update README with Qwen2.5 and manual start

README.md

@@ -1,10 +1,10 @@
-# GLM-4.6V-Flash Server
+# ToolAgent
 
-基于 vLLM 的 OpenAI 兼容 API 服务。
+基于 vLLM + opencode 的 AI 编程助手服务。
 
 ## Requirements
 
-- NVIDIA GPU with ≥44 GiB memory (e.g. L20)
+- NVIDIA GPU with ≥24 GiB memory (e.g. L20)
 - CUDA driver ≥570.x (CUDA 12.8)
 - Python 3.12
 
@@ -25,21 +25,53 @@ pip install transformers==5.12.0
 
 ## 启动
 
-```bash
-python server.py
-```
-
-或指定 GPU：
+### 一键启动
 
 ```bash
-CUDA_VISIBLE_DEVICES=2 python server.py
+./start.sh          # 前后端同时启动
+./start.sh backend  # 仅后端
+./start.sh frontend # 仅前端
+./start.sh all 3    # 指定 GPU 3
 ```
 
+### 手动启动
+
+#### 后端 (vLLM)
+
+```bash
+source /home/kxqandccx/miniconda3/bin/activate agent_use
+CUDA_VISIBLE_DEVICES=2 nohup python server.py > server.log 2>&1 &
+```
+
+模型加载约 30-60 秒。日志在 `server.log`。
+
+#### 前端 (opencode web)
+
+```bash
+cd /home/kxqandccx/kxq/llm_tool_use
+nohup opencode web --port 3000 > web.log 2>&1 &
+```
+
+访问 `http://127.0.0.1:3000/`。
+
 ## 验证
 
 ```bash
+# 查看可用模型
 curl http://localhost:8000/v1/models
+
+# 文本对话
 curl http://localhost:8000/v1/chat/completions \
   -H "Content-Type: application/json" \
-  -d '{"model":"GLM-4.6V-Flash","messages":[{"role":"user","content":"hello"}]}'
+  -d '{"model":"Qwen2.5-7B-Instruct","messages":[{"role":"user","content":"你好"}]}'
+
+# 工具调用
+curl http://localhost:8000/v1/chat/completions \
+  -H "Content-Type: application/json" \
+  -d '{
+    "model":"Qwen2.5-7B-Instruct",
+    "messages":[{"role":"user","content":"北京天气"}],
+    "tools":[{"type":"function","function":{"name":"get_weather","description":"获取天气","parameters":{"type":"object","properties":{"city":{"type":"string"}},"required":["city"]}}}],
+    "tool_choice":"auto"
+  }'
 ```