127 lines
4.5 KiB
Python
127 lines
4.5 KiB
Python
|
import socket
|
||
|
|
import json
|
||
|
|
from openai import OpenAI
|
||
|
|
|
||
|
|
# 1. 初始化 DeepSeek 客户端
|
||
|
|
# 注意：务必确保已经执行过 pip install openai
|
||
|
|
client = OpenAI(
|
||
|
|
api_key="sk-420190f448fe41158c4e2ccff90e35ce",
|
||
|
|
base_url="https://api.deepseek.com" # 核心修改：将网关指向 DeepSeek 服务器
|
||
|
|
)
|
||
|
|
|
||
|
|
# 核心修改：使用 DeepSeek 的主模型。
|
||
|
|
# (注: DeepSeek-V4/V4.1 的视觉支持已集成，具体模型名请以你 DeepSeek 后台显示的可用模型为准)
|
||
|
|
MODEL_NAME = "deepseek-flash"
|
||
|
|
|
||
|
|
def call_cad_mcp_server(tool_name, arguments):
|
||
|
|
"""封装与 AutoCAD MCP 基座的 TCP 通信"""
|
||
|
|
try:
|
||
|
|
cad_socket = socket.socket(socket.AF_INET, socket.SOCK_STREAM)
|
||
|
|
cad_socket.connect(("127.0.0.1", 8080))
|
||
|
|
|
||
|
|
req = {
|
||
|
|
"jsonrpc": "2.0",
|
||
|
|
"id": 1,
|
||
|
|
"method": "tools/call",
|
||
|
|
"params": {
|
||
|
|
"name": tool_name,
|
||
|
|
"arguments": arguments
|
||
|
|
}
|
||
|
|
}
|
||
|
|
cad_socket.sendall(json.dumps(req).encode('utf-8'))
|
||
|
|
|
||
|
|
response_data = b""
|
||
|
|
while True:
|
||
|
|
chunk = cad_socket.recv(8192)
|
||
|
|
response_data += chunk
|
||
|
|
if len(chunk) < 8192:
|
||
|
|
break
|
||
|
|
|
||
|
|
cad_socket.close()
|
||
|
|
return json.loads(response_data.decode('utf-8'))
|
||
|
|
except Exception as e:
|
||
|
|
print(f"[Error] 连接 CAD 基座失败: {e}")
|
||
|
|
return None
|
||
|
|
|
||
|
|
def main():
|
||
|
|
print("=== DeepSeek CAD Vision Agent 启动 ===")
|
||
|
|
|
||
|
|
# 2. 定义 MCP 工具 (Tool Calling)
|
||
|
|
tools = [
|
||
|
|
{
|
||
|
|
"type": "function",
|
||
|
|
"function": {
|
||
|
|
"name": "get_viewport_screenshot",
|
||
|
|
"description": "获取当前 AutoCAD 视口的实时截图。当用户询问图纸上的视觉特征、数量或位置时，必须先调用此工具获取画面。"
|
||
|
|
}
|
||
|
|
}
|
||
|
|
]
|
||
|
|
|
||
|
|
# 3. 初始化历史
|
||
|
|
messages = [
|
||
|
|
{"role": "system", "content": "你是一个专业的 AutoCAD 视觉审查助手。必须先使用截图工具观察图纸，再回答用户问题。"},
|
||
|
|
{"role": "user", "content": "请看看当前 CAD 屏幕上，我一共画了几个圆？"}
|
||
|
|
]
|
||
|
|
|
||
|
|
print("\n[DeepSeek] 正在思考如何完成任务...")
|
||
|
|
|
||
|
|
# === 第一回合：DeepSeek 思考并决定调用工具 ===
|
||
|
|
response = client.chat.completions.create(
|
||
|
|
model=MODEL_NAME,
|
||
|
|
messages=messages,
|
||
|
|
tools=tools
|
||
|
|
)
|
||
|
|
|
||
|
|
assistant_message = response.choices[0].message
|
||
|
|
messages.append(assistant_message)
|
||
|
|
|
||
|
|
# 检查 DeepSeek 是否发起了 Tool Call
|
||
|
|
if assistant_message.tool_calls:
|
||
|
|
tool_call = assistant_message.tool_calls[0]
|
||
|
|
tool_name = tool_call.function.name
|
||
|
|
|
||
|
|
print(f"[DeepSeek] 决定调用 CAD 工具: {tool_name}")
|
||
|
|
print(f"[CAD] 正在执行截图，请稍候...")
|
||
|
|
|
||
|
|
# === 与 CAD 基座通信 ===
|
||
|
|
cad_res = call_cad_mcp_server(tool_name, {})
|
||
|
|
|
||
|
|
if cad_res and "result" in cad_res:
|
||
|
|
content_array = cad_res["result"]["content"]
|
||
|
|
base64_img = ""
|
||
|
|
mime_type = "image/png"
|
||
|
|
for item in content_array:
|
||
|
|
if item["type"] == "image":
|
||
|
|
base64_img = item["data"]
|
||
|
|
mime_type = item.get("mimeType", "image/png")
|
||
|
|
|
||
|
|
print("[CAD] 截图成功！正在将视觉数据传回大模型神经中枢...")
|
||
|
|
|
||
|
|
# 4. 将 Base64 图片按标准多模态格式塞回历史
|
||
|
|
messages.append({
|
||
|
|
"role": "tool",
|
||
|
|
"tool_call_id": tool_call.id,
|
||
|
|
"content": [
|
||
|
|
{"type": "text", "text": "这是 AutoCAD 当前界面的实时截图。请根据图片回答用户的问题。"},
|
||
|
|
{"type": "image_url", "image_url": {"url": f"data:{mime_type};base64,{base64_img}"}}
|
||
|
|
]
|
||
|
|
})
|
||
|
|
|
||
|
|
# === 第二回合：DeepSeek “看”图并回答 ===
|
||
|
|
print("[DeepSeek] 正在进行视觉分析...")
|
||
|
|
final_response = client.chat.completions.create(
|
||
|
|
model=MODEL_NAME,
|
||
|
|
messages=messages
|
||
|
|
)
|
||
|
|
|
||
|
|
print("\n==================================")
|
||
|
|
print(f"[DeepSeek 最终回答]:\n{final_response.choices[0].message.content}")
|
||
|
|
print("==================================")
|
||
|
|
|
||
|
|
else:
|
||
|
|
print("[Error] CAD 工具执行失败。")
|
||
|
|
else:
|
||
|
|
print(f"[DeepSeek 盲猜]: {assistant_message.content}")
|
||
|
|
|
||
|
|
if __name__ == "__main__":
|
||
|
|
main()
|