bangbang-aigc-server/travel-algorithms/travel_algorithms/__init__.py

#!/usr/bin/env python3
# -*- coding: utf-8 -*-

"""
Travel Algorithms Package
AI驱动的旅游内容生成算法包

这个包提供了一套完整的AI算法，用于生成旅游相关的内容，包括：
- 主题生成
- 内容创作
- 内容审核
- 海报生成
- 文档处理

特性：
- 配置化设计，支持动态提示词加载
- JSON修复和格式化
- 支持多种AI模型和参数
- 灵活的输出管理
- 完整的错误处理
"""

__version__ = "1.0.0"
__author__ = "Travel Content Creator Team"

# 核心配置和服务
from .config import (
    AlgorithmConfig,
    AIModelConfig,
    PromptConfig,
    ContentGenerationConfig,
    PosterGenerationConfig,
    DocumentProcessingConfig,
    OutputConfig,
    ResourceConfig,
    TaskModelConfig
)

from .core import (
    AIService,
    OutputManager,
    PromptManager,
    JSONProcessor
)

# 算法模块
from .content_generation import (
    TopicGenerator,
    ContentGenerator,
    ContentJudger
)

# 海报生成算法
from .poster_generation import (
    PosterGenerator,
    TextGenerator,
    TemplateManager
)

# 文档处理算法
from .document_processing import (
    DocumentProcessor,
    TextExtractor,
    ContentIntegrator,
    ContentTransformer,
    ExtractedDocument,
    IntegratedContent,
    TransformedContent
)

# 网页爬虫算法
from .web_crawling import (
    XHSCrawler,
    XHSNote,
    XHSSearchResult,
    SearchConfig,
    KeywordAnalyzer,
    KeywordResult,
    ContentAnalyzer,
    AnalysisResult
)

# 异常类
from .exceptions import (
    AlgorithmError,
    ConfigError,
    AIServiceError,
    ContentGenerationError,
    PosterGenerationError,
    DocumentProcessingError,
    ResourceNotFoundError,
    ValidationError
)

# 便捷导入
__all__ = [
    # 版本信息
    "__version__",
    "__author__",
    
    # 配置类
    "AlgorithmConfig",
    "AIModelConfig",
    "PromptConfig",
    "ContentGenerationConfig",
    "PosterGenerationConfig", 
    "DocumentProcessingConfig",
    "WebCrawlingConfig",
    "KeywordAnalysisConfig",
    "ContentAnalysisConfig",
    "OutputConfig",
    "ResourceConfig",
    "TaskModelConfig",
    
    # 核心服务
    "AIService",
    "OutputManager",
    "PromptManager",
    "JSONProcessor",
    
    # 算法模块
    "TopicGenerator",
    "ContentGenerator", 
    "ContentJudger",
    "PosterGenerator",
    "TextGenerator",
    "TemplateManager",
    "DocumentProcessor",
    "TextExtractor",
    "ContentIntegrator",
    "ContentTransformer",
    "XHSCrawler",
    "KeywordAnalyzer",
    "ContentAnalyzer",
    
    # 数据模型
    "ExtractedDocument",
    "IntegratedContent",
    "TransformedContent",
    "XHSNote",
    "XHSSearchResult",
    "SearchConfig",
    "KeywordResult",
    "AnalysisResult",
    
    # 异常类
    "AlgorithmError",
    "ConfigError",
    "AIServiceError", 
    "ContentGenerationError",
    "PosterGenerationError",
    "DocumentProcessingError",
    "CrawlingError",
    "ResourceNotFoundError",
    "ValidationError",
    
    # 便捷功能
    "create_default_config",
    "create_content_pipeline",
    "create_poster_pipeline",
    "create_document_pipeline",
    "create_crawling_pipeline",
]


def create_default_config(
    resource_base_directory: str = None,
    ai_model: str = "qwq-plus",
    **kwargs
) -> AlgorithmConfig:
    """
    创建默认配置

    Args:
        resource_base_directory: 资源基础目录（可选）
        ai_model: AI模型名称
        **kwargs: 其他配置覆盖项

    Returns:
        配置实例
    """
    config_dict = {}
    
    if resource_base_directory:
        config_dict["resources"] = {
            "resource_base_directory": resource_base_directory
        }
    
    if ai_model != "qwq-plus":
        config_dict["ai_model"] = {
            "model": ai_model
        }
    
    # 应用其他覆盖项
    config_dict.update(kwargs)
    
    return AlgorithmConfig.from_dict(config_dict)


def create_content_pipeline(config: AlgorithmConfig = None) -> dict:
    """
    创建内容生成流水线

    Args:
        config: 算法配置（可选，默认使用默认配置）

    Returns:
        包含各个组件的字典
    """
    if config is None:
        config = create_default_config()
    
    return {
        "config": config,
        "topic_generator": TopicGenerator(config),
        "content_generator": ContentGenerator(config),
        "content_judger": ContentJudger(config),
        "ai_service": AIService(config.ai_model),
        "output_manager": OutputManager(config.output),
        "prompt_manager": PromptManager(config.prompts, config.resources),
        "json_processor": JSONProcessor(
            enable_repair=config.content_generation.enable_json_repair,
            max_repair_attempts=config.content_generation.json_repair_attempts
        )
    }


def create_poster_pipeline(config: AlgorithmConfig = None) -> dict:
    """
    创建海报生成流水线

    Args:
        config: 算法配置（可选，默认使用默认配置）

    Returns:
        包含海报生成组件的字典
    """
    if config is None:
        config = create_default_config()
    
    return {
        "config": config,
        "poster_generator": PosterGenerator(config),
        "text_generator": TextGenerator(
            config, 
            AIService(config.ai_model),
            PromptManager(config.prompts, config.resources),
            JSONProcessor(
                enable_repair=config.content_generation.enable_json_repair,
                max_repair_attempts=config.content_generation.json_repair_attempts
            )
        ),
        "template_manager": TemplateManager(config.poster_generation, config.resources),
        "ai_service": AIService(config.ai_model),
        "output_manager": OutputManager(config.output),
        "prompt_manager": PromptManager(config.prompts, config.resources),
        "json_processor": JSONProcessor(
            enable_repair=config.content_generation.enable_json_repair,
            max_repair_attempts=config.content_generation.json_repair_attempts
        )
    }


def create_document_pipeline(config: AlgorithmConfig = None) -> dict:
    """
    创建文档处理流水线

    Args:
        config: 算法配置（可选，默认使用默认配置）

    Returns:
        包含文档处理组件的字典
    """
    if config is None:
        config = create_default_config()
    
    return {
        "config": config,
        "document_processor": DocumentProcessor(config),
        "text_extractor": TextExtractor(config.document_processing),
        "content_integrator": ContentIntegrator(config.document_processing),
        "content_transformer": ContentTransformer(config),
        "ai_service": AIService(config.ai_model),
        "output_manager": OutputManager(config.output),
        "prompt_manager": PromptManager(config.prompts, config.resources),
        "json_processor": JSONProcessor(
            enable_repair=config.content_generation.enable_json_repair,
            max_repair_attempts=config.content_generation.json_repair_attempts
        )
    }


def create_crawling_pipeline(config: AlgorithmConfig = None) -> dict:
    """
    创建爬虫分析流水线

    Args:
        config: 算法配置（可选，默认使用默认配置）

    Returns:
        包含爬虫分析组件的字典
    """
    if config is None:
        config = create_default_config()
    
    return {
        "config": config,
        "xhs_crawler": XHSCrawler(config.web_crawling),
        "keyword_analyzer": KeywordAnalyzer(config),
        "content_analyzer": ContentAnalyzer(config),
        "ai_service": AIService(config.ai_model),
        "output_manager": OutputManager(config.output),
        "prompt_manager": PromptManager(config.prompts, config.resources),
        "json_processor": JSONProcessor(
            enable_repair=config.content_generation.enable_json_repair,
            max_repair_attempts=config.content_generation.json_repair_attempts
        )
    }

# 设置日志
import logging
logging.getLogger(__name__).addHandler(logging.NullHandler())