roll back ktransformers backend, add max_tokens, max_completion_tokens param

ktransformers/tests/function_call_test.py

@@ -0,0 +1,45 @@
+from openai import OpenAI
+
+def send_messages(messages):
+    response = client.chat.completions.create(
+        model="deepseek-chat",
+        messages=messages,
+        tools=tools
+    )
+    return response.choices[0].message
+
+client = OpenAI(
+    api_key="placeholder",
+    base_url="http://0.0.0.0:10002/v1",
+)
+
+tools = [
+    {
+        "type": "function",
+        "function": {
+            "name": "get_weather",
+            "description": "Get weather of an location, the user shoud supply a location first",
+            "parameters": {
+                "type": "object",
+                "properties": {
+                    "location": {
+                        "type": "string",
+                        "description": "The city and state, e.g. San Francisco, CA",
+                    }
+                },
+                "required": ["location"]
+            },
+        }
+    },
+]
+
+messages = [{"role": "user", "content": "How's the weather in Hangzhou?"}]
+message = send_messages(messages)
+print(f"User>\t {messages[0]['content']}")
+print(message)
+tool = message.tool_calls[0]
+messages.append(message)
+
+messages.append({"role": "tool", "tool_call_id": tool.id, "content": "24℃"})
+message = send_messages(messages)
+print(f"Model>\t {message.content}")