File size: 9,973 Bytes
ea53ae2 |
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 |
"""
外部服务抽象接口
为LLM、Embedding和VectorStore等外部依赖提供抽象层
"""
from abc import ABC, abstractmethod
from typing import Any, Dict, List, Optional, Union, Tuple
from dataclasses import dataclass
from enum import Enum
import asyncio
class ModelStatus(Enum):
"""模型状态枚举"""
AVAILABLE = "available"
UNAVAILABLE = "unavailable"
ERROR = "error"
RATE_LIMITED = "rate_limited"
@dataclass
class ModelInfo:
"""模型信息"""
name: str
provider: str
status: ModelStatus
capabilities: List[str]
context_length: Optional[int] = None
cost_per_token: Optional[float] = None
rate_limit: Optional[Dict[str, int]] = None
@dataclass
class ChatMessage:
"""聊天消息"""
role: str # "user", "assistant", "system"
content: str
timestamp: Optional[str] = None
metadata: Optional[Dict[str, Any]] = None
@dataclass
class ChatResponse:
"""聊天响应"""
content: str
model_used: str
tokens_used: Optional[int] = None
finish_reason: Optional[str] = None
metadata: Optional[Dict[str, Any]] = None
@dataclass
class EmbeddingResult:
"""嵌入结果"""
vectors: List[List[float]]
model_used: str
tokens_used: Optional[int] = None
metadata: Optional[Dict[str, Any]] = None
@dataclass
class DocumentChunk:
"""文档块"""
content: str
metadata: Dict[str, Any]
chunk_id: Optional[str] = None
source: Optional[str] = None
@dataclass
class SearchResult:
"""搜索结果"""
document: DocumentChunk
score: float
rank: int
class ILLMService(ABC):
"""大语言模型服务抽象接口"""
@abstractmethod
def get_available_models(self) -> List[ModelInfo]:
"""获取可用模型列表"""
pass
@abstractmethod
def chat(self,
messages: List[ChatMessage],
model: Optional[str] = None,
temperature: float = 0.7,
max_tokens: Optional[int] = None,
**kwargs) -> ChatResponse:
"""聊天对话"""
pass
@abstractmethod
async def chat_async(self,
messages: List[ChatMessage],
model: Optional[str] = None,
temperature: float = 0.7,
max_tokens: Optional[int] = None,
**kwargs) -> ChatResponse:
"""异步聊天对话"""
pass
@abstractmethod
def stream_chat(self,
messages: List[ChatMessage],
model: Optional[str] = None,
temperature: float = 0.7,
max_tokens: Optional[int] = None,
**kwargs):
"""流式聊天对话"""
pass
@abstractmethod
def get_model_status(self, model: str) -> ModelStatus:
"""获取模型状态"""
pass
@abstractmethod
def validate_connection(self) -> bool:
"""验证连接"""
pass
class IEmbeddingService(ABC):
"""嵌入服务抽象接口"""
@abstractmethod
def get_available_models(self) -> List[ModelInfo]:
"""获取可用嵌入模型列表"""
pass
@abstractmethod
def embed_texts(self,
texts: List[str],
model: Optional[str] = None,
**kwargs) -> EmbeddingResult:
"""文本嵌入"""
pass
@abstractmethod
async def embed_texts_async(self,
texts: List[str],
model: Optional[str] = None,
**kwargs) -> EmbeddingResult:
"""异步文本嵌入"""
pass
@abstractmethod
def embed_query(self,
query: str,
model: Optional[str] = None,
**kwargs) -> List[float]:
"""查询嵌入"""
pass
@abstractmethod
def get_embedding_dimension(self, model: Optional[str] = None) -> int:
"""获取嵌入维度"""
pass
@abstractmethod
def validate_connection(self) -> bool:
"""验证连接"""
pass
class IVectorStoreService(ABC):
"""向量存储服务抽象接口"""
@abstractmethod
def create_collection(self,
name: str,
dimension: int,
metadata: Optional[Dict[str, Any]] = None) -> bool:
"""创建集合"""
pass
@abstractmethod
def delete_collection(self, name: str) -> bool:
"""删除集合"""
pass
@abstractmethod
def list_collections(self) -> List[str]:
"""列出所有集合"""
pass
@abstractmethod
def add_documents(self,
collection_name: str,
documents: List[DocumentChunk],
embeddings: List[List[float]],
**kwargs) -> bool:
"""添加文档"""
pass
@abstractmethod
def search(self,
collection_name: str,
query_embedding: List[float],
top_k: int = 5,
filter_conditions: Optional[Dict[str, Any]] = None,
**kwargs) -> List[SearchResult]:
"""相似性搜索"""
pass
@abstractmethod
def delete_documents(self,
collection_name: str,
document_ids: List[str]) -> bool:
"""删除文档"""
pass
@abstractmethod
def get_collection_stats(self, collection_name: str) -> Dict[str, Any]:
"""获取集合统计信息"""
pass
@abstractmethod
def validate_connection(self) -> bool:
"""验证连接"""
pass
class IDocumentProcessorService(ABC):
"""文档处理服务抽象接口"""
@abstractmethod
def process_file(self,
file_path: str,
chunk_size: int = 1000,
chunk_overlap: int = 200,
**kwargs) -> List[DocumentChunk]:
"""处理文件并分块"""
pass
@abstractmethod
def extract_text(self, file_path: str, **kwargs) -> str:
"""提取文本内容"""
pass
@abstractmethod
def get_supported_formats(self) -> List[str]:
"""获取支持的文件格式"""
pass
@abstractmethod
def validate_file(self, file_path: str) -> Tuple[bool, Optional[str]]:
"""验证文件格式和大小"""
pass
class IMemoryService(ABC):
"""内存服务抽象接口"""
@abstractmethod
def save_conversation(self,
conversation_id: str,
messages: List[ChatMessage]) -> bool:
"""保存对话"""
pass
@abstractmethod
def load_conversation(self, conversation_id: str) -> List[ChatMessage]:
"""加载对话"""
pass
@abstractmethod
def delete_conversation(self, conversation_id: str) -> bool:
"""删除对话"""
pass
@abstractmethod
def list_conversations(self) -> List[Dict[str, Any]]:
"""列出所有对话"""
pass
@abstractmethod
def cleanup_old_conversations(self, days: int = 30) -> int:
"""清理旧对话"""
pass
class IRateLimiterService(ABC):
"""限流服务抽象接口"""
@abstractmethod
def check_rate_limit(self,
key: str,
limit: int,
window_seconds: int) -> Tuple[bool, int]:
"""检查限流状态
Returns:
Tuple[bool, int]: (是否允许请求, 剩余配额)
"""
pass
@abstractmethod
def reset_rate_limit(self, key: str) -> bool:
"""重置限流"""
pass
@abstractmethod
def get_rate_limit_info(self, key: str) -> Dict[str, Any]:
"""获取限流信息"""
pass
class IHealthCheckService(ABC):
"""健康检查服务抽象接口"""
@abstractmethod
def check_service_health(self, service_name: str) -> Dict[str, Any]:
"""检查单个服务健康状态"""
pass
@abstractmethod
def check_all_services_health(self) -> Dict[str, Dict[str, Any]]:
"""检查所有服务健康状态"""
pass
@abstractmethod
def register_health_check(self,
service_name: str,
check_function: callable) -> bool:
"""注册健康检查"""
pass
class IMetricsService(ABC):
"""指标服务抽象接口"""
@abstractmethod
def record_metric(self,
name: str,
value: float,
tags: Optional[Dict[str, str]] = None) -> None:
"""记录指标"""
pass
@abstractmethod
def increment_counter(self,
name: str,
tags: Optional[Dict[str, str]] = None) -> None:
"""递增计数器"""
pass
@abstractmethod
def record_histogram(self,
name: str,
value: float,
tags: Optional[Dict[str, str]] = None) -> None:
"""记录直方图"""
pass
@abstractmethod
def get_metrics(self,
name_pattern: Optional[str] = None) -> Dict[str, Any]:
"""获取指标数据"""
pass
# 异常类
class ExternalServiceException(Exception):
"""外部服务异常基类"""
pass
class LLMServiceException(ExternalServiceException):
"""LLM服务异常"""
pass
class EmbeddingServiceException(ExternalServiceException):
"""嵌入服务异常"""
pass
class VectorStoreException(ExternalServiceException):
"""向量存储异常"""
pass
class RateLimitException(ExternalServiceException):
"""限流异常"""
pass
class HealthCheckException(ExternalServiceException):
"""健康检查异常"""
pass |