feat: support glm-4.6v (#54)

Author: tomsun28

README.md

@@ -169,7 +169,7 @@ client = ZaiClient(api_key="your-api-key")
 
 # Create chat completion
 response = client.chat.completions.create(
-    model='glm-4',
+    model='glm-4.6',
     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',
+    model='glm-4.6',
     messages=[
         {'role': 'system', 'content': 'You are a helpful assistant.'},
         {'role': 'user', 'content': 'What is artificial intelligence?'},
@@ -228,7 +228,7 @@ client = ZaiClient(api_key="your-api-key")
 base64_image = encode_image('examples/test_multi_modal.jpeg')
 
 response = client.chat.completions.create(
-    model='glm-4v',
+    model='glm-4.6v',
     messages=[
         {
             'role': 'user',
@@ -338,7 +338,7 @@ client = ZaiClient(api_key="your-api-key")
 
 try:
     response = client.chat.completions.create(
-        model="glm-4",
+        model="glm-4.6",
         messages=[
             {"role": "user", "content": "Hello, Z.ai!"}
         ]

README_CN.md

@@ -107,7 +107,7 @@ client = ZhipuAiClient(api_key="your-api-key")
 
 # Create chat completion
 response = client.chat.completions.create(
-    model="glm-4",
+    model="glm-4.6",
     messages=[
         {"role": "user", "content": "Hello, Z.ai!"}
     ]
@@ -175,7 +175,7 @@ client = ZaiClient(api_key="your-api-key")
 
 # 创建对话
 response = client.chat.completions.create(
-    model='glm-4',
+    model='glm-4.6',
     messages=[
         {'role': 'system', 'content': 'You are a helpful assistant.'},
         {'role': 'user', 'content': 'Tell me a story about AI.'},
@@ -198,7 +198,7 @@ client = ZaiClient(api_key="your-api-key")
 
 # 创建对话
 response = client.chat.completions.create(
-    model='glm-4',
+    model='glm-4.6',
     messages=[
         {'role': 'system', 'content': 'You are a helpful assistant.'},
         {'role': 'user', 'content': 'What is artificial intelligence?'},
@@ -234,7 +234,7 @@ client = ZaiClient(api_key="your-api-key")
 base64_image = encode_image('examples/test_multi_modal.jpeg')
 
 response = client.chat.completions.create(
-    model='glm-4v',
+    model='glm-4.6v',
     messages=[
         {
             'role': 'user',
@@ -344,7 +344,7 @@ client = ZaiClient(api_key="your-api-key")  # 请填写您自己的APIKey
 
 try:
     response = client.chat.completions.create(
-        model="glm-4",
+        model="glm-4.6",
         messages=[
             {"role": "user", "content": "你好， Z.ai ！"}
         ]

examples/basic_usage.py

@@ -126,7 +126,7 @@ def encode_image(image_path):
 	base64_image = encode_image('examples/test_multi_modal.jpeg')
 
 	response = client.chat.completions.create(
-		model='glm-4v',
+		model='glm-4.6v',
 		messages=[
 			{
 				'role': 'user',

pyproject.toml

@@ -1,6 +1,6 @@
 [tool.poetry]
 name = "zai-sdk"
-version = "0.0.4.3"
+version = "0.1.0"
 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__ = '0.0.4.3'
+__version__ = '0.1.0'

src/zai/types/chat/chat_completion_chunk.py

@@ -68,7 +68,7 @@ class ChoiceDelta(BaseModel):
 	Attributes:
 		content: Content delta
 		role: Role of the message sender
-		reasoning_content: Reasoning content delta
+		reasoning_content: Reasoning content delta, it's recommended to return the model's reasoning_content in next request to achieve better results in multi-turn conversations.
 		tool_calls: List of tool call deltas
 		audio: Audio completion chunk
 	"""

tests/integration_tests/test_chat.py

@@ -323,7 +323,7 @@ def test_completions_stream_with_tools(logging_conf):
 		print(f'request_id:{request_id}')
 		response = client.chat.completions.create(
 			request_id=request_id,
-			model='glm-4v',  # Fill in the model name to call
+			model='glm-4.6v',  # Fill in the model name to call
 			extra_body={'temperature': 0.5, 'max_tokens': 50},
 			messages=[
 				{
@@ -361,7 +361,7 @@ def test_completions_vis_base64(test_file_path, logging_conf):
 		print(f'request_id:{request_id}')
 		response = client.chat.completions.create(
 			request_id=request_id,
-			model='glm-4v',  # Fill in the model name to call
+			model='glm-4.6v',  # Fill in the model name to call
 			extra_body={'temperature': 0.5, 'max_tokens': 50},
 			messages=[
 				{
@@ -402,7 +402,7 @@ def test_async_completions(logging_conf):
 		print(f'request_id:{request_id}')
 		response = client.chat.completions.create(
 			request_id=request_id,
-			model='glm-4v',  # Fill in the model name to call
+			model='glm-4.6v',  # Fill in the model name to call
 			messages=[
 				{
 					'role': 'user',