Delete services

services/glm.py

@@ -1,76 +0,0 @@
-import openai
-import logging
-from typing import List, Dict, Any
-from config import config
-
-logger = logging.getLogger(__name__)
-
-
-class GLMService:
-    def __init__(self) -> None:
-        self.client = openai.AsyncOpenAI(
-            base_url=config.NVIDIA_BASE_URL,
-            api_key=config.NVIDIA_API_KEY,
-            timeout=60.0,
-            max_retries=2,
-        )
-        self.model = config.MODEL_NAME
-    async def chat(self, messages: List[Dict[str, str]]) -> str:
-        try:
-            response = await self.client.chat.completions.create(
-                model=self.model,
-                messages=messages,
-                temperature=config.GLM_TEMPERATURE,
-                top_p=config.GLM_TOP_P,
-                frequency_penalty=config.GLM_FREQUENCY_PENALTY,
-                presence_penalty=config.GLM_PRESENCE_PENALTY,
-                max_tokens=config.GLM_MAX_TOKENS,
-            )
-            content = response.choices[0].message.content
-            if not content:
-                logger.warning("Empty response from GLM")
-                return "(пустой ответ от модели)"
-            logger.info("GLM response received, length: %d", len(content))
-            return content
-        except openai.APIError as e:
-            logger.error("GLM API error: %s", e)
-            raise
-        except Exception as e:
-            logger.error("Unexpected GLM error: %s", e)
-            raise
-
-    async def summarize(self, dialog_text: str) -> str:
-        """Суммаризировать диалог через GLM."""
-        try:
-            messages = [
-                {
-                    "role": "system",
-                    "content": (
-                        "Суммаризируй следующий диалог между пользователем и ассистентом. "
-                        "Сохрани ключевые факты, предпочтения пользователя, важные детали и контекст. "
-                        "Будь краток, максимум 4096 токенов. Используй русский язык."
-                    )
-                },
-                {"role": "user", "content": dialog_text}
-            ]
-            response = await self.client.chat.completions.create(
-                model=self.model,
-                messages=messages,
-                temperature=0.1,
-                max_tokens=config.SUMMARY_MAX_TOKENS,
-            )
-            content = response.choices[0].message.content
-            if not content:
-                logger.warning("Empty summary from GLM")
-                return ""
-            logger.info("Summary generated, length: %d", len(content))
-            return content
-        except Exception as e:
-            logger.error("Summary generation failed: %s", e)
-            return ""
-
-   
-
-
-glm_service = GLMService()
-