmy://root:root@127.0.0.1:3306/app # Changed from postgresql+asyncpg to mysql+asyncmy +sqlalchemy.url = mysql+pymysql://root:root@127.0.0.1:3306/app # Changed from postgresql+asyncpg to mysql+asyncmy [post_write_hooks] @@ -71,17 +71,17 @@ keys = root,sqlalchemy,alembic [logger_root] level = WARN handlers = console -qalname = root +qualname = root [logger_sqlalchemy] level = WARN handlers = -qalname = sqlalchemy.engine +qualname = sqlalchemy.engine [logger_alembic] level = INFO handlers = -qalname = alembic +qualname = alembic [handlers] keys = console @@ -97,4 +97,4 @@ keys = generic [formatter_generic] format = %(levelname)-5.5s [%(name)s] %(message)s -datefmt = %H:%M:%S \ No newline at end of file +datefmt = %H:%M:%S diff --git a/backend/alembic/versions/0001_recording_add_fields_and_indexes.py b/backend/alembic/versions/0001_recording_add_fields_and_indexes.py new file mode 100644 index 0000000..29bba6b --- /dev/null +++ b/backend/alembic/versions/0001_recording_add_fields_and_indexes.py @@ -0,0 +1,21 @@ +from alembic import op +import sqlalchemy as sa +from sqlalchemy.dialects.mysql import JSON as MySQLJSON + +revision = '0001' +down_revision = None +branch_labels = None +depends_on = None + + +def upgrade(): + op.add_column('recording', sa.Column('ref_type', sa.String(length=50), nullable=True)) + op.add_column('recording', sa.Column('ref_id', sa.BigInteger(), nullable=True)) + op.create_index('idx_ref_type_id', 'recording', ['ref_type', 'ref_id']) + + +def downgrade(): + op.drop_index('idx_ref_type_id', table_name='recording') + + op.drop_column('recording', 'ref_id') + op.drop_column('recording', 'ref_type') diff --git a/backend/alembic/versions/0002_add_ref_to_audit_log.py b/backend/alembic/versions/0002_add_ref_to_audit_log.py new file mode 100644 index 0000000..70e5617 --- /dev/null +++ b/backend/alembic/versions/0002_add_ref_to_audit_log.py @@ -0,0 +1,29 @@ +"""add ref_type and ref_id to audit_log + +Revision ID: 0002 +Revises: 0001 +Create Date: 2025-12-14 + +""" +from alembic import op +import sqlalchemy as sa + +# revision identifiers, used by Alembic. +revision = "0002" +down_revision = "0001" +branch_labels = None +depends_on = None + + +def upgrade(): + with op.batch_alter_table('audit_log') as batch_op: + batch_op.add_column(sa.Column('ref_type', sa.String(length=50), nullable=True)) + batch_op.add_column(sa.Column('ref_id', sa.BigInteger(), nullable=True)) + op.create_index('idx_audit_log_ref_type_id', 'audit_log', ['ref_type', 'ref_id']) + + +def downgrade(): + op.drop_index('idx_audit_log_ref_type_id', table_name='audit_log') + with op.batch_alter_table('audit_log') as batch_op: + batch_op.drop_column('ref_id') + batch_op.drop_column('ref_type') diff --git a/backend/alembic/versions/0003_add_ref_to_image_processing_task.py b/backend/alembic/versions/0003_add_ref_to_image_processing_task.py new file mode 100644 index 0000000..8245275 --- /dev/null +++ b/backend/alembic/versions/0003_add_ref_to_image_processing_task.py @@ -0,0 +1,37 @@ +"""add ref_type and ref_id to image_processing_task + +Revision ID: 0003 +Revises: 0002 +Create Date: 2025-12-15 + +""" +from alembic import op +import sqlalchemy as sa + +# revision identifiers, used by Alembic. +revision = "0003" +down_revision = "0002" +branch_labels = None +depends_on = None + + +def upgrade(): + with op.batch_alter_table('image_processing_task') as batch_op: + batch_op.add_column(sa.Column('ref_type', sa.String(length=50), nullable=True)) + batch_op.add_column(sa.Column('ref_id', sa.BigInteger(), nullable=True)) + batch_op.drop_column('file_id') + batch_op.drop_column('type') + op.create_index( + 'idx_image_task_ref_type_id_status', + 'image_processing_task', + ['ref_type', 'ref_id', 'status'] + ) + + +def downgrade(): + op.drop_index('idx_image_task_ref_type_id_status', table_name='image_processing_task') + with op.batch_alter_table('image_processing_task') as batch_op: + batch_op.drop_column('ref_id') + batch_op.drop_column('ref_type') + batch_op.add_column(sa.Column('file_id', sa.BigInteger(), nullable=True)) + batch_op.add_column(sa.Column('type', sa.String(length=50), nullable=True)) diff --git a/backend/app/admin/crud/audit_log_crud.py b/backend/app/admin/crud/audit_log_crud.py index 071248d..ae8eb46 100755 --- a/backend/app/admin/crud/audit_log_crud.py +++ b/backend/app/admin/crud/audit_log_crud.py @@ -11,6 +11,7 @@ from backend.app.admin.schema.audit_log import CreateAuditLogParam, AuditLogStat from backend.app.ai import Image, ImageProcessingTask from backend.app.ai.model.image_task import ImageTaskStatus from backend.common.const import API_TYPE_RECOGNITION +from backend.app.admin.schema.wx import DictLevel class CRUDAuditLog(CRUDPlus[AuditLog]): @@ -74,6 +75,7 @@ class CRUDAuditLog(CRUDPlus[AuditLog]): .join(ImageProcessingTask, Image.id == ImageProcessingTask.image_id) .where( ranked_subquery.c.rn == 1, # 只选择每个image_id的第一条记录 + ImageProcessingTask.dict_level == DictLevel.LEVEL1.value, ImageProcessingTask.status == ImageTaskStatus.COMPLETED # 只选择任务状态为completed的记录 ) .order_by(ranked_subquery.c.called_at.desc(), ranked_subquery.c.id.desc()) @@ -93,6 +95,7 @@ class CRUDAuditLog(CRUDPlus[AuditLog]): AuditLog.user_id == user_id, AuditLog.api_type == API_TYPE_RECOGNITION, AuditLog.called_at >= today_start, + ImageProcessingTask.dict_level == DictLevel.LEVEL1.value, ImageProcessingTask.status == ImageTaskStatus.COMPLETED ) ) diff --git a/backend/app/admin/model/audit_log.py b/backend/app/admin/model/audit_log.py index 8488352..710d37b 100755 --- a/backend/app/admin/model/audit_log.py +++ b/backend/app/admin/model/audit_log.py @@ -24,6 +24,8 @@ class AuditLog(Base): status_code: Mapped[Optional[int]] = mapped_column(Integer, comment="HTTP状态码") image_id: Mapped[Optional[int]] = mapped_column(BigInteger, ForeignKey('image.id'), comment="关联的图片ID") user_id: Mapped[Optional[int]] = mapped_column(BigInteger, ForeignKey('wx_user.id'), comment="调用用户ID") + ref_type: Mapped[Optional[str]] = mapped_column(String(50), nullable=True, comment="通用引用类型") + ref_id: Mapped[Optional[int]] = mapped_column(BigInteger, nullable=True, comment="通用引用ID") dict_level: Mapped[Optional[str]] = mapped_column(String(20), comment="dict level") api_version: Mapped[Optional[str]] = mapped_column(String(20), comment="API版本") error_message: Mapped[Optional[str]] = mapped_column(Text, default=None, comment="错误信息") @@ -34,6 +36,7 @@ class AuditLog(Base): Index('idx_audit_logs_image_id', 'image_id'), # 为用户历史记录查询优化的索引 Index('idx_audit_log_user_api_called', 'user_id', 'api_type', 'called_at'), + Index('idx_audit_log_ref_type_id', 'ref_type', 'ref_id'), ) @@ -51,4 +54,4 @@ class DailySummary(Base): __table_args__ = ( # 为用户历史记录查询优化的索引 Index('idx_daily_summary_api_called', 'user_id', 'summary_time'), - ) \ No newline at end of file + ) diff --git a/backend/app/admin/schema/audit_log.py b/backend/app/admin/schema/audit_log.py index 0ee18a4..60bff19 100755 --- a/backend/app/admin/schema/audit_log.py +++ b/backend/app/admin/schema/audit_log.py @@ -22,6 +22,8 @@ class AuditLogSchemaBase(SchemaBase): user_id: int = Field(description="调用用户ID") api_version: str = Field(description="API版本") dict_level: Optional[str] = Field(None, description="词典等级") + ref_type: Optional[str] = Field(None, description="通用引用类型") + ref_id: Optional[int] = Field(None, description="通用引用ID") class CreateAuditLogParam(AuditLogSchemaBase): @@ -66,4 +68,4 @@ class DailySummaryPageSchema(SchemaBase): items: List[DailySummarySchema] = Field(description="每日汇总记录列表") total: int = Field(description="总记录数") page: int = Field(description="当前页码") - size: int = Field(description="每页记录数") \ No newline at end of file + size: int = Field(description="每页记录数") diff --git a/backend/app/admin/schema/wx.py b/backend/app/admin/schema/wx.py index 98fd6a5..210d5ef 100755 --- a/backend/app/admin/schema/wx.py +++ b/backend/app/admin/schema/wx.py @@ -53,9 +53,9 @@ class UserAuth(BaseModel): class DictLevel(str, Enum): - LEVEL1 = "LEVEL1" # "小学" - LEVEL2 = "LEVEL2" # "初高中" - LEVEL3 = "LEVEL3" # "四六级" + LEVEL1 = "level1" # "小学" + LEVEL2 = "level2" # "初高中" + LEVEL3 = "level3" # "四六级" class UserSettings(BaseModel): diff --git a/backend/app/admin/service/dict_service.py b/backend/app/admin/service/dict_service.py index b1b3d17..cd9b034 100755 --- a/backend/app/admin/service/dict_service.py +++ b/backend/app/admin/service/dict_service.py @@ -1,4 +1,5 @@ import json +import re from typing import Optional, Set, Dict, Any, Tuple, List import asyncio @@ -12,7 +13,6 @@ from backend.common.exception import errors from backend.database.db import async_db_session, background_db_session from backend.database.redis import redis_client -# Import required modules for the new method from backend.app.ai.model import Image from backend.app.ai.crud.image_curd import image_dao from backend.app.ai.model.image_task import ImageProcessingTask @@ -754,20 +754,13 @@ class DictService: # 处理description字段 (根据新需求应该是desc_en) descriptions = level_data.get("desc_en", []) - if not isinstance(descriptions, list): - # 兼容旧的字段名 - descriptions = level_data.get("desc_en", []) if isinstance(descriptions, list): for desc in descriptions: if isinstance(desc, str): # 按空格分割获取单词 - desc_words = desc.split() - for word in desc_words: - # 清理单词（移除标点符号等） - cleaned_word = ''.join(char for char in word if char.isalnum()) - if cleaned_word: - words.add(cleaned_word.lower()) + desc_words = set(re.findall(r'\b[\w-]+\b', desc.lower())) + words.update(desc_words) return words diff --git a/backend/app/admin/tasks.py b/backend/app/admin/tasks.py index e5e03a8..62b2ac1 100755 --- a/backend/app/admin/tasks.py +++ b/backend/app/admin/tasks.py @@ -5,7 +5,7 @@ """ from datetime import datetime, timedelta import logging -from sqlalchemy import select, and_, desc +from sqlalchemy import select, and_, desc, func from backend.app.admin.model.audit_log import AuditLog, DailySummary from backend.app.ai.model.image import Image from backend.app.ai.model.image_task import ImageProcessingTask, ImageTaskStatus @@ -15,6 +15,7 @@ from backend.app.admin.schema.audit_log import CreateDailySummaryParam from backend.common.const import API_TYPE_RECOGNITION from backend.database.db import async_db_session from backend.utils.timezone import timezone +from backend.app.admin.schema.wx import DictLevel async def wx_user_index_history() -> None: @@ -55,31 +56,40 @@ async def wx_user_index_history() -> None: # 为这批用户获取 audit_log 记录，只包含有对应completed状态image_processing_task的记录 audit_logs_stmt = ( - select(AuditLog) + select( + AuditLog.user_id.label('user_id'), + AuditLog.image_id.label('image_id'), + func.max(AuditLog.called_at).label('last_called_at') + ) .join(ImageProcessingTask, and_( AuditLog.image_id == ImageProcessingTask.image_id, + ImageProcessingTask.dict_level == DictLevel.LEVEL1.value, ImageProcessingTask.status == ImageTaskStatus.COMPLETED, )) .where( and_( AuditLog.user_id.in_(batch_user_ids), AuditLog.api_type == API_TYPE_RECOGNITION, + AuditLog.dict_level == DictLevel.LEVEL1.value, + AuditLog.image_id.is_not(None), AuditLog.called_at >= yesterday_start, AuditLog.called_at < yesterday_end ) ) - .order_by(AuditLog.user_id, desc(AuditLog.called_at)) + .group_by(AuditLog.user_id, AuditLog.image_id) + .order_by(AuditLog.user_id, desc(func.max(AuditLog.called_at))) ) audit_logs_result = await db.execute(audit_logs_stmt) - all_audit_logs = audit_logs_result.scalars().all() + all_audit_logs = audit_logs_result.fetchall() # 按用户 ID 分组 audit_logs user_audit_logs = {} - for log in all_audit_logs: - if log.user_id not in user_audit_logs: - user_audit_logs[log.user_id] = [] - user_audit_logs[log.user_id].append(log) + for row in all_audit_logs: + uid = row.user_id + if uid not in user_audit_logs: + user_audit_logs[uid] = [] + user_audit_logs[uid].append(row) # 获取这批用户的信息 users_stmt = select(WxUser).where(WxUser.id.in_(batch_user_ids)) @@ -87,7 +97,7 @@ async def wx_user_index_history() -> None: users = {user.id: user for user in users_result.scalars().all()} # 获取所有相关的 image 记录 - all_image_ids = [log.image_id for log in all_audit_logs if log.image_id] + all_image_ids = list(dict.fromkeys([row.image_id for row in all_audit_logs if row.image_id])) image_map = {} if all_image_ids: # 只查询需要的 thumbnail_id 字段，避免加载整个 Image 对象浪费内存 diff --git a/backend/app/ai/api/image_text.py b/backend/app/ai/api/image_text.py index 55e0fcd..c182845 100644 --- a/backend/app/ai/api/image_text.py +++ b/backend/app/ai/api/image_text.py @@ -5,6 +5,7 @@ from fastapi import APIRouter, Request, Query from starlette.background import BackgroundTasks from backend.app.ai.schema.image_text import ImageTextSchema, ImageTextWithRecordingsSchema, CreateImageTextParam, UpdateImageTextParam, ImageTextInitResponseSchema, ImageTextInitParam +from backend.app.ai.schema.recording import LatestRecordingResult from backend.app.ai.service.image_text_service import image_text_service from backend.app.ai.service.recording_service import recording_service from backend.common.exception import errors @@ -55,6 +56,24 @@ async def get_standard_audio_file_id( return response_base.success(data={'audio_id': str(file_id)}) +@router.get("/{text_id}/record_result", summary="获取最新评测结果", dependencies=[DependsJwtAuth]) +async def get_latest_record_result( + request: Request, + text_id: int, +) -> ResponseSchemaModel[LatestRecordingResult | None]: + rec = await recording_service.get_latest_result_by_text_id(text_id, request.user.id) + if not rec: + return response_base.success(data=None) + data = LatestRecordingResult( + id=rec.get("id"), + image_id=rec.get("image_id"), + image_text_id=rec.get("image_text_id"), + file_id=rec.get("file_id"), + details=rec.get("details"), + ) + return response_base.success(data=data) + + # @router.get("/{text_id}", summary="获取图片文本详情", dependencies=[DependsJwtAuth]) # async def get_image_text( # text_id: int @@ -159,4 +178,4 @@ async def get_standard_audio_file_id( # - 图片的所有文本记录列表 # """ # texts = await image_text_service.get_texts_by_image_id(image_id) -# return response_base.success(data=texts) \ No newline at end of file +# return response_base.success(data=texts) diff --git a/backend/app/ai/api/router.py b/backend/app/ai/api/router.py index d073a8c..0b12552 100644 --- a/backend/app/ai/api/router.py +++ b/backend/app/ai/api/router.py @@ -5,10 +5,12 @@ from fastapi import APIRouter from backend.app.ai.api.image import router as image_router from backend.app.ai.api.recording import router as recording_router from backend.app.ai.api.image_text import router as image_text_router +from backend.app.ai.api.scene import router as scene_router from backend.core.conf import settings v1 = APIRouter(prefix=settings.FASTAPI_API_V1_PATH) v1.include_router(image_router, prefix='/image', tags=['AI图片服务']) v1.include_router(recording_router, prefix='/recording', tags=['AI录音服务']) -v1.include_router(image_text_router, prefix='/image_text', tags=['AI图片文本服务']) \ No newline at end of file +v1.include_router(image_text_router, prefix='/image_text', tags=['AI图片文本服务']) +v1.include_router(scene_router, prefix='/scene', tags=['AI场景服务']) diff --git a/backend/app/ai/api/scene.py b/backend/app/ai/api/scene.py new file mode 100644 index 0000000..e585564 --- /dev/null +++ b/backend/app/ai/api/scene.py @@ -0,0 +1,72 @@ +#!/usr/bin/env python3 +# -*- coding: utf-8 -*- +from fastapi import APIRouter, Depends, Request, BackgroundTasks +from backend.common.response.response_schema import ResponseSchemaModel +from backend.common.security.jwt import DependsJwtAuth +from backend.app.ai.schema.sentence import SentenceTaskRequest, SentenceTaskResponse, SentenceTaskStatusResponse, SentenceAssessmentRequest, SentenceAssessmentResponse, SceneSentenceContent +from backend.app.ai.schema.recording import RecordingAssessmentResult +from backend.app.ai.service.sentence_service import sentence_service +from backend.app.ai.service.recording_service import recording_service + +router = APIRouter() + + +@router.post("/create", summary="创建场景任务", dependencies=[DependsJwtAuth]) +async def create_scene_task( + request: Request, + params: SentenceTaskRequest +) -> ResponseSchemaModel[SentenceTaskResponse]: + result = await sentence_service.create_scene_task( + image_id=params.image_id, + user_id=request.user.id, + scene_type=params.scene_type + ) + data = SentenceTaskResponse(task_id=result.get("task_id"), status=result.get("status")) + return ResponseSchemaModel[SentenceTaskResponse](code=200, msg="Success", data=data) + + +@router.post("/scene_sentence/assessment", summary="场景句型评测", dependencies=[DependsJwtAuth]) +async def assess_scene_sentence_api( + request: Request, + background_tasks: BackgroundTasks, + params: SentenceAssessmentRequest +) -> ResponseSchemaModel[SentenceAssessmentResponse]: + assessment = await recording_service.assess_scene_sentence( + file_id=params.file_id, + ref_text=params.ref_text, + ref_type=params.ref_type, + ref_id=params.ref_id, + user_id=request.user.id, + background_tasks=background_tasks + ) + data = SentenceAssessmentResponse( + file_id=params.file_id, + assessment_result=RecordingAssessmentResult(assessment=assessment), + ref_type=params.ref_type, + ref_id=str(params.ref_id) + ) + return ResponseSchemaModel[SentenceAssessmentResponse](code=200, msg="Success", data=data) + + +@router.get("/task/{task_id}", summary="查询句型任务状态", dependencies=[DependsJwtAuth]) +async def get_sentence_task_status( + request: Request, + task_id: int, +) -> ResponseSchemaModel[SentenceTaskStatusResponse]: + result = await sentence_service.get_task_status(task_id) + data = SentenceTaskStatusResponse( + task_id=result.get("task_id"), + ref_type=result.get("ref_type"), + ref_id=result.get("ref_id"), + status=result.get("status"), + error_message=result.get("error_message"), + ) + return ResponseSchemaModel[SentenceTaskStatusResponse](code=200, msg="Success", data=data) + +@router.get("/image/{image_id}/sentence", summary="获取图片最新的场景句型", dependencies=[DependsJwtAuth]) +async def get_latest_scene_sentence( + request: Request, + image_id: int, +) -> ResponseSchemaModel[SceneSentenceContent | None]: + content = await sentence_service.get_latest_scene_sentence(image_id, request.user.id) + return ResponseSchemaModel[SceneSentenceContent | None](code=200, msg="Success", data=content) diff --git a/backend/app/ai/crud/image_chat_crud.py b/backend/app/ai/crud/image_chat_crud.py new file mode 100644 index 0000000..1444855 --- /dev/null +++ b/backend/app/ai/crud/image_chat_crud.py @@ -0,0 +1,27 @@ +#!/usr/bin/env python3 +# -*- coding: utf-8 -*- +from typing import Optional, List +from sqlalchemy import select +from sqlalchemy.ext.asyncio import AsyncSession +from sqlalchemy_crud_plus import CRUDPlus + +from backend.app.ai.model.image_chat import ImageChat + + +class ImageChatCRUD(CRUDPlus[ImageChat]): + async def get(self, db: AsyncSession, id: int) -> Optional[ImageChat]: + return await self.select_model(db, id) + + async def create(self, db: AsyncSession, obj_in: dict) -> ImageChat: + db_obj = ImageChat(**obj_in) + db.add(db_obj) + await db.flush() + return db_obj + + async def get_by_image_id(self, db: AsyncSession, image_id: int) -> List[ImageChat]: + stmt = select(self.model).where(self.model.image_id == image_id) + result = await db.execute(stmt) + return list(result.scalars().all()) + + +image_chat_dao: ImageChatCRUD = ImageChatCRUD(ImageChat) diff --git a/backend/app/ai/crud/image_chat_msg_crud.py b/backend/app/ai/crud/image_chat_msg_crud.py new file mode 100644 index 0000000..6f8864e --- /dev/null +++ b/backend/app/ai/crud/image_chat_msg_crud.py @@ -0,0 +1,33 @@ +#!/usr/bin/env python3 +# -*- coding: utf-8 -*- +from typing import Optional, List +from sqlalchemy import select, func +from sqlalchemy.ext.asyncio import AsyncSession +from sqlalchemy_crud_plus import CRUDPlus + +from backend.app.ai.model.image_chat import ImageChatMsg + + +class ImageChatMsgCRUD(CRUDPlus[ImageChatMsg]): + async def get(self, db: AsyncSession, id: int) -> Optional[ImageChatMsg]: + return await self.select_model(db, id) + + async def create(self, db: AsyncSession, obj_in: dict) -> ImageChatMsg: + db_obj = ImageChatMsg(**obj_in) + db.add(db_obj) + await db.flush() + return db_obj + + async def get_by_chat_id(self, db: AsyncSession, chat_id: int) -> List[ImageChatMsg]: + stmt = select(self.model).where(self.model.image_chat_id == chat_id).order_by(self.model.turn_index) + result = await db.execute(stmt) + return list(result.scalars().all()) + + async def get_last_turn_index(self, db: AsyncSession, chat_id: int) -> int: + stmt = select(func.max(self.model.turn_index)).where(self.model.image_chat_id == chat_id) + result = await db.execute(stmt) + return result.scalar() or 0 + + +image_chat_msg_dao: ImageChatMsgCRUD = ImageChatMsgCRUD(ImageChatMsg) + diff --git a/backend/app/ai/crud/recording_crud.py b/backend/app/ai/crud/recording_crud.py index a38dc1e..ddc4b2e 100644 --- a/backend/app/ai/crud/recording_crud.py +++ b/backend/app/ai/crud/recording_crud.py @@ -53,5 +53,29 @@ class RecordingCRUD(CRUDPlus[Recording]): result = await db.execute(stmt) return result.scalar_one_or_none() + async def get_by_ref(self, db: AsyncSession, ref_type: str, ref_id: int) -> List[Recording]: + """根据通用引用获取录音记录""" + stmt = select(self.model).where( + and_( + self.model.ref_type == ref_type, + self.model.ref_id == ref_id, + self.model.is_standard == False + ) + ).order_by(self.model.created_time.asc()) + result = await db.execute(stmt) + return list(result.scalars().all()) -recording_dao: RecordingCRUD = RecordingCRUD(Recording) \ No newline at end of file + async def get_latest_by_ref(self, db: AsyncSession, ref_type: str, ref_id: int) -> Optional[Recording]: + """根据通用引用获取最新录音记录""" + stmt = select(self.model).where( + and_( + self.model.ref_type == ref_type, + self.model.ref_id == ref_id, + self.model.is_standard == False + ) + ).order_by(self.model.created_time.desc()).limit(1) + result = await db.execute(stmt) + return result.scalar_one_or_none() + + +recording_dao: RecordingCRUD = RecordingCRUD(Recording) diff --git a/backend/app/ai/crud/scene_sentence_crud.py b/backend/app/ai/crud/scene_sentence_crud.py new file mode 100644 index 0000000..1ad2d01 --- /dev/null +++ b/backend/app/ai/crud/scene_sentence_crud.py @@ -0,0 +1,63 @@ +#!/usr/bin/env python3 +# -*- coding: utf-8 -*- +from typing import Optional, List +from sqlalchemy import select, func +from sqlalchemy.ext.asyncio import AsyncSession +from sqlalchemy_crud_plus import CRUDPlus + +from backend.app.ai.model.scene_sentence import SceneSentence, SceneSentenceItem + + +class SceneSentenceCRUD(CRUDPlus[SceneSentence]): + async def get(self, db: AsyncSession, id: int) -> Optional[SceneSentence]: + return await self.select_model(db, id) + + async def create(self, db: AsyncSession, obj_in: dict) -> SceneSentence: + db_obj = SceneSentence(**obj_in) + db.add(db_obj) + await db.flush() + return db_obj + + async def get_last_seq(self, db: AsyncSession, image_chat_id: int) -> int: + stmt = select(func.max(self.model.seq)).where(self.model.image_chat_id == image_chat_id) + result = await db.execute(stmt) + return result.scalar() or 0 + + async def get_latest_by_image_and_user(self, db: AsyncSession, image_id: int, user_id: int) -> Optional[SceneSentence]: + stmt = ( + select(self.model) + .where( + self.model.image_id == image_id, + self.model.user_id == user_id + ) + .order_by(self.model.called_at.desc(), self.model.id.desc()) + .limit(1) + ) + result = await db.execute(stmt) + return result.scalar_one_or_none() + + +class SceneSentenceItemCRUD(CRUDPlus[SceneSentenceItem]): + async def create(self, db: AsyncSession, obj_in: dict) -> SceneSentenceItem: + db_obj = SceneSentenceItem(**obj_in) + db.add(db_obj) + await db.flush() + return db_obj + + async def create_many(self, db: AsyncSession, items: List[dict]) -> List[SceneSentenceItem]: + created: List[SceneSentenceItem] = [] + for it in items: + db_obj = SceneSentenceItem(**it) + db.add(db_obj) + created.append(db_obj) + await db.flush() + return created + + async def get_by_session(self, db: AsyncSession, sentence_id: int) -> List[SceneSentenceItem]: + stmt = select(self.model).where(self.model.sentence_id == sentence_id).order_by(self.model.seq) + result = await db.execute(stmt) + return list(result.scalars().all()) + + +scene_sentence_dao: SceneSentenceCRUD = SceneSentenceCRUD(SceneSentence) +scene_sentence_item_dao: SceneSentenceItemCRUD = SceneSentenceItemCRUD(SceneSentenceItem) diff --git a/backend/app/ai/crud/sentence_card_crud.py b/backend/app/ai/crud/sentence_card_crud.py new file mode 100644 index 0000000..e47ec9a --- /dev/null +++ b/backend/app/ai/crud/sentence_card_crud.py @@ -0,0 +1,38 @@ +#!/usr/bin/env python3 +# -*- coding: utf-8 -*- +from typing import Optional, List +from sqlalchemy import select +from sqlalchemy.ext.asyncio import AsyncSession +from sqlalchemy_crud_plus import CRUDPlus + +from backend.app.ai.model.sentence_card import SentenceCard + + +class SentenceCardCRUD(CRUDPlus[SentenceCard]): + async def get(self, db: AsyncSession, id: int) -> Optional[SentenceCard]: + return await self.select_model(db, id) + + async def create(self, db: AsyncSession, obj_in: dict) -> SentenceCard: + db_obj = SentenceCard(**obj_in) + db.add(db_obj) + await db.flush() + return db_obj + + async def get_latest_by_image_and_type(self, db: AsyncSession, image_id: int, card_type: str) -> Optional[SentenceCard]: + stmt = select(self.model).where( + self.model.image_id == image_id, + self.model.card_type == card_type + ).order_by(self.model.called_at.desc(), self.model.id.desc()).limit(1) + result = await db.execute(stmt) + return result.scalar_one_or_none() + + async def get_by_image_and_type(self, db: AsyncSession, image_id: int, card_type: str) -> List[SentenceCard]: + stmt = select(self.model).where( + self.model.image_id == image_id, + self.model.card_type == card_type + ).order_by(self.model.called_at.desc(), self.model.id.desc()) + result = await db.execute(stmt) + return list(result.scalars().all()) + + +sentence_card_dao: SentenceCardCRUD = SentenceCardCRUD(SentenceCard) diff --git a/backend/app/ai/model/__init__.py b/backend/app/ai/model/__init__.py index 25e1f98..1a31106 100644 --- a/backend/app/ai/model/__init__.py +++ b/backend/app/ai/model/__init__.py @@ -2,4 +2,6 @@ from backend.common.model import MappedBase # noqa: I from backend.app.ai.model.image import Image from backend.app.ai.model.image_text import ImageText from backend.app.ai.model.image_task import ImageProcessingTask -# from backend.app.ai.model.article import Article, ArticleParagraph, ArticleSentence \ No newline at end of file +from backend.app.ai.model.recording import Recording +from backend.app.ai.model.sentence_card import SentenceCard +from backend.app.ai.model.scene_sentence import SceneSentence, SceneSentenceItem diff --git a/backend/app/ai/model/image_chat.py b/backend/app/ai/model/image_chat.py new file mode 100644 index 0000000..cb06dd2 --- /dev/null +++ b/backend/app/ai/model/image_chat.py @@ -0,0 +1,50 @@ +#!/usr/bin/env python3 +# -*- coding: utf-8 -*- +from typing import Optional +from datetime import datetime + +from sqlalchemy import BigInteger, Text, String, Integer, Float, DateTime, ForeignKey, Index +from sqlalchemy.dialects.mysql import JSON as MySQLJSON +from sqlalchemy.orm import mapped_column, Mapped + +from backend.common.model import snowflake_id_key, Base + + +class ImageChat(Base): + __tablename__ = 'image_chat' + + id: Mapped[snowflake_id_key] = mapped_column(BigInteger, init=False, primary_key=True) + image_id: Mapped[Optional[int]] = mapped_column(BigInteger, ForeignKey('image.id'), nullable=True, comment="关联的图片ID") + user_id: Mapped[Optional[int]] = mapped_column(BigInteger, ForeignKey('wx_user.id'), nullable=True, comment="关联的用户ID") + chat_type: Mapped[str] = mapped_column(String(30), nullable=False, comment="聊天类型(scene_sentence/scene_dialogue/sentence_exercise/general)") + model_name: Mapped[str] = mapped_column(String(50), nullable=False, comment="模型名称") + ext: Mapped[Optional[dict]] = mapped_column(MySQLJSON, default=None, comment="扩展数据") + total_tokens: Mapped[Optional[int]] = mapped_column(Integer, default=0, comment="会话累计token") + last_called_at: Mapped[Optional[datetime]] = mapped_column(DateTime, default=None, comment="最近调用时间") + + __table_args__ = ( + Index('idx_image_chat_image_id', 'image_id'), + Index('idx_image_chat_user_called', 'user_id', 'last_called_at'), + Index('idx_image_chat_type_called', 'chat_type', 'last_called_at'), + ) + + +class ImageChatMsg(Base): + __tablename__ = 'image_chat_msg' + + id: Mapped[snowflake_id_key] = mapped_column(BigInteger, init=False, primary_key=True) + image_chat_id: Mapped[int] = mapped_column(BigInteger, ForeignKey('image_chat.id'), nullable=False, comment="会话ID") + turn_index: Mapped[int] = mapped_column(Integer, nullable=False, comment="轮次序号") + model_name: Mapped[str] = mapped_column(String(50), nullable=False, comment="模型名称") + messages: Mapped[Optional[dict]] = mapped_column(MySQLJSON, default=None, comment="增量请求消息") + response_data: Mapped[Optional[dict]] = mapped_column(MySQLJSON, default=None, comment="响应数据") + token_usage: Mapped[Optional[dict]] = mapped_column(MySQLJSON, default=None, comment="本轮消耗的token数量") + duration: Mapped[Optional[float]] = mapped_column(Float, default=None, comment="调用耗时(秒)") + status_code: Mapped[Optional[int]] = mapped_column(Integer, default=None, comment="HTTP状态码") + error_message: Mapped[Optional[str]] = mapped_column(Text, default=None, comment="错误信息") + called_at: Mapped[datetime] = mapped_column(DateTime, default=datetime.now(), comment="调用时间") + ext: Mapped[Optional[dict]] = mapped_column(MySQLJSON, default=None, comment="扩展数据") + + __table_args__ = ( + Index('idx_image_chat_msg_chat_turn', 'image_chat_id', 'turn_index'), + ) diff --git a/backend/app/ai/model/image_task.py b/backend/app/ai/model/image_task.py index a060b67..56ebe49 100644 --- a/backend/app/ai/model/image_task.py +++ b/backend/app/ai/model/image_task.py @@ -22,10 +22,10 @@ class ImageProcessingTask(Base): id: Mapped[snowflake_id_key] = mapped_column(BigInteger, init=False, primary_key=True) image_id: Mapped[int] = mapped_column(BigInteger, nullable=False, comment="关联的图片ID") - file_id: Mapped[int] = mapped_column(BigInteger, nullable=False, comment="关联的文件ID") user_id: Mapped[int] = mapped_column(BigInteger, nullable=False, comment="用户ID") dict_level: Mapped[str] = mapped_column(String(20), nullable=False, comment="词典等级") - type: Mapped[str] = mapped_column(String(50), nullable=False, comment="处理类型") + ref_type: Mapped[str] = mapped_column(String(50), nullable=False, comment="引用类型") + ref_id: Mapped[int] = mapped_column(BigInteger, nullable=False, comment="引用ID") status: Mapped[ImageTaskStatus] = mapped_column(String(20), default=ImageTaskStatus.PENDING, comment="任务状态") result: Mapped[Optional[dict]] = mapped_column(MySQLJSON, default=None, comment="处理结果") error_message: Mapped[Optional[str]] = mapped_column(Text, default=None, comment="错误信息") @@ -35,8 +35,8 @@ class ImageProcessingTask(Base): __table_args__ = ( # 为 image_id 添加索引以优化查询 Index('idx_image_task_image_id', 'image_id'), - # 为 status 添加索引以优化查询 - Index('idx_image_task_status', 'status'), # 为 user_id 添加索引以优化查询 Index('idx_image_task_user_id', 'user_id'), - ) \ No newline at end of file + # 为 ref_type/ref_id/status 添加复合索引用于检索 + Index('idx_image_task_ref_type_id_status', 'ref_type', 'ref_id', 'status'), + ) diff --git a/backend/app/ai/model/recording.py b/backend/app/ai/model/recording.py index fc7b3a3..955a759 100755 --- a/backend/app/ai/model/recording.py +++ b/backend/app/ai/model/recording.py @@ -22,6 +22,8 @@ class Recording(Base): image_text_id: Mapped[Optional[int]] = mapped_column(BigInteger, ForeignKey('image_text.id'), nullable=True, comment="关联的图片文本ID") text: Mapped[Optional[str]] = mapped_column(String(255), nullable=True, comment='朗读文本') eval_mode: Mapped[Optional[int]] = mapped_column(Integer, nullable=True, comment='评测模式') + ref_type: Mapped[Optional[str]] = mapped_column(String(50), default=None, comment="通用引用类型") + ref_id: Mapped[Optional[int]] = mapped_column(BigInteger, default=None, comment="通用引用ID") info: Mapped[Optional[RecordingMetadata]] = mapped_column(PydanticType(pydantic_type=RecordingMetadata), default=None, comment="附加元数据") # 其他可能的字段（根据实际需求添加） details: Mapped[Optional[dict]] = mapped_column(MySQLJSON, default=None, comment="评估信息") # 其他信息 is_standard: Mapped[bool] = mapped_column(Boolean, default=False, comment="是否为标准朗读音频") @@ -30,4 +32,5 @@ class Recording(Base): __table_args__ = ( Index('idx_image_user_id', 'image_id', 'user_id'), Index('idx_image_text_id', 'image_text_id'), - ) \ No newline at end of file + Index('idx_ref_type_id', 'ref_type', 'ref_id'), + ) diff --git a/backend/app/ai/model/scene_sentence.py b/backend/app/ai/model/scene_sentence.py new file mode 100644 index 0000000..9ee24dc --- /dev/null +++ b/backend/app/ai/model/scene_sentence.py @@ -0,0 +1,50 @@ +#!/usr/bin/env python3 +# -*- coding: utf-8 -*- +from typing import Optional, List +from datetime import datetime + +from sqlalchemy import BigInteger, Text, String, Integer, Float, DateTime, ForeignKey, Index +from sqlalchemy.dialects.mysql import JSON as MySQLJSON +from sqlalchemy.orm import mapped_column, Mapped + +from backend.common.model import snowflake_id_key, Base + + +class SceneSentence(Base): + __tablename__ = 'scene_sentence' + + id: Mapped[snowflake_id_key] = mapped_column(BigInteger, init=False, primary_key=True) + image_id: Mapped[int] = mapped_column(BigInteger, ForeignKey('image.id'), nullable=False, comment="关联的图片ID") + user_id: Mapped[int] = mapped_column(BigInteger, ForeignKey('wx_user.id'), nullable=False, comment="关联的用户ID") + image_chat_id: Mapped[Optional[int]] = mapped_column(BigInteger, ForeignKey('image_chat.id'), nullable=True, comment="关联的会话ID") + seq: Mapped[int] = mapped_column(Integer, nullable=False, comment="同一会话的批次序号") + scene_tag: Mapped[Optional[List[str]]] = mapped_column(MySQLJSON, default=None, comment="场景标签") + total_count: Mapped[int] = mapped_column(Integer, default=0, comment="句型总数") + viewed_count: Mapped[int] = mapped_column(Integer, default=0, comment="已浏览数") + practiced_count: Mapped[int] = mapped_column(Integer, default=0, comment="已跟读数") + called_at: Mapped[datetime] = mapped_column(DateTime, default=datetime.now(), comment="创建时间") + ext: Mapped[Optional[dict]] = mapped_column(MySQLJSON, default=None, comment="扩展数据") + + __table_args__ = ( + Index('idx_scene_sentence_session_image_user', 'image_id', 'user_id'), + Index('idx_scene_sentence_session_chat_seq', 'image_chat_id', 'seq'), + ) + + +class SceneSentenceItem(Base): + __tablename__ = 'scene_sentence_item' + + id: Mapped[snowflake_id_key] = mapped_column(BigInteger, init=False, primary_key=True) + image_text_id: Mapped[Optional[int]] = mapped_column(BigInteger, ForeignKey('image_text.id'), nullable=True, comment="关联的图片文本ID") + sentence_id: Mapped[int] = mapped_column(BigInteger, ForeignKey('scene_sentence.id'), nullable=False, comment="所属批次ID") + sentence_en: Mapped[str] = mapped_column(String(255), nullable=False, comment="英文句型") + sentence_zh: Mapped[str] = mapped_column(String(255), nullable=False, comment="中文翻译") + seq: Mapped[int] = mapped_column(Integer, default=0, comment="卡片序号") + function_tags: Mapped[Optional[List[str]]] = mapped_column(MySQLJSON, default=None, comment="功能标签") + core_vocab: Mapped[Optional[List[str]]] = mapped_column(MySQLJSON, default=None, comment="核心词汇") + collocations: Mapped[Optional[List[str]]] = mapped_column(MySQLJSON, default=None, comment="核心搭配") + ext: Mapped[Optional[dict]] = mapped_column(MySQLJSON, default=None, comment="扩展数据") + + __table_args__ = ( + Index('idx_scene_sentence_item_session_order', 'sentence_id', 'seq'), + ) diff --git a/backend/app/ai/model/sentence_card.py b/backend/app/ai/model/sentence_card.py new file mode 100644 index 0000000..dbd3d02 --- /dev/null +++ b/backend/app/ai/model/sentence_card.py @@ -0,0 +1,28 @@ +#!/usr/bin/env python3 +# -*- coding: utf-8 -*- +from typing import Optional +from datetime import datetime + +from sqlalchemy import BigInteger, Text, String, Float, Integer, DateTime, ForeignKey, Index +from sqlalchemy.dialects.mysql import JSON as MySQLJSON +from sqlalchemy.orm import mapped_column, Mapped + +from backend.common.model import snowflake_id_key, Base + + +class SentenceCard(Base): + __tablename__ = 'sentence_card' + + id: Mapped[snowflake_id_key] = mapped_column(BigInteger, init=False, primary_key=True) + image_id: Mapped[Optional[int]] = mapped_column(BigInteger, ForeignKey('image.id'), nullable=True, comment="关联的图片ID") + user_id: Mapped[Optional[int]] = mapped_column(BigInteger, ForeignKey('wx_user.id'), nullable=True, comment="关联的用户ID") + image_chat_id: Mapped[Optional[int]] = mapped_column(BigInteger, ForeignKey('image_chat.id'), nullable=True, comment="关联的会话ID") + card_type: Mapped[str] = mapped_column(String(30), nullable=False, comment="卡片类型(scene_sentence/scene_dialogue/sentence_exercise)") + scene_tag: Mapped[Optional[str]] = mapped_column(String(50), default=None, comment="场景标签") + details: Mapped[Optional[str]] = mapped_column(Text, default=None, comment="句型详情JSON字符串") + called_at: Mapped[datetime] = mapped_column(DateTime, default=datetime.now(), comment="调用时间") + + __table_args__ = ( + Index('idx_sentence_card_image_id', 'image_id'), + Index('idx_sentence_card_type_called', 'card_type', 'called_at'), + ) diff --git a/backend/app/ai/schema/image_chat.py b/backend/app/ai/schema/image_chat.py new file mode 100644 index 0000000..f9dbf75 --- /dev/null +++ b/backend/app/ai/schema/image_chat.py @@ -0,0 +1,18 @@ +#!/usr/bin/env python3 +# -*- coding: utf-8 -*- +from typing import Optional +from pydantic import Field + +from backend.common.schema import SchemaBase + + +class ImageChatSchemaBase(SchemaBase): + chat_type: str = Field(description="聊天类型(scene_sentence/scene_dialogue/sentence_exercise/general)") + model_name: str = Field(description="模型名称") + image_id: Optional[int] = Field(None, description="关联的图片ID") + user_id: Optional[int] = Field(None, description="调用用户ID") + ext: Optional[dict] = Field(None, description="扩展数据") + + +class CreateImageChatParam(ImageChatSchemaBase): + pass diff --git a/backend/app/ai/schema/image_task.py b/backend/app/ai/schema/image_task.py index fc9e573..caca858 100644 --- a/backend/app/ai/schema/image_task.py +++ b/backend/app/ai/schema/image_task.py @@ -9,10 +9,10 @@ from backend.common.schema import SchemaBase class ImageTaskSchemaBase(SchemaBase): image_id: int - file_id: int user_id: int dict_level: str - type: str + ref_type: str + ref_id: int status: ImageTaskStatus = ImageTaskStatus.PENDING result: Optional[dict] = None error_message: Optional[str] = None @@ -40,4 +40,4 @@ class ImageTaskStatusResponse(BaseModel): image_id: str status: ImageTaskStatus # result: Optional[dict] = None - error_message: Optional[str] = None \ No newline at end of file + error_message: Optional[str] = None diff --git a/backend/app/ai/schema/sentence.py b/backend/app/ai/schema/sentence.py new file mode 100644 index 0000000..15d7f90 --- /dev/null +++ b/backend/app/ai/schema/sentence.py @@ -0,0 +1,70 @@ +from typing import Optional +from backend.common.schema import SchemaBase +from backend.app.ai.schema.recording import RecordingAssessmentResult + + +class SentenceTaskRequest(SchemaBase): + image_id: int + scene_type: str + + +class SentenceTaskResponse(SchemaBase): + task_id: str + status: str + +class SentenceTaskStatusResponse(SchemaBase): + task_id: str + ref_type: str + ref_id: str + status: str + error_message: Optional[str] = None + +class SceneSentenceItem(SchemaBase): + seq: int | None = None + sentenceEn: str + sentenceZh: str + functionTags: Optional[list] = None + sceneExplanation: Optional[str] = None + pronunciationTip: Optional[str] = None + coreVocab: Optional[list] = None + coreVocabDesc: Optional[list] = None + collocations: Optional[list] = None + grammarPoint: Optional[str] = None + commonMistakes: Optional[list] = None + pragmaticAlternative: Optional[list] = None + sceneTransferTip: Optional[str] = None + difficultyTag: Optional[str] = None + extendedExample: Optional[list] = None + imageTextId: Optional[str] = None + responsePairs: Optional[list] = None + fluencyHacks: Optional[str] = None + culturalNote: Optional[str] = None + practiceSteps: Optional[list] = None + avoidScenarios: Optional[str] = None + selfCheckList: Optional[list] = None + toneIntensity: Optional[str] = None + similarSentenceDistinction: Optional[str] = None + speechRateTip: Optional[str] = None + personalizedTips: Optional[str] = None + +class SceneSentenceContent(SchemaBase): + id: str + image_id: str + user_id: str + scene_tag: Optional[list[str]] = None + total: int + list: list[SceneSentenceItem] + + +class SentenceAssessmentRequest(SchemaBase): + file_id: int + ref_text: str + ref_type: str + ref_id: int + + +class SentenceAssessmentResponse(SchemaBase): + file_id: Optional[int] + assessment_result: RecordingAssessmentResult + ref_type: Optional[str] = None + ref_id: Optional[str] = None diff --git a/backend/app/ai/service/image_chat_service.py b/backend/app/ai/service/image_chat_service.py new file mode 100644 index 0000000..96f039c --- /dev/null +++ b/backend/app/ai/service/image_chat_service.py @@ -0,0 +1,54 @@ +#!/usr/bin/env python3 +# -*- coding: utf-8 -*- +from typing import Optional, List, Dict, Any + +from sqlalchemy.ext.asyncio import AsyncSession + +from backend.app.ai.crud.image_chat_crud import image_chat_dao +from backend.app.ai.crud.image_chat_msg_crud import image_chat_msg_dao +from backend.app.ai.model.image_chat import ImageChat, ImageChatMsg +from backend.app.ai.schema.image_chat import CreateImageChatParam +from backend.database.db import async_db_session + + +class ImageChatService: + @staticmethod + async def create(obj: CreateImageChatParam) -> Optional[ImageChat]: + async with async_db_session.begin() as db: + return await image_chat_dao.create(db, obj.model_dump(exclude_none=True)) + + @staticmethod + async def get_by_image_id(image_id: int) -> List[ImageChat]: + async with async_db_session() as db: + return await image_chat_dao.get_by_image_id(db, image_id) + + @staticmethod + async def get(chat_id: int) -> Optional[ImageChat]: + async with async_db_session() as db: + return await image_chat_dao.get(db, chat_id) + + @staticmethod + async def create_conversation(payload: Dict[str, Any]) -> Optional[ImageChat]: + async with async_db_session.begin() as db: + chat = await image_chat_dao.create(db, payload) + return chat + + @staticmethod + async def append_turn(chat_id: int, turn: Dict[str, Any]) -> Optional[ImageChatMsg]: + async with async_db_session.begin() as db: + chat = await image_chat_dao.get(db, chat_id) + if not chat: + return None + last_index = await image_chat_msg_dao.get_last_turn_index(db, chat_id) + turn["image_chat_id"] = chat_id + turn["turn_index"] = last_index + 1 + msg = await image_chat_msg_dao.create(db, turn) + usage = turn.get("token_usage") or {} + total = usage.get("total_tokens") or usage.get("TotalTokens") or usage.get("total") or 0 + if total: + chat.total_tokens = (chat.total_tokens or 0) + int(total) + chat.last_called_at = turn.get("called_at") or chat.last_called_at + return msg + + +image_chat_service = ImageChatService() diff --git a/backend/app/ai/service/image_service.py b/backend/app/ai/service/image_service.py index 85e072e..f51a990 100755 --- a/backend/app/ai/service/image_service.py +++ b/backend/app/ai/service/image_service.py @@ -276,11 +276,11 @@ class ImageService: # 创建异步处理任务 task_params = CreateImageTaskParam( image_id=image_id, - file_id=file_id, user_id=current_user.id, status=ImageTaskStatus.PENDING, dict_level=dict_level, - type=type + ref_type="image", + ref_id=image_id, ) task = await image_task_dao.create_task(db, task_params) @@ -290,7 +290,7 @@ class ImageService: await db.commit() # 添加后台任务来处理图片识别 - asyncio.create_task(ImageService._process_image_with_limiting(task_id, current_user.id)) + asyncio.create_task(ImageService._process_image_with_limiting(task_id, current_user.id, type)) return { "task_id": str(task_id), @@ -299,7 +299,7 @@ class ImageService: } @staticmethod - async def _process_image_with_limiting(task_id: int, user_id: int) -> None: + async def _process_image_with_limiting(task_id: int, user_id: int, proc_type: str) -> None: """带限流控制的后台处理图片识别任务""" task_processing_success = False points_deducted = False @@ -314,7 +314,7 @@ class ImageService: except Exception: pass if need_recognition: - await ImageService._process_image_recognition(task_id) + await ImageService._process_image_recognition(task_id, proc_type) # Step 2: Process all remaining steps in a single database transaction for consistency async with background_db_session() as db: @@ -437,7 +437,7 @@ class ImageService: raise @staticmethod - async def _process_image_recognition(task_id: int) -> None: + async def _process_image_recognition(task_id: int, proc_type: str) -> None: """后台处理图片识别任务 - compatible version for task processor""" # This is maintained for backward compatibility with the task processor # It creates its own database connection like the original implementation @@ -467,7 +467,8 @@ class ImageService: await db.commit() # 下载文件（在数据库事务外执行） - file_content, file_name, content_type = await file_service.download_image_file(task.file_id) + image_record = await image_dao.get(db, task.image_id) + file_content, file_name, content_type = await file_service.download_image_file(image_record.file_id if image_record else None) image_format = image_service.detect_image_format(file_content) image_format_str = image_format.value base64_image = base64.b64encode(file_content).decode('utf-8') @@ -480,7 +481,7 @@ class ImageService: file_name=file_name, format=image_format_str, data=base64_image, - type=task.type, + type=proc_type, dict_level=task.dict_level ) diff --git a/backend/app/ai/service/recording_service.py b/backend/app/ai/service/recording_service.py index b442efa..2e81a29 100644 --- a/backend/app/ai/service/recording_service.py +++ b/backend/app/ai/service/recording_service.py @@ -91,6 +91,21 @@ class RecordingService: async with async_db_session() as db: return await recording_dao.get_standard_by_text_id(db, text_id) + @staticmethod + async def get_latest_result_by_text_id(text_id: int, user_id: int) -> Optional[dict]: + """根据图片文本ID获取最新一次非标准录音的结果，返回基础标识与details""" + async with async_db_session() as db: + rec = await recording_dao.get_latest_by_text_id(db, text_id) + if not rec: + return None + return { + "id": str(rec.id) if rec.id is not None else None, + "image_id": str(rec.image_id) if rec.image_id is not None else None, + "image_text_id": str(rec.image_text_id) if rec.image_text_id is not None else None, + "file_id": str(rec.file_id) if rec.file_id is not None else None, + "details": rec.details, + } + @staticmethod async def update_recording_details(id: int, details: dict) -> bool: """更新录音的评估详情""" @@ -253,7 +268,7 @@ class RecordingService: return metadata @staticmethod - async def create_recording_record(file_id: int, ref_text: Optional[str] = None, image_id: Optional[int] = None, image_text_id: Optional[int] = None, eval_mode: Optional[int] = None, user_id: Optional[int] = None) -> int: + async def create_recording_record(file_id: int, ref_text: Optional[str] = None, image_id: Optional[int] = None, image_text_id: Optional[int] = None, eval_mode: Optional[int] = None, user_id: Optional[int] = None, ref_type: Optional[str] = None, ref_id: Optional[int] = None) -> int: """创建录音记录并提取基本元数据""" try: # 检查文件是否存在 @@ -273,7 +288,9 @@ class RecordingService: eval_mode=eval_mode, info=metadata, text=ref_text, - user_id=user_id + user_id=user_id, + ref_type=ref_type, + ref_id=ref_id ) db.add(recording) await db.commit() @@ -284,7 +301,7 @@ class RecordingService: raise RuntimeError(f"Failed to create recording record for file_id {file_id}: {str(e)}") @staticmethod - async def create_recording_record_with_details(file_id: int, ref_text: Optional[str] = None, image_id: Optional[int] = None, image_text_id: Optional[int] = None, eval_mode: Optional[int] = None, user_id: Optional[int] = None, details: Optional[dict] = None, is_standard: bool = False) -> int: + async def create_recording_record_with_details(file_id: int, ref_text: Optional[str] = None, image_id: Optional[int] = None, image_text_id: Optional[int] = None, eval_mode: Optional[int] = None, user_id: Optional[int] = None, details: Optional[dict] = None, is_standard: bool = False, ref_type: Optional[str] = None, ref_id: Optional[int] = None) -> int: """创建录音记录并设置详细信息""" try: # 检查文件是否存在 @@ -306,7 +323,9 @@ class RecordingService: text=ref_text, details=details, is_standard=is_standard, # 设置标准音频标记 - user_id=user_id + user_id=user_id, + ref_type=ref_type, + ref_id=ref_id ) db.add(recording) await db.commit() @@ -413,6 +432,53 @@ class RecordingService: # 重新抛出异常 raise RuntimeError(f"Failed to assess recording: {str(e)}") + async def assess_scene_sentence(self, file_id: int, ref_text: str, ref_type: str, ref_id: int, user_id: int = 0, background_tasks=None) -> dict: + start_time = time.time() + status_code = 200 + error_message = None + image_id = None + recording = await self.get_recording_by_file_id(file_id) + if not recording: + try: + recording_id = await self.create_recording_record(file_id, ref_text, image_id, None, 1, user_id, ref_type, ref_id) + recording = await self.get_recording_by_file_id(file_id) + if not recording: + raise RuntimeError(f"Failed to create recording record for file_id {file_id}") + except Exception as e: + raise RuntimeError(f"Failed to create recording record for file_id {file_id}: {str(e)}") + if not await points_service.check_sufficient_points(user_id, SPEECH_ASSESSMENT_COST): + raise RuntimeError('积分不足，请充值以继续使用') + try: + result = await self.tencent_cloud.assessment_speech(file_id, ref_text, str(recording.id), image_id, user_id) + details = {"assessment": result} + success = await self.update_recording_details(recording.id, details) + if not success: + raise RuntimeError(f"Failed to update recording details for file_id {file_id}") + async with async_db_session.begin() as db: + await points_service.deduct_points_with_db( + user_id=user_id, + amount=SPEECH_ASSESSMENT_COST, + db=db, + related_id=recording.id, + details={"recording_id": recording.id}, + action=POINTS_ACTION_SPEECH_ASSESSMENT + ) + duration = time.time() - start_time + if background_tasks: + self._log_audit(background_tasks, file_id, ref_text, result, duration, status_code, user_id, image_id, 0) + return result + except Exception as e: + error_result = {"assessment": {"error": str(e)}} + try: + await self.update_recording_details(recording.id, error_result) + except Exception: + pass + status_code = 500 + error_message = str(e) + duration = time.time() - start_time + if background_tasks: + self._log_audit(background_tasks, file_id, ref_text, error_result, duration, status_code, user_id, image_id, 0, error_message) + raise RuntimeError(f"Failed to assess recording: {str(e)}") @staticmethod def _log_audit(background_tasks, file_id: int, ref_text: Optional[str], result: dict, duration: float, status_code: int, user_id: int, image_id: Optional[int], image_text_id: int, error_message: Optional[str] = None): diff --git a/backend/app/ai/service/scene_sentence_service.py b/backend/app/ai/service/scene_sentence_service.py new file mode 100644 index 0000000..1cc25c4 --- /dev/null +++ b/backend/app/ai/service/scene_sentence_service.py @@ -0,0 +1,74 @@ +#!/usr/bin/env python3 +# -*- coding: utf-8 -*- +from typing import Optional, List, Dict, Any +from datetime import datetime + +from backend.database.db import async_db_session +from backend.app.ai.crud.scene_sentence_crud import scene_sentence_dao, scene_sentence_item_dao +from backend.app.ai.crud.image_text_crud import image_text_dao +from backend.app.admin.schema.wx import DictLevel + + +class SceneSentenceService: + @staticmethod + async def create_session_with_items(image_id: int, user_id: int, image_chat_id: Optional[int], scene_tag: Optional[List[str]] = None, items: List[Dict[str, Any]] = [], called_at: datetime = datetime.now()) -> Dict[str, Any]: + async with async_db_session.begin() as db: + last_seq = 0 + if image_chat_id: + last_seq = await scene_sentence_dao.get_last_seq(db, image_chat_id) + sentence = await scene_sentence_dao.create(db, { + "image_id": image_id, + "user_id": user_id, + "image_chat_id": image_chat_id, + "scene_tag": scene_tag, + "seq": int(last_seq) + 1, + "total_count": len(items), + "viewed_count": 0, + "practiced_count": 0, + "called_at": called_at, + "ext": {}, + }) + payloads = [] + level2_texts = await image_text_dao.get_by_image_id_and_level(db, image_id, DictLevel.LEVEL2.value) + text_map = { (t.content or "").strip(): t.id for t in level2_texts } + for idx, it in enumerate(items): + content_key = (it.get("sentence_en") or it.get("sentenceEn", "")).strip().lower() + image_text_id = text_map.get(content_key) + ext_payload = { + "scene_explanation": it.get("scene_explanation") or it.get("sceneExplanation"), + "pronunciation_tip": it.get("pronunciation_tip") or it.get("pronunciationTip"), + "pronunciation_url": it.get("pronunciation_url"), + "core_vocab_desc": it.get("core_vocab_desc") or [], + "grammar_point": it.get("grammar_point"), + "common_mistakes": it.get("common_mistakes"), + "pragmatic_alternative": it.get("pragmatic_alternative") or [], + "scene_transfer_tip": it.get("scene_transfer_tip"), + "difficulty_tag": it.get("difficulty_tag"), + "extended_example": it.get("extended_example"), + "response_pairs": it.get("response_pairs") or it.get("responsePairs") or [], + "fluency_hacks": it.get("fluency_hacks") or it.get("fluencyHacks"), + "cultural_note": it.get("cultural_note") or it.get("culturalNote"), + "practice_steps": it.get("practice_steps") or it.get("practiceSteps") or [], + "avoid_scenarios": it.get("avoid_scenarios") or it.get("avoidScenarios"), + "self_check_list": it.get("self_check_list") or it.get("selfCheckList") or [], + "tone_intensity": it.get("tone_intensity") or it.get("toneIntensity"), + "similar_sentence_distinction": it.get("similar_sentence_distinction") or it.get("similarSentenceDistinction"), + "speech_rate_tip": it.get("speech_rate_tip") or it.get("speechRateTip"), + "personalized_tips": it.get("personalized_tips") or it.get("personalizedTips"), + } + payloads.append({ + "sentence_id": sentence.id, + "seq": idx, + "image_text_id": image_text_id, + "sentence_en": it.get("sentence_en") or it.get("sentenceEn", ""), + "sentence_zh": it.get("sentence_zh") or it.get("sentenceZh", ""), + "function_tags": it.get("function_tags") or it.get("functionTags") or [], + "core_vocab": it.get("core_vocab") or it.get("coreVocab") or [], + "collocations": it.get("collocations") or [], + "ext": ext_payload, + }) + created_items = await scene_sentence_item_dao.create_many(db, payloads) + return {"sentence_id": sentence.id, "count": len(created_items)} + + +scene_sentence_service = SceneSentenceService() diff --git a/backend/app/ai/service/sentence_service.py b/backend/app/ai/service/sentence_service.py new file mode 100644 index 0000000..c9c80b0 --- /dev/null +++ b/backend/app/ai/service/sentence_service.py @@ -0,0 +1,464 @@ +#!/usr/bin/env python3 +# -*- coding: utf-8 -*- +from typing import Optional, List, Dict, Any +from datetime import datetime +import json + +from backend.app.ai.crud.sentence_card_crud import sentence_card_dao +from backend.app.ai.crud.scene_sentence_crud import scene_sentence_dao, scene_sentence_item_dao +from backend.app.ai.model.sentence_card import SentenceCard +from backend.app.ai.schema.image_chat import CreateImageChatParam +from backend.app.ai.service.image_chat_service import image_chat_service +from backend.app.ai.crud.image_curd import image_dao +from backend.database.db import async_db_session, background_db_session +from backend.core.conf import settings +from backend.middleware.qwen import Qwen +from backend.middleware.tencent_hunyuan import Hunyuan +from backend.app.admin.schema.wx import DictLevel +from backend.app.ai.service.scene_sentence_service import scene_sentence_service +from backend.app.ai.model.image_task import ImageTaskStatus, ImageProcessingTask +from backend.app.ai.crud.image_task_crud import image_task_dao +from backend.app.ai.schema.image_task import CreateImageTaskParam +from backend.app.admin.service.points_service import points_service +from backend.app.ai.service.rate_limit_service import rate_limit_service +from backend.common.const import SENTENCE_CARD_COST, SENTENCE_TYPE_SCENE_SENTENCE, SENTENCE_TYPE_SCENE_DIALOGUE, SENTENCE_TYPE_SCENE_EXERCISE + + +class SentenceService: + @staticmethod + def _compose_prompt(payload: dict, mode: str) -> str: + base = ( + "你是英语教育场景的专业助手，需基于给定的图片场景信息和基础内容，扩展生成适配英语进阶学习者的「句型卡片、模拟场景对话、句型套用练习」结构化内容，所有内容需贴合场景、功能导向，无语义重复，且符合日常沟通逻辑。\n" + "输入信息如下（JSON）：\n" + f"{json.dumps(payload, ensure_ascii=False)}\n" + "输出要求：\n" + "1. 内容约束：基于基础句型扩展功能标签、场景说明，每句补充「发音提示（重音/连读）」\n" + "2. 格式约束：严格按照下方JSON结构输出，无额外解释，确保字段完整、值为数组/字符串类型。\n" + "3. 语言约束：所有英文内容符合日常沟通表达，无语法错误；中文翻译精准，场景说明简洁易懂（≤50字）。\n" + ) + if mode == SENTENCE_TYPE_SCENE_SENTENCE: + base = ( + "你是英语教育场景的专业助手，需基于给定的图片场景信息和基础内容，扩展生成适配英语进阶学习者的[场景句型]结构化内容，所有内容需贴合场景、功能导向，无语义重复，且符合日常沟通逻辑。\n" + "输入信息如下（JSON）：\n" + f"{json.dumps(payload, ensure_ascii=False)}\n" + "输出要求：\n" + "0. description是图片的详细描述，围绕描述展开后续的分析。\n" + "1. 内容约束：基于基础句型扩展功能标签、场景说明，每句补充「发音提示（重音/连读）」等输出结构中要求的内容，需符合现实生活和真实世界的习惯。\n" + "2. 格式约束：严格按照下方JSON结构输出，无额外解释，确保字段完整、值为数组/字符串类型。\n" + "3. 语言约束：所有英文内容符合日常沟通表达，无语法错误；中文翻译精准，场景说明简洁易懂（≤50字）。\n" + "4. 严格按照JSON结构输出，无额外解释，确保字段完整、值为数组/字符串类型，输出的 json 结构是：\n" + ) + struct = ( + """ +"sentence": { // 对象：场景句型模块（适配前端展示） +"total": 5, // 数字：句型数量(5-8) +"list": [ // 数组：场景句型列表（数量与total一致） +{ "seq": 1, // 数字：序号（1-8） +"sentence_en": "", // 字符串：英文句型, 使用输入信息中的 desc_en 与之顺序对应的句子 +"sentence_zh": "", // 字符串：中文翻译，使用输入信息中的 desc_zh 与之顺序对应的句子 +"function_tags": ["询问", "索要物品"], // 数组：功能标签（主+子） +"scene_explanation": "咖啡厅场景向店员礼貌索要菜单，比“Give me the menu”更得体", // 字符串：场景使用说明（≤50字） +"pronunciation_tip": "重音在menu /ˈmenjuː/，have a look at 连读为 /hævəlʊkæt/", // 字符串：发音提示（重音/连读） +"core_vocab": ["menu", "look"], // 数组：核心词汇 +"core_vocab_desc": ["n. 菜单", "v. 查看"], // 数组：核心词汇在此句型中的含义（与core_vocab顺序对应） +"collocations": ["have a look at + 物品（查看某物）"], // 数组：核心搭配 +"grammar_point": "情态动词Can表请求（非正式），主谓倒装结构：Can + 主语 + 动词原形", // 核心语法解析 +"common_mistakes": ["1. 漏介词at（Can I have a look the menu）", "2. look误读为/lʊk/（正确/luːk/）", "3. 忘记在look后加at（Can I have a look at the menu）", ...], // 数组：句型中语法或单词用法可能出错的地方，包括但不限于常见发音错误，场景语气不当，单词单复数错误，主谓倒装错误、省略介词、省略主语等语法错误； +"pragmatic_alternative": ["Could I have a look at the menu?（更礼貌，正式场景）", "May I see the menu?（更正式，高阶）", ...], // 语用替代表达 +"scene_transfer_tip": "迁移至餐厅场景：Can I have a look at the wine list?（把menu替换为wine list）", // 场景迁移提示 +"difficulty_tag": "intermediate", // 难度标签（beginner/intermediate/advanced） +"extended_example": ["Can I have a look at your phone?（向朋友借看手机，非正式场景）", ""], // 数组： 精简拓展例句 +"response_pairs": [], // 数组：对话回应搭配（3-4个核心回应，含肯定/否定/中性，带场景适配说明，设计意图：形成对话闭环，支持角色扮演/实际互动） +"fluency_hacks": "", // 字符串：口语流畅度技巧（≤30字，聚焦填充词/弱读/语气调节，设计意图：贴近母语者表达节奏，避免生硬卡顿） +"cultural_note": "", // 字符串：文化适配提示（≤40字，说明中外表达习惯差异，设计意图：避免文化误解，提升沟通得体性） +"practice_steps": [], // 数组：分阶练习步骤（3步，每步1句话，可操作，设计意图：提供明确学习路径，衔接输入与输出，提升口语落地能力） +"avoid_scenarios": "", // 字符串：避免使用场景（≤35字，明确禁忌场景+替代方案，设计意图：减少用错场合的尴尬，明确使用边界） +"self_check_list": [], // 数组：自我检测清单（3-4个可量化检查点，含语法/发音/流畅度维度，设计意图：提供即时自查工具，无需他人批改验证效果） +"tone_intensity": "", // 字符串：语气强度标注（≤35字，用“弱/中/强”+适用对象描述，设计意图：直观匹配语气与互动对象，避免语气不当） +"similar_sentence_distinction": "", // 字符串：相似句型辨析（≤40字，聚焦使用场景+核心差异，不搞复杂语法，设计意图：理清易混点，避免张冠李戴） +"speech_rate_tip": "", // 字符串：语速建议（≤25字，明确日常场景语速+关键部分节奏，设计意图：让表达更自然，提升沟通效率） +"personalized_tips": "" // 字符串：个性化学习提示（≤30字，分初学者/进阶者给出重点建议，设计意图：适配不同水平需求，提升学习针对性） +} ] } + """ + ) + return base + struct + if mode == SENTENCE_TYPE_SCENE_DIALOGUE: + struct = ( + """ +"dialog": { // 对象：模拟场景对话模块（适配前端对话交互） + "roleOptions": ["customer", "barista"], // 数组：可选角色（固定值：customer/barista） + "defaultRole": "customer", // 字符串：默认角色（customer/barista二选一） + "dialogRound": 2, // 数字：对话轮数（2-3轮） + "list": [ // 数组：对话轮次列表（数量与dialogRound一致） + { + "roundId": "dialog-001", // 字符串：轮次唯一ID + "speaker": "barista", // 字符串：本轮说话者（customer/barista） + "speakerEn": "Can I help you?", // 字符串：说话者英文内容 + "speakerZh": "请问需要点什么？", // 字符串：说话者中文翻译 + "responseOptions": [ // 数组：用户可选回应（固定3条） + { + "optionId": "resp-001", // 字符串：选项唯一ID + "optionEn": "I'd like to order a latte with less sugar.", // 字符串：选项英文内容 + "optionZh": "我想点一杯少糖的拿铁。", // 字符串：选项中文翻译 + "feedback": "✅ 完美！该句型是咖啡厅点餐核心表达，with精准补充饮品定制要求" // 字符串：选择后的交互反馈 + } + ] + } + ] +} + """ + ) + return base + "生成场景对话结构：" + struct + if mode == SENTENCE_TYPE_SCENE_EXERCISE: + struct = ( + """ +"sentencePractice": { // 对象：句型套用练习模块（适配前端填空练习） + "total": 5, // 数字：练习数量（5-8道） + "list": [ // 数组：练习列表（数量与total一致） + { + "practiceId": "practice-001", // 字符串：练习唯一ID + "baseSentenceEn": "I'd like to order ______", // 字符串：基础句型框架（挖空） + "baseSentenceZh": "我想点______", // 字符串：框架中文翻译 + "keywordPool": [ // 数组：可选关键词池（3-4个） + { + "wordEn": "latte", // 字符串：英文关键词 + "wordZh": "拿铁", // 字符串：中文翻译 + "type": "drink" // 字符串：词汇类型（drink/custom/food等） + } + ], + "wrongTips": [ // 数组：常见错误提示（2-3条） + "错误：order + bread（面包）→ 咖啡厅场景中order后优先接饮品，面包需用“have”搭配" + ], + "extendScene": { // 对象：拓展场景（迁移练习） + "sceneTag": "milk_tea_shop", // 字符串：拓展场景标签 + "extendSentenceEn": "I'd like to order ______", // 字符串：拓展句型框架 + "extendKeywordPool": ["milk tea", "taro balls", "sugar-free"] // 数组：拓展关键词池 + } + } + ] + """ + ) + return base + "生成句型练习结构：" + struct + return base + + @staticmethod + async def generate_scene_sentence(image_id: int, user_id: int, payload: dict) -> dict: + if "user_level" not in payload: + payload["user_level"] = "intermediate" + prompt = SentenceService._compose_prompt(payload, SENTENCE_TYPE_SCENE_SENTENCE) + start_at = datetime.now() + res = await Hunyuan.chat( + messages=[{"role": "user", "content": prompt}], + image_id=image_id, + user_id=user_id, + system_prompt=None, + chat_type=SENTENCE_TYPE_SCENE_SENTENCE + ) + if not res.get("success"): + return None + image_chat_id = res.get("image_chat_id") + parsed = {} + try: + parsed = json.loads(res.get("result")) if isinstance(res.get("result"), str) else res.get("result", {}) + except Exception: + parsed = {} + + print(parsed) + items = [] + sc = parsed.get("sentence") or {} + for idx, d in enumerate(sc.get("list", []), start=1): + items.append({ + "seq": d.get("seq") or idx, + "sentence_en": d.get("sentence_en") or d.get("sentenceEn",""), + "sentence_zh": d.get("sentence_zh") or d.get("sentenceZh",""), + "function_tags": d.get("function_tags") or d.get("functionTags", []), + "scene_explanation": d.get("scene_explanation") or d.get("sceneExplanation", ""), + "pronunciation_tip": d.get("pronunciation_tip") or d.get("pronunciationTip", ""), + "pronunciation_url": d.get("pronunciation_url"), + "core_vocab": payload.get("core_vocab") or payload.get("coreVocab") or [], + "core_vocab_desc": d.get("core_vocab_desc") or [], + "collocations": payload.get("collocations", []), + "grammar_point": d.get("grammar_point"), + "common_mistakes": d.get("common_mistakes"), + "pragmatic_alternative": d.get("pragmatic_alternative") or [], + "scene_transfer_tip": d.get("scene_transfer_tip"), + "difficulty_tag": d.get("difficulty_tag") or "intermediate", + "extended_example": d.get("extended_example"), + "response_pairs": d.get("response_pairs") or d.get("responsePairs") or [], + "fluency_hacks": d.get("fluency_hacks") or d.get("fluencyHacks"), + "cultural_note": d.get("cultural_note") or d.get("culturalNote"), + "practice_steps": d.get("practice_steps") or d.get("practiceSteps") or [], + "avoid_scenarios": d.get("avoid_scenarios") or d.get("avoidScenarios"), + "self_check_list": d.get("self_check_list") or d.get("selfCheckList") or [], + "tone_intensity": d.get("tone_intensity") or d.get("toneIntensity"), + "similar_sentence_distinction": d.get("similar_sentence_distinction") or d.get("similarSentenceDistinction"), + "speech_rate_tip": d.get("speech_rate_tip") or d.get("speechRateTip"), + "personalized_tips": d.get("personalized_tips") or d.get("personalizedTips"), + }) + return await scene_sentence_service.create_session_with_items( + image_id=image_id, + user_id=user_id, + image_chat_id=image_chat_id, + scene_tag=payload.get("scene_tag") or [], + items=items, + called_at=start_at + ) + + @staticmethod + async def generate_scene_dialogue(image_id: int, user_id: int, scene_tag: str, desc_en: List[str], desc_zh: List[str], core_vocab: List[str], collocations: List[str]) -> List[SentenceCard]: + payload = { + "scene_tag": scene_tag, + "desc_en": desc_en, + "desc_zh": desc_zh, + "core_vocab": core_vocab, + "collocations": collocations, + "user_level": "intermediate" + } + prompt = SentenceService._compose_prompt(payload, SENTENCE_TYPE_SCENE_DIALOGUE) + start_at = datetime.now() + res = await Hunyuan.chat( + messages=[{"role": "user", "content": prompt}], + image_id=image_id, + user_id=user_id, + system_prompt=None, + chat_type=SENTENCE_TYPE_SCENE_DIALOGUE + ) + if not res.get("success"): + return None + image_chat_id = res.get("image_chat_id") + parsed = {} + try: + parsed = json.loads(res.get("result")) if isinstance(res.get("result"), str) else res.get("result", {}) + except Exception: + parsed = {} + items = [] + sc = parsed.get("sentenceCard") or {} + for d in sc.get("list", []): + sid = f"card-{int(start_at.timestamp())}" + items.append({ + "sentenceId": sid, + "sentenceEn": d.get("sentenceEn"), + "sentenceZh": d.get("sentenceZh"), + "functionTags": d.get("functionTags") or [], + "sceneExplanation": d.get("sceneExplanation") or "", + "pronunciationTip": d.get("pronunciationTip"), + "coreVocab": d.get("coreVocab") or core_vocab, + "collocations": d.get("collocations") or collocations + }) + created: List[SentenceCard] = [] + async with async_db_session.begin() as db: + image = await image_dao.get(db, image_id) + for item in items: + card = await sentence_card_dao.create(db, { + "image_id": image_id, + "user_id": user_id, + "image_chat_id": image_chat_id, + "card_type": SENTENCE_TYPE_SCENE_SENTENCE, + "scene_tag": scene_tag, + "details": json.dumps(item, ensure_ascii=False), + "called_at": start_at, + }) + created.append(card) + return created + + @staticmethod + async def generate_sentence_exercise_card(image_id: int, user_id: int, scene_tag: str, desc_en: List[str], desc_zh: List[str], core_vocab: List[str], collocations: List[str]) -> List[SentenceCard]: + start_at = datetime.now() + items = [] + max_len = min(len(desc_en or []), len(desc_zh or [])) + for idx in range(max_len): + sid = f"card-{int(start_at.timestamp())}" + items.append({ + "sentenceId": sid, + "sentenceEn": desc_en[idx], + "sentenceZh": desc_zh[idx], + "functionTags": [], + "sceneExplanation": "", + "pronunciationTip": None, + "coreVocab": core_vocab, + "collocations": collocations + }) + created: List[SentenceCard] = [] + async with async_db_session.begin() as db: + image = await image_dao.get(db, image_id) + for item in items: + card = await sentence_card_dao.create(db, { + "image_id": image_id, + "user_id": user_id, + "image_chat_id": None, + "card_type": SENTENCE_TYPE_SCENE_EXERCISE, + "scene_tag": scene_tag, + "details": json.dumps(item, ensure_ascii=False), + "called_at": start_at, + }) + created.append(card) + return created + + @staticmethod + async def create_scene_task(image_id: int, user_id: int, scene_type: str) -> dict: + from backend.common.exception import errors + if not await points_service.check_sufficient_points(user_id, SENTENCE_CARD_COST): + raise errors.ForbiddenError(msg='积分不足，请充值以继续使用') + slot_acquired = await rate_limit_service.acquire_task_slot(user_id) + if not slot_acquired: + max_tasks = await rate_limit_service.get_user_task_limit(user_id) + raise errors.ForbiddenError(msg=f'用户同时最多只能运行 {max_tasks} 个任务，请等待现有任务完成后再试') + if scene_type not in (SENTENCE_TYPE_SCENE_DIALOGUE, SENTENCE_TYPE_SCENE_EXERCISE, SENTENCE_TYPE_SCENE_SENTENCE): + raise errors.BadRequestError(msg=f'不支持的任务类型 {scene_type}') + async with async_db_session.begin() as db: + image = await image_dao.get(db, image_id) + if not image: + raise errors.NotFoundError(msg='图片不存在') + dict_level = DictLevel.LEVEL2.value + task_params = CreateImageTaskParam( + image_id=image_id, + user_id=user_id, + status=ImageTaskStatus.PENDING, + dict_level=dict_level, + ref_type=scene_type, + ref_id=image_id, + ) + task = await image_task_dao.create_task(db, task_params) + await db.flush() + task_id = task.id + await db.commit() + import asyncio + asyncio.create_task(SentenceService._process_scene_task(task_id, user_id)) + return {"task_id": str(task_id), "status": "accepted"} + + @staticmethod + async def _process_scene_task(task_id: int, user_id: int) -> None: + from backend.common.log import log as logger + task_processing_success = False + points_deducted = False + try: + async with background_db_session() as db: + task = await image_task_dao.get(db, task_id) + image = await image_dao.get(db, task.image_id) + if not image or not image.details or "recognition_result" not in image.details: + raise Exception("Image Recognition result not found") + recognition = image.details["recognition_result"] + scene_tag = recognition.get("scene_tag") or image.details.get("scene_tag") or [] + description = recognition.get("description") or "" + level2 = recognition.get("level2") or {} + desc_en = level2.get("desc_en", []) + desc_zh = level2.get("desc_zh", []) + core_vocab = level2.get("core_vocab", []) + collocations = level2.get("collocations", []) + if task.ref_type == SENTENCE_TYPE_SCENE_DIALOGUE: + cards = await SentenceService.generate_scene_dialogue(task.image_id, task.user_id, scene_tag, desc_en, desc_zh, core_vocab, collocations) + elif task.ref_type == SENTENCE_TYPE_SCENE_EXERCISE: + cards = await SentenceService.generate_sentence_exercise_card(task.image_id, task.user_id, scene_tag, desc_en, desc_zh, core_vocab, collocations) + elif task.ref_type == SENTENCE_TYPE_SCENE_SENTENCE: + payload = { + "description": description, + "scene_tag": scene_tag, + "desc_en": desc_en, + "desc_zh": desc_zh, + "core_vocab": core_vocab, + "collocations": collocations, + "user_level": "intermediate", + } + cards = await SentenceService.generate_scene_sentence(task.image_id, task.user_id, payload) + else: + raise Exception(f"Unsupported card type: {task.ref_type}") + async with background_db_session() as db: + await db.begin() + image = await image_dao.get(db, task.image_id) + points_deducted = await points_service.deduct_points_with_db( + user_id=task.user_id, + amount=SENTENCE_CARD_COST, + db=db, + related_id=image.id if image else None, + details={"task_id": task_id, "sentence_type": task.ref_type}, + action=task.ref_type + ) + if not points_deducted: + raise Exception("Failed to deduct points") + from backend.app.ai.tasks import update_task_status_with_retry + await update_task_status_with_retry(db, task_id, ImageTaskStatus.COMPLETED, result={"count": len(cards)}) + await db.commit() + task_processing_success = True + except Exception as e: + logger.error(f"Error processing sentence card task {task_id}: {str(e)}") + try: + async with background_db_session() as db: + await db.begin() + from backend.app.ai.tasks import update_task_status_with_retry + await update_task_status_with_retry(db, task_id, ImageTaskStatus.FAILED, error_message=str(e)) + await db.commit() + except Exception: + pass + finally: + try: + await rate_limit_service.release_task_slot(user_id) + except Exception: + pass + + @staticmethod + async def get_task_status(task_id: int) -> dict: + async with async_db_session() as db: + from backend.common.exception import errors + task = await image_task_dao.get(db, task_id) + if not task: + raise errors.NotFoundError(msg="Task not found") + response = { + "task_id": str(task.id), + "ref_type": task.ref_type, + "ref_id": str(task.ref_id), + "status": task.status, + "error_message": None, + } + if task.status == ImageTaskStatus.FAILED: + response["error_message"] = task.error_message + return response + + @staticmethod + async def get_latest_scene_sentence(image_id: int, user_id: int) -> dict | None: + async with async_db_session() as db: + sentence = await scene_sentence_dao.get_latest_by_image_and_user(db, image_id, user_id) + if not sentence: + return None + items = await scene_sentence_item_dao.get_by_session(db, sentence.id) + payload_items = [] + for it in items: + ext = it.ext or {} + payload_items.append({ + "seq": it.seq, + "sentenceEn": it.sentence_en, + "sentenceZh": it.sentence_zh, + "functionTags": it.function_tags or [], + "sceneExplanation": ext.get("scene_explanation") or "", + "pronunciationTip": ext.get("pronunciation_tip"), + "coreVocab": it.core_vocab or [], + "coreVocabDesc": ext.get("core_vocab_desc") or [], + "collocations": it.collocations or [], + "grammarPoint": ext.get("grammar_point"), + "commonMistakes": ext.get("common_mistakes"), + "pragmaticAlternative": ext.get("pragmatic_alternative") or [], + "sceneTransferTip": ext.get("scene_transfer_tip"), + "difficultyTag": ext.get("difficulty_tag"), + "extendedExample": ext.get("extended_example"), + "responsePairs": ext.get("response_pairs") or [], + "fluencyHacks": ext.get("fluency_hacks"), + "culturalNote": ext.get("cultural_note"), + "practiceSteps": ext.get("practice_steps") or [], + "avoidScenarios": ext.get("avoid_scenarios"), + "selfCheckList": ext.get("self_check_list") or [], + "toneIntensity": ext.get("tone_intensity"), + "similarSentenceDistinction": ext.get("similar_sentence_distinction"), + "speechRateTip": ext.get("speech_rate_tip"), + "personalizedTips": ext.get("personalized_tips"), + "imageTextId": str(it.image_text_id) if it.image_text_id is not None else None, + }) + return { + "id": str(sentence.id), + "image_id": str(sentence.image_id), + "user_id": str(sentence.user_id), + "scene_tag": sentence.scene_tag, + "total": len(payload_items), + "list": payload_items, + } + + +sentence_service = SentenceService() diff --git a/backend/common/const.py b/backend/common/const.py index d718052..c2a7367 100644 --- a/backend/common/const.py +++ b/backend/common/const.py @@ -5,6 +5,7 @@ IMAGE_RECOGNITION_COST = 10 # 0.0015/1000 * 10 # Speech assessment service cost in points SPEECH_ASSESSMENT_COST = 1 +SENTENCE_CARD_COST = 2 # Points action types POINTS_ACTION_SYSTEM_GIFT = "system_gift" @@ -20,3 +21,7 @@ POINTS_ACTION_REFUND_DEDUCT = "refund_deduct" API_TYPE_RECOGNITION = 'recognition' FREE_TRIAL_BALANCE = 30 + +SENTENCE_TYPE_SCENE_DIALOGUE = "scene_dialogue" +SENTENCE_TYPE_SCENE_EXERCISE = "scene_exercise" +SENTENCE_TYPE_SCENE_SENTENCE = "scene_sentence" diff --git a/backend/core/conf.py b/backend/core/conf.py index e7ec239..06e4562 100755 --- a/backend/core/conf.py +++ b/backend/core/conf.py @@ -56,6 +56,10 @@ class Settings(BaseSettings): API_TIMEOUT: int = 600 ASYNC_POLL_INTERVAL: int = 1 ASYNC_MODE: str = "enable" + HUNYUAN_MODLE: str + HUNYUAN_APP_ID: str + HUNYUAN_SECRET_ID: str + HUNYUAN_SECRET_KEY: str TENCENT_CLOUD_APP_ID: str TENCENT_CLOUD_SECRET_ID: str TENCENT_CLOUD_SECRET_KEY: str diff --git a/backend/core/registrar.py b/backend/core/registrar.py index f00091d..728b9fa 100755 --- a/backend/core/registrar.py +++ b/backend/core/registrar.py @@ -180,4 +180,4 @@ def register_page(app: FastAPI): :param app: :return: """ - add_pagination(app) \ No newline at end of file + add_pagination(app) diff --git a/backend/main.py b/backend/main.py index 29058ee..9903c07 100755 --- a/backend/main.py +++ b/backend/main.py @@ -12,13 +12,15 @@ from random import sample from string import ascii_letters, digits from wechatpayv3 import WeChatPay, WeChatPayType from backend.app.admin.tasks import wx_user_index_history +from backend.app.ai.service.sentence_service import SentenceService app = register_app() @app.get("/") async def read_root(): - # await wx_user_index_history() + await wx_user_index_history() + # res = await SentenceService()._process_scene_task(2111026809104629760, 2108963527040565248) return {"Hello": f"World, {datetime.now().isoformat()}"} diff --git a/backend/middleware/qwen.py b/backend/middleware/qwen.py index 4a6f0b3..b798248 100755 --- a/backend/middleware/qwen.py +++ b/backend/middleware/qwen.py @@ -80,47 +80,55 @@ Core objective: Analyze the image based on its PRIMARY SCENE (e.g., office, rest level1 (Beginner): - Learning goal: Recognize core vocabulary + use basic functional sentences (describe objects/scenes, simple requests) - Vocab: High-frequency daily words (no uncommon words) -- Grammar: Simple present/past tense, basic SV/SVO structure -- Word count per sentence: ~10 words -- Sentence type: 6 unique functional types (describe object, simple request, state fact, point out location, express preference, ask simple question) +- Grammar: Present continuous, modal verbs (can/could/would), simple clauses +- Word count per sentence: ≤15 words +- Sentence type: 6 unique functional types (detailed description, polite request, ask for information, suggest action, state need, confirm fact, express feeling) +- The sentence structure of the described object: quantity + name + feature + purpose. level2 (Intermediate): - Learning goal: Master scene-specific collocations + practical communication sentences (daily/office interaction) - Vocab: Scene-specific common words + fixed collocations (e.g., "print a document", "place an order") -- Grammar: Present continuous, modal verbs (can/could/would), simple clauses -- Word count per sentence: 15-20 words -- Sentence type: 7 unique functional types (detailed description, polite request, ask for information, suggest action, state need, confirm fact, express feeling) - -level3 (Advanced): -- Learning goal: Use professional/scene-specific uncommon words + context-aware pragmatic expressions (with tone/formality differences) -- Vocab: Scene-specific professional words (e.g., "barista" for café, "agenda" for meeting) + advanced collocations - Grammar: Complex clauses, passive voice, subjunctive mood (as appropriate to the scene) - Word count per sentence: ≤25 words -- Sentence type: 8 unique functional types (detailed scene analysis, formal/informal contrast, conditional statement, explain purpose, ask follow-up questions, express suggestion, summarize information, clarify meaning) +- Sentence type: 8-12 unique functional types (detailed scene analysis, formal/informal contrast, conditional statement, explain purpose, ask follow-up questions, express suggestion, summarize information, clarify meaning) // Output Requirements 1. JSON Structure (add core vocab/collocation for easy parsing): { - "scene_tag": "xxx", // e.g., "office", "café", "supermarket" (primary scene of the image) + "scene_tag": ["xxx", "xxx"], // e.g., "office", "café", "supermarket" (Multiple tags that are consistent with the main scene of the picture) + "description": "", // Clear and accurate description of the content of the picture, including but not limited to objects, relationships, colors, etc. "level1": { - "desc_en": ["sentence1", "sentence2", ...], // 6 unique sentences (no repeated semantics/functions) - "desc_zh": ["translation1", "translation2", ...], // one-to-one with desc_en - "core_vocab": ["word1", "word2", ...], // 3-5 core high-frequency words from LEVEL1 sentences - "collocations": ["word1 + collocation1", ...] // 2-3 fixed collocations (e.g., "sit + on a chair") + "desc_en": ["sentence1", "sentence2", ...], // 6 to 8 distinct sentences with different modalities (without repeating the same meaning or function. Don't use Chinese. Consistent with native English speakers' daily communication habits) + "desc_zh": ["translation1", "translation2", ...], // one-to-one with desc_en, chinese translation must be natural and not stiff, consistent with native English speakers' daily communication habits. }, - "level2": { - "desc_en": ["sentence1", ...], // 7 unique sentences - "desc_zh": ["translation1", ...], - "core_vocab": ["word1", ...], // 4-6 scene-specific words - "collocations": ["collocation1", ...] // 3-4 scene-specific collocations - }, - "level3": { - "desc_en": ["sentence1", ...], // 8 unique sentences - "desc_zh": ["translation1", ...], - "core_vocab": ["word1", ...], // 5-7 professional/uncommon words - "collocations": ["collocation1", ...], // 4-5 advanced collocations - "pragmatic_notes": ["note1", ...] // 1-2 notes on tone/formality (e.g., "Could you..." is politer than "Can you...") - } +"level2": { + "desc_en": [ + "Requirement: 8-12 daily spoken English sentences matching the image scenario (prioritize short sentences, ≤20 words)", + "Type: Declarative sentences / polite interrogative sentences that can be used directly (avoid formal language and complex clauses)", + "Scenario Adaptation: Strictly align with the real-life scenario shown in the image (e.g., restaurant ordering, asking for directions on the subway, chatting with friends, etc.)", + "Core Principle: Natural and not stiff, consistent with native English speakers' daily communication habits (e.g., prefer \"How's it going?\" over \"How are you recently?\")" + ], + "desc_zh": [ + "Requirement: Colloquial Chinese translations of the corresponding English sentences", + "Principle: Avoid literal translations and formal expressions; conform to daily Chinese speaking habits (e.g., translate \"Could you pass the salt?\" as \"能递下盐吗？\" instead of \"你能把盐递给我吗？\")", + "Adaptability: Translations should fit the logical expression of Chinese scenarios (e.g., more polite for workplace communication, more casual for friend chats)" + ], + "core_vocab": [ + "Requirement: 5-8 core spoken words for the scenario", + "Standard: High-frequency daily use (avoid rare words and academic terms); can directly replace key words in sentences for reuse", + "Example: For the \"supermarket shopping\" scenario, prioritize words like \"discount, check out, cart\" that can be directly applied to sentences" + ], + "collocations": [ + "Requirement: 5-8 high-frequency spoken collocations for the scenario", + "Standard: Short and practical fixed collocations; can be used by directly replacing core words (avoid complex phrases)", + "Example: For the \"food delivery ordering\" scenario, collocations include \"order food, pick up the phone (for delivery calls), track the order\"" + ], + "pragmatic_notes": [ + "Requirement: 2-4 scenario-specific pragmatic notes (avoid general descriptions)", + "Content: Clear usage scenarios + tone adaptation + practical skills (e.g., \"Suitable for chatting with friends; casual tone; starting with the filler word 'actually' makes it more natural\")", + "Practical Value: Include \"replacement skills\" (e.g., \"Sentence pattern 'I'm in the mood for + [food]' can be used by directly replacing the food noun\")" + ] + } } 2. Uniqueness: No repetition in SEMANTICS/FUNCTIONS (not just literal repetition) — e.g., avoid two sentences both meaning "This is a laptop" (even with different wording). 3. Focus: Prioritize ARTIFICIAL/CENTRAL objects and PRIMARY scene (ignore trivial background elements) — e.g., for a café image, focus on "coffee", "barista", "menu" (not "wall", "floor"). @@ -543,9 +551,14 @@ level3 (Advanced): def _log_audit(api_type: str, model_name: str, request_data: dict, response_data: dict, duration: float, status_code: int, error_message: str | None = None, dict_level: str | None = None, - image_id: int = 0, user_id: int = 0, called_at: datetime | None = None): + image_id: int = 0, user_id: int = 0, called_at: datetime | None = None, + ref_type: str | None = None, ref_id: int | None = None): """记录API调用审计日志""" - token_usage = response_data.get("usage", {}) + raw_usage = response_data.get("usage", {}) + pt = raw_usage.get("input_tokens") or raw_usage.get("prompt_tokens") or 0 + ct = raw_usage.get("output_tokens") or raw_usage.get("completion_tokens") or 0 + tt = raw_usage.get("total_tokens") or (pt + ct) + token_usage = {"prompt_tokens": int(pt or 0), "completion_tokens": int(ct or 0), "total_tokens": int(tt or 0)} cost = Qwen._calculate_cost(api_type, token_usage) @@ -564,6 +577,8 @@ level3 (Advanced): called_at=called_at or datetime.now(), api_version=settings.FASTAPI_API_V1_PATH, dict_level=dict_level, + ref_type=ref_type, + ref_id=ref_id, ) try: # Use background tasks for audit logging to avoid blocking @@ -595,4 +610,4 @@ level3 (Advanced): # Run in background without blocking asyncio.create_task(_create_audit_log()) except Exception as e: - logger.error(f"Failed to save audit log: {str(e)}") \ No newline at end of file + logger.error(f"Failed to save audit log: {str(e)}") diff --git a/backend/middleware/tencent_hunyuan.py b/backend/middleware/tencent_hunyuan.py new file mode 100644 index 0000000..06300eb --- /dev/null +++ b/backend/middleware/tencent_hunyuan.py @@ -0,0 +1,177 @@ +import asyncio +import json +import time +from concurrent.futures import ThreadPoolExecutor +from datetime import datetime + +from tencentcloud.common.common_client import CommonClient +from tencentcloud.common import credential +from tencentcloud.common.exception.tencent_cloud_sdk_exception import TencentCloudSDKException +from tencentcloud.common.profile.client_profile import ClientProfile +from tencentcloud.common.profile.http_profile import HttpProfile + +from backend.core.conf import settings +from backend.common.log import log as logger +from backend.app.admin.schema.audit_log import CreateAuditLogParam +from backend.app.admin.service.audit_log_service import audit_log_service +from backend.app.ai.schema.image_chat import CreateImageChatParam +from backend.app.ai.service.image_chat_service import image_chat_service + + +class NonStreamResponse(object): + def __init__(self): + self.response = "" + + def _deserialize(self, obj): + self.response = json.dumps(obj) + + +class Hunyuan: + _executor = ThreadPoolExecutor(max_workers=10) + + @staticmethod + async def chat(messages: list[dict], image_id: int, user_id: int, system_prompt: str | None = None, chat_type: str | None = "general") -> dict: + start_time = time.time() + start_at = datetime.now() + status_code = 500 + error_message = "" + response_data: dict = {} + try: + cred = credential.Credential(settings.HUNYUAN_SECRET_ID, settings.HUNYUAN_SECRET_KEY) + httpProfile = HttpProfile() + httpProfile.endpoint = "hunyuan.tencentcloudapi.com" + try: + httpProfile.reqTimeout = int(getattr(settings, "API_TIMEOUT", 600)) + except Exception: + httpProfile.reqTimeout = 600 + clientProfile = ClientProfile() + clientProfile.httpProfile = httpProfile + + _msg = ([{"Role": "system", "Content": system_prompt}] if system_prompt else []) + [ + {"Role": m.get("role"), "Content": m.get("content")} for m in (messages or []) + ] + req_body = { + "Model": settings.HUNYUAN_MODLE, + "Messages": _msg, + "Stream": False, + } + + loop = asyncio.get_event_loop() + resp = await loop.run_in_executor( + Hunyuan._executor, + lambda: CommonClient("hunyuan", "2023-09-01", cred, "", profile=clientProfile)._call_and_deserialize( + "ChatCompletions", req_body, NonStreamResponse + ) + ) + + if isinstance(resp, NonStreamResponse): + status_code = 200 + response_data = json.loads(resp.response) + else: + status_code = 200 + chunks = [] + for event in resp: + chunks.append(event) + response_data = {"stream": True, "events": chunks} + + duration = time.time() - start_time + token_usage = response_data.get("Usage") or response_data.get("usage") or {} + model_name = settings.HUNYUAN_MODLE + + image_chat_id = None + try: + chat = await image_chat_service.create_conversation({ + "chat_type": chat_type or "general", + "model_name": model_name, + "image_id": image_id, + "user_id": user_id, + "ext": {"module": chat_type or "general"}, + }) + if chat: + image_chat_id = chat.id + msg = await image_chat_service.append_turn(chat.id, { + "model_name": model_name, + "messages": {"messages": req_body.get("Messages")}, + "response_data": response_data, + "token_usage": ( + {"prompt_tokens": (token_usage.get("PromptTokens") or token_usage.get("prompt_tokens") or token_usage.get("input_tokens") or 0), + "completion_tokens": (token_usage.get("CompletionTokens") or token_usage.get("completion_tokens") or token_usage.get("output_tokens") or 0), + "total_tokens": (token_usage.get("TotalTokens") or token_usage.get("total_tokens") or token_usage.get("total") or + ((token_usage.get("PromptTokens") or token_usage.get("prompt_tokens") or 0) + + (token_usage.get("CompletionTokens") or token_usage.get("completion_tokens") or 0)))} + if isinstance(token_usage, dict) else {} + ), + "duration": duration, + "status_code": status_code, + "error_message": error_message or None, + "called_at": start_at, + "ext": {"module": chat_type or "general"}, + }) + norm_usage = {} + if isinstance(token_usage, dict): + pt = token_usage.get("PromptTokens") or token_usage.get("prompt_tokens") or token_usage.get("input_tokens") or 0 + ct = token_usage.get("CompletionTokens") or token_usage.get("completion_tokens") or token_usage.get("output_tokens") or 0 + tt = token_usage.get("TotalTokens") or token_usage.get("total_tokens") or token_usage.get("total") or (pt + ct) + norm_usage = {"prompt_tokens": int(pt or 0), "completion_tokens": int(ct or 0), "total_tokens": int(tt or 0)} + audit_log = CreateAuditLogParam( + api_type="chat", + model_name=model_name, + response_data=response_data, + request_data=req_body, + token_usage=norm_usage, + duration=duration, + status_code=status_code, + error_message=error_message, + called_at=start_at, + image_id=image_id, + user_id=user_id, + cost=0, + api_version=settings.FASTAPI_API_V1_PATH, + dict_level=None, + ref_type="image_chat_msg", + ref_id=(msg.id if chat and msg else None), + ) + await audit_log_service.create(obj=audit_log) + except Exception as e: + logger.error(f"save image chat failed: {str(e)}") + + result_text = "" + try: + if "Choices" in response_data: + choices = response_data["Choices"] + if isinstance(choices, list) and choices: + msg = choices[0].get("Message", {}) + result_text = msg.get("Content", "") + elif "output" in response_data: + choices = response_data["output"].get("choices", []) + if isinstance(choices, list) and choices: + msg = choices[0].get("message", {}) + content = msg.get("content", "") + if isinstance(content, list): + result_text = " ".join([seg.get("text", "") for seg in content if isinstance(seg, dict)]) + elif isinstance(content, str): + result_text = content + except Exception: + pass + + return { + "success": True, + "result": result_text, + "token_usage": token_usage, + "image_chat_id": image_chat_id, + } + + except TencentCloudSDKException as err: + error_message = str(err) + logger.exception(f"hunyuan chat exception: {error_message}") + return { + "success": False, + "error": error_message, + } + except Exception as e: + error_message = str(e) + logger.exception(f"hunyuan chat exception: {error_message}") + return { + "success": False, + "error": error_message, + } diff --git a/backend/middleware/test.py b/backend/middleware/test.py index 320dd16..4d8baa6 100644 --- a/backend/middleware/test.py +++ b/backend/middleware/test.py @@ -120,4 +120,8 @@ # # process(0) # # 录音识别 # process_rec(0) -# # process_multithread(20) \ No newline at end of file +# # process_multithread(20) +import re +desc_words = "a well-food." +words = set(re.findall(r'\b[\w-]+\b', desc_words.lower())) +print(words) \ No newline at end of file diff --git a/deploy/app_server.conf b/deploy/app_server.conf index 8398b89..4da3c85 100755 --- a/deploy/app_server.conf +++ b/deploy/app_server.conf @@ -1,9 +1,9 @@ -[program:app_server] -directory=/app -command=/usr/local/bin/gunicorn -c /app/deploy/gunicorn.conf.py main:app -user=root -autostart=true -autorestart=true -startretries=5 -redirect_stderr=true -stdout_logfile=/var/log/app_server/app_server.log +[program:app_server] +directory=/app +command=/bin/sh -lc 'alembic -c backend/alembic.ini upgrade head && /usr/local/bin/gunicorn -c /app/deploy/gunicorn.conf.py main:app' +user=root +autostart=true +autorestart=true +startretries=5 +redirect_stderr=true +stdout_logfile=/var/log/app_server/app_server.log diff --git a/requirements.txt b/requirements.txt index 4fb70a8..912cee3 100755 --- a/requirements.txt +++ b/requirements.txt @@ -257,6 +257,7 @@ starlette==0.46.1 # asgi-correlation-id # fastapi termcolor==2.5.0 +tencentcloud-sdk-python-common==3.1.11 # via pytest-sugar tomli==2.2.1 ; python_full_version < '3.11' # via pytest @@ -322,4 +323,5 @@ zope-event==5.0 zope-interface==7.2 # via gevent mysql-connector-python==8.0.33 # Added MySQL connector - # via fastapi-best-architecture \ No newline at end of file + # via fastapi-best-architecture +pymysql==1.1.2 \ No newline at end of file