实现terminalcode和文件交互

llm_server/rag_server.py

@@ -1,3 +1,4 @@
+import os
 import torch
 import torch.nn.functional as F
 from fastapi import FastAPI
@@ -6,11 +7,14 @@ from typing import List
 from modelscope import AutoTokenizer, AutoModel, AutoModelForCausalLM
 from transformers import BitsAndBytesConfig
 
+# 自动获取脚本所在目录作为基础路径
+BASE_DIR = os.path.dirname(os.path.abspath(__file__))
+
 # 在 load_models() 里添加量化配置
 quantization_config = BitsAndBytesConfig(load_in_8bit=True)
 # ===================== 模型路径 =====================
-EMBED_MODEL_PATH = "/home/admin/minor_agent/modelscope/models/Qwen/Qwen3-Embedding-0___6B"
-RERANK_MODEL_PATH = "/home/admin/minor_agent/modelscope/models/Qwen/Qwen3-Reranker-4B"
+EMBED_MODEL_PATH = os.path.join(BASE_DIR, "models", "Qwen", "Qwen3-Embedding-0___6B")
+RERANK_MODEL_PATH = os.path.join(BASE_DIR, "models", "Qwen", "Qwen3-Reranker-4B")
 
 # ===================== 初始化 FastAPI =====================
 app = FastAPI(title="RAG Backend with 8-bit Qwen3 Models")