feat: support glm-4.7 model (#56)

README.md

@@ -11,7 +11,7 @@
 ## ✨ Core Features
 
 ### 🤖 **Chat Completions**
-- **Standard Chat**: Create chat completions with various models including `glm-4`, `charglm-3`
+- **Standard Chat**: Create chat completions with various models including `glm-4.7`
 - **Streaming Support**: Real-time streaming responses for interactive applications
 - **Tool Calling**: Function calling capabilities for enhanced AI interactions
 - **Character Role-Playing**: Support for character-based conversations with `charglm-3` model
@@ -105,7 +105,7 @@ client = ZhipuAiClient(api_key="your-api-key")
 
 # Create chat completion
 response = client.chat.completions.create(
-    model="glm-4",
+    model="glm-4.7",
     messages=[
         {"role": "user", "content": "Hello, Z.ai!"}
     ]
@@ -169,7 +169,7 @@ client = ZaiClient(api_key="your-api-key")
 
 # Create chat completion
 response = client.chat.completions.create(
-    model='glm-4.6',
+    model='glm-4.7',
     messages=[
         {'role': 'system', 'content': 'You are a helpful assistant.'},
         {'role': 'user', 'content': 'Tell me a story about AI.'},
@@ -192,7 +192,7 @@ client = ZaiClient(api_key="your-api-key")
 
 # Create chat completion
 response = client.chat.completions.create(
-    model='glm-4.6',
+    model='glm-4.7',
     messages=[
         {'role': 'system', 'content': 'You are a helpful assistant.'},
         {'role': 'user', 'content': 'What is artificial intelligence?'},
@@ -244,65 +244,6 @@ response = client.chat.completions.create(
 print(response)
 ```
 
-### Character Role-Playing
-
-```python
-from zai import ZaiClient
-
-# Initialize client
-client = ZaiClient(api_key="your-api-key")
-
-# Create chat completion
-response = client.chat.completions.create(
-    model='charglm-3',
-    messages=[{'role': 'user', 'content': 'Hello, how are you doing lately?'}],
-    meta={
-        'user_info': 'I am a film director who specializes in music-themed movies.',
-        'bot_info': 'You are a popular domestic female singer and actress with outstanding musical talent.',
-        'bot_name': 'Alice',
-        'user_name': 'Director',
-    },
-)
-print(response)
-```
-
-### Assistant Conversation
-
-```python
-from zai import ZaiClient
-
-# Initialize client
-client = ZaiClient(api_key="your-api-key")
-
-# Create assistant conversation
-response = client.assistant.conversation(
-    # You can use 65940acff94777010aa6b796 for testing
-    # or you can create your own assistant_id in Z.ai console
-    assistant_id='your own assistant_id',
-    model='glm-4-assistant',
-    messages=[
-        {
-            'role': 'user',
-            'content': [
-                {
-                    'type': 'text',
-                    'text': 'Help me search for the latest Z.ai product information',
-                }
-            ],
-        }
-    ],
-    stream=True,
-    attachments=None,
-    metadata=None,
-    request_id='request_1790291013237211136',
-    user_id='12345678',
-)
-
-for chunk in response:
-    if chunk.choices[0].delta.type == 'content':
-        print(chunk.choices[0].delta.content, end='')
-```
-
 ### Video Generation
 
 ```python
@@ -311,7 +252,7 @@ client = ZaiClient(api_key="your-api-key")
 
 # Generate video
 response = client.videos.generations(
-    model="cogvideox-2",
+    model="cogvideox-3",
     prompt="A cat is playing with a ball.",
     quality="quality",  # Output mode, "quality" for quality priority, "speed" for speed priority
     with_audio=True, # Whether to include audio
@@ -338,7 +279,7 @@ client = ZaiClient(api_key="your-api-key")
 
 try:
     response = client.chat.completions.create(
-        model="glm-4.6",
+        model="glm-4.7",
         messages=[
             {"role": "user", "content": "Hello, Z.ai!"}
         ]

README_CN.md

@@ -6,12 +6,12 @@
 
 [English Readme](README.md)
 
-[Z.ai 开放平台](https://docs.z.ai/)官方 Python SDK，帮助开发者快速集成 Z.ai 强大的人工智能能力到Python应用中。
+[智谱开放平台](https://docs.bigmodel.cn/)官方 Python SDK，帮助开发者快速集成智谱强大的人工智能能力到Python应用中。
 
 ## ✨ 核心功能
 
 ### 🤖 **对话补全**
-- **标准对话**: 支持 `glm-4`、`charglm-3` 等多种模型的对话补全
+- **标准对话**: 支持 `glm-4.7` 等多种模型的对话补全
 - **流式支持**: 实时流式响应，适用于交互式应用
 - **工具调用**: 函数调用能力，增强 AI 交互体验
 - **角色扮演**: 支持基于 `charglm-3` 模型的角色对话
@@ -107,7 +107,7 @@ client = ZhipuAiClient(api_key="your-api-key")
 
 # Create chat completion
 response = client.chat.completions.create(
-    model="glm-4.6",
+    model="glm-4.7",
     messages=[
         {"role": "user", "content": "Hello, Z.ai!"}
     ]
@@ -250,64 +250,6 @@ response = client.chat.completions.create(
 print(response)
 ```
 
-### 角色扮演
-
-```python
-from zai import ZaiClient
-
-# 初始化客户端
-client = ZaiClient(api_key="your-api-key")
-
-# 创建对话
-response = client.chat.completions.create(
-    model='charglm-3',
-    messages=[{'role': 'user', 'content': 'Hello, how are you doing lately?'}],
-    meta={
-        'user_info': 'I am a film director who specializes in music-themed movies.',
-        'bot_info': 'You are a popular domestic female singer and actress with outstanding musical talent.',
-        'bot_name': 'Alice',
-        'user_name': 'Director',
-    },
-)
-print(response)
-```
-
-### 智能体对话
-
-```python
-from zai import ZaiClient
-
-# Initialize client
-client = ZaiClient(api_key="your-api-key")
-
-# Create assistant conversation
-response = client.assistant.conversation(
-    # 你可使用 65940acff94777010aa6b796 作为测试ID
-    assistant_id='你的assistant_id',
-    model='glm-4-assistant',
-    messages=[
-        {
-            'role': 'user',
-            'content': [
-                {
-                    'type': 'text',
-                    'text': 'Help me search for the latest Z.ai product information',
-                }
-            ],
-        }
-    ],
-    stream=True,
-    attachments=None,
-    metadata=None,
-    request_id='request_1790291013237211136',
-    user_id='12345678',
-)
-
-for chunk in response:
-    if chunk.choices[0].delta.type == 'content':
-        print(chunk.choices[0].delta.content, end='')
-```
-
 ### 视频生成
 
 ```python
@@ -317,7 +259,7 @@ client = ZaiClient()  # 请填写您自己的APIKey
 
 # 提交生成任务
 response = client.videos.generations(
-    model="cogvideox-2",  # 使用的视频生成模型
+    model="cogvideox-3",  # 使用的视频生成模型
     image_url=image_url,  # 提供的图片URL地址或者 Base64 编码
     prompt="让画面动起来",  
     quality="speed",  # 输出模式，"quality"为质量优先，"speed"为速度优先
@@ -344,7 +286,7 @@ client = ZaiClient(api_key="your-api-key")  # 请填写您自己的APIKey
 
 try:
     response = client.chat.completions.create(
-        model="glm-4.6",
+        model="glm-4.7",
         messages=[
             {"role": "user", "content": "你好， Z.ai ！"}
         ]

examples/basic_usage.py

@@ -6,7 +6,7 @@ def completion():
 
 	# Create chat completion
 	response = client.chat.completions.create(
-		model='glm-4.6',
+		model='glm-4.7',
 		messages=[{'role': 'user', 'content': 'Hello, Z.ai!'}],
 		temperature=1.0,
 	)
@@ -19,7 +19,7 @@ def completion_with_stream():
 
 	# Create chat completion
 	response = client.chat.completions.create(
-		model='glm-4.6',
+		model='glm-4.7',
 		messages=[
 			{'role': 'system', 'content': 'You are a helpful assistant.'},
 			{'role': 'user', 'content': 'Tell me a story about AI.'},
@@ -38,7 +38,7 @@ def completion_with_websearch():
 
 	# Create chat completion
 	response = client.chat.completions.create(
-		model='glm-4.6',
+		model='glm-4.7',
 		messages=[
 			{'role': 'system', 'content': 'You are a helpful assistant.'},
 			{'role': 'user', 'content': 'What is artificial intelligence?'},
@@ -66,7 +66,7 @@ def completion_with_mcp_server_url():
 	
 	# Create chat completion with MCP server URL
 	response = client.chat.completions.create(
-		model='glm-4',
+		model='glm-4.7',
 		stream=False,
 		messages=[{'role': 'user', 'content': 'Hello, please introduce GPT?'}],
 		tools=[
@@ -95,7 +95,7 @@ def completion_with_mcp_server_label():
 	
 	# Create chat completion with MCP server label
 	response = client.chat.completions.create(
-		model='glm-4',
+		model='glm-4.7',
 		stream=False,
 		messages=[{'role': 'user', 'content': 'Hello, please introduce GPT?'}],
 		tools=[
@@ -208,7 +208,7 @@ def audio_transcription():
 
 	# Create audio transcription
 	response = client.audio.transcriptions.create(
-		model='glm-4',
+		model='glm-asr-2512',
 		file='audio.mp3',
 	)
 	print(response.text)
@@ -217,7 +217,7 @@ def ofZai():
     client = ZaiClient()
     print(client.base_url)
     response = client.chat.completions.create(
-        model='glm-4',
+        model='glm-4.7',
         messages=[{'role': 'user', 'content': 'Hello, Z.ai!'}],
         temperature=0.7,
     )
@@ -227,7 +227,7 @@ def ofZhipu():
 	client = ZhipuAiClient()
 	print(client.base_url)
 	response = client.chat.completions.create(
-		model='glm-4',
+		model='glm-4.7',
 		messages=[{'role': 'user', 'content': 'Hello, Z.ai!'}],
 		temperature=0.7,
 	)

examples/function_call_example.py

@@ -36,7 +36,7 @@ def parse_function_call(model_response, messages):
             "tool_call_id": tool_call.id
         })
         response = client.chat.completions.create(
-            model="glm-4",  # Specify the model name to use
+            model="glm-4.7",  # Specify the model name to use
             messages=messages,
             tools=tools,
         )
@@ -99,7 +99,7 @@ messages.append({"role": "system", "content": "Do not assume or guess the values
 messages.append({"role": "user", "content": "Help me check the flights from Beijing to Guangzhou on January 23."})
 
 response = client.chat.completions.create(
-    model="glm-4",  # Specify the model name to use
+    model="glm-4.7",  # Specify the model name to use
     messages=messages,
     tools=tools,
 )
@@ -110,7 +110,7 @@ parse_function_call(response, messages)
 
 messages.append({"role": "user", "content": "What is the price of flight 8321?"})
 response = client.chat.completions.create(
-    model="glm-4",  # Specify the model name to use
+    model="glm-4.7",  # Specify the model name to use
     messages=messages,
     tools=tools,
 )

examples/glm4_example.py

@@ -23,7 +23,7 @@ def stream_web_search_example():
     }]
     client = ZaiClient()
     response = client.chat.completions.create(
-        model="glm-4-air",
+        model="glm-4.7",
         messages=messages,
         tools=tools,
         stream=True
@@ -35,7 +35,7 @@ def sync_example():
     print("=== GLM-4 Synchronous Example ===")
     client = ZaiClient()
     response = client.chat.completions.create(
-        model="glm-4-plus",
+        model="glm-4.7",
         messages=[
             {"role": "system", "content": "You are a helpful assistant who provides professional, accurate, and insightful advice."},
             {"role": "user", "content": "I'm very interested in the planets of the solar system, especially Saturn. Please provide basic information about Saturn, including its size, composition, ring system, and any unique astronomical phenomena."},
@@ -47,7 +47,7 @@ def async_example():
     print("=== GLM-4 Async Example ===")
     client = ZaiClient()
     response = client.chat.asyncCompletions.create(
-        model="glm-4-plus",
+        model="glm-4.7",
         messages=[
             {
                 "role": "user",

examples/glm_thinking.py

@@ -1,7 +1,6 @@
 import os
 import sys
 sys.path.append(os.path.dirname(os.path.dirname(os.path.abspath(__file__))))
-import time
 import traceback
 from typing import Optional
 
@@ -16,7 +15,7 @@ class ZaiSampler(SamplerBase):
 
     def __init__(
         self,
-        model: str = "glm-4.5",
+        model: str = "glm-4.7",
         api_key: str = '',
         system_message: Optional[str] = None,
         temperature: float = 0.0,

examples/stream_tools.py

@@ -4,7 +4,7 @@ def main():
     client = ZhipuAiClient()
     # create chat completion with tool calls and streaming
     response = client.chat.completions.create(
-        model="glm-4.6",
+        model="glm-4.7",
         messages=[
             {"role": "user", "content": "How is the weather in Beijing and Shanghai? Please provide the answer in Celsius."},
         ],

examples/voice_clone.py

@@ -1,6 +1,5 @@
 from zai import ZaiClient, ZhipuAiClient
 import time
-import os
 
 def voice_clone():
 	# Initialize client

pyproject.toml

@@ -1,6 +1,6 @@
 [tool.poetry]
 name = "zai-sdk"
-version = "0.1.0"
+version = "0.2.0"
 description = "A SDK library for accessing big model apis from Z.ai"
 authors = ["Z.ai"]
 readme = "README.md"

src/zai/_version.py

@@ -1,2 +1,2 @@
 __title__ = 'Z.ai'
-__version__ = '0.1.0'
+__version__ = '0.2.0'

tests/integration_tests/test_chat.py

@@ -16,7 +16,7 @@ def test_completions_temp0(logging_conf):
 		print(f'request_id:{request_id}')
 		response = client.chat.completions.create(
 			request_id=request_id,
-			model='glm-4',
+			model='glm-4.7',
 			messages=[{'role': 'user', 'content': 'tell me a joke'}],
 			top_p=0.7,
 			temperature=0,
@@ -42,7 +42,7 @@ def test_completions_temp1(logging_conf):
 		print(f'request_id:{request_id}')
 		response = client.chat.completions.create(
 			request_id=request_id,
-			model='glm-4',
+			model='glm-4.7',
 			messages=[{'role': 'user', 'content': 'tell me a joke'}],
 			top_p=0.7,
 			temperature=1,
@@ -68,7 +68,7 @@ def test_completions_top0(logging_conf):
 		print(f'request_id:{request_id}')
 		response = client.chat.completions.create(
 			request_id=request_id,
-			model='glm-4',
+			model='glm-4.7',
 			messages=[{'role': 'user', 'content': 'tell me a joke'}],
 			top_p=0,
 			temperature=0.9,
@@ -94,7 +94,7 @@ def test_completions_top1(logging_conf):
 		print(f'request_id:{request_id}')
 		response = client.chat.completions.create(
 			request_id=request_id,
-			model='glm-4',
+			model='glm-4.7',
 			messages=[{'role': 'user', 'content': 'tell me a joke'}],
 			top_p=1,
 			temperature=0.9,
@@ -120,7 +120,7 @@ def test_completions(logging_conf):
 		print(f'request_id:{request_id}')
 		response = client.chat.completions.create(
 			request_id=request_id,
-			model='glm-4',  # Fill in the model name to call
+			model='glm-4.7',  # Fill in the model name to call
 			messages=[
 				{
 					'role': 'user',
@@ -170,7 +170,7 @@ def test_completions_disenable_web_search(logging_conf):
 		print(f'request_id:{request_id}')
 		response = client.chat.completions.create(
 			request_id=request_id,
-			model='glm-4',  # Fill in the model name to call
+			model='glm-4.7',  # Fill in the model name to call
 			messages=[
 				{
 					'role': 'user',
@@ -221,7 +221,7 @@ def test_completions_enable_web_search(logging_conf):
 		print(f'request_id:{request_id}')
 		response = client.chat.completions.create(
 			request_id=request_id,
-			model='glm-4',  # Fill in the model name to call
+			model='glm-4.7',  # Fill in the model name to call
 			messages=[
 				{
 					'role': 'user',
@@ -272,7 +272,7 @@ def test_completions_sensitive_word_check(logging_conf):
 		print(f'request_id:{request_id}')
 		response = client.chat.completions.create(
 			request_id=request_id,
-			model='glm-4',  # Fill in the model name to call
+			model='glm-4.7',  # Fill in the model name to call
 			stream=True,
 			messages=[
 				{
@@ -467,7 +467,7 @@ def test_completions_vis(logging_conf):
 		print(f'request_id:{request_id}')
 		response = client.chat.completions.create(
 			request_id=request_id,
-			model='glm-4',
+			model='glm-4.7',
 			messages=[{'role': 'user', 'content': 'tell me a joke'}],
 			top_p=1,
 			temperature=0.9,

tests/integration_tests/test_thinking.py

@@ -15,7 +15,7 @@ def test_chat_completion_with_thinking(logging_conf):
 		print(f'request_id:{request_id}')
 		response = client.chat.completions.create(
 			request_id=request_id,
-			model='glm-4.5',
+			model='glm-4.7',
 			messages=[{'role': 'user', 'content': '请介绍一下Agent的原理，并给出详细的推理过程'}],
 			top_p=0.7,
 			temperature=0.9,
@@ -39,7 +39,7 @@ def test_chat_completion_without_thinking(logging_conf):
 		print(f'request_id:{request_id}')
 		response = client.chat.completions.create(
 			request_id=request_id,
-			model='glm-4.5',
+			model='glm-4.7',
 			messages=[{'role': 'user', 'content': '请介绍一下Agent的原理'}],
 			top_p=0.7,
 			temperature=0.9,

tests/integration_tests/test_vlm_thinking.py

@@ -15,7 +15,7 @@ def test_completions_vlm_thinking(logging_conf):
 		print(f'request_id:{request_id}')
 		response = client.chat.completions.create(
 			request_id=request_id,
-			model='glm-4.1v-thinking-flash',  # Fill in the model name to call
+			model='glm-4.6v',  # Fill in the model name to call
 			messages=[
 				{
 					'role': 'user',
@@ -53,7 +53,7 @@ def test_completions_vlm_thinking_stream(logging_conf):
 		print(f'request_id:{request_id}')
 		response = client.chat.completions.create(
 			request_id=request_id,
-			model='glm-4.1v-thinking-flash',  # Fill in the model name to call
+			model='glm-4.6v',  # Fill in the model name to call
 			messages=[
 				{
 					'role': 'user',