vectorvein 0.2.80__tar.gz → 0.2.82__tar.gz

{vectorvein-0.2.80 → vectorvein-0.2.82}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: vectorvein
-Version: 0.2.80
+Version: 0.2.82
 Summary: VectorVein Python SDK
 Author-Email: Anderson <andersonby@163.com>
 License: MIT

{vectorvein-0.2.80 → vectorvein-0.2.82}/pyproject.toml

@@ -17,7 +17,7 @@ description = "VectorVein Python SDK"
 name = "vectorvein"
 readme = "README.md"
 requires-python = ">=3.10"
-version = "0.2.80"
+version = "0.2.82"
 
 [project.license]
 text = "MIT"

{vectorvein-0.2.80 → vectorvein-0.2.82}/src/vectorvein/chat_clients/openai_compatible_client.py

@@ -99,7 +99,7 @@ class OpenAICompatibleChatClient(BaseChatClient):
             return AzureOpenAI(
                 azure_endpoint=self.endpoint.api_base,
                 api_key=self.endpoint.api_key,
-                api_version="2025-01-01-preview",
+                api_version="2025-03-01-preview",
                 http_client=self.http_client,
             )
         else:
@@ -336,7 +336,7 @@ class OpenAICompatibleChatClient(BaseChatClient):
             else:
                 max_tokens = self.model_setting.context_length - token_counts - 64
 
-        if "o3-mini" in self.model_id:
+        if "o3-mini" in self.model_id or "o4-mini" in self.model_id:
             max_completion_tokens = max_tokens
             max_tokens = NOT_GIVEN
 
@@ -581,7 +581,7 @@ class AsyncOpenAICompatibleChatClient(BaseAsyncChatClient):
             return AsyncAzureOpenAI(
                 azure_endpoint=self.endpoint.api_base,
                 api_key=self.endpoint.api_key,
-                api_version="2025-01-01-preview",
+                api_version="2025-03-01-preview",
                 http_client=self.http_client,
             )
         else:
@@ -818,7 +818,7 @@ class AsyncOpenAICompatibleChatClient(BaseAsyncChatClient):
             else:
                 max_tokens = self.model_setting.context_length - token_counts - 64
 
-        if "o3-mini" in self.model_id:
+        if "o3-mini" in self.model_id or "o4-mini" in self.model_id:
             max_completion_tokens = max_tokens
             max_tokens = NOT_GIVEN
 

{vectorvein-0.2.80 → vectorvein-0.2.82}/src/vectorvein/types/defaults.py

@@ -469,6 +469,30 @@ ZHIPUAI_MODELS: Final[Dict[str, ModelSettingDict]] = {
         "max_output_tokens": 20480,
         "native_multimodal": False,
     },
+    "glm-z1-air": {
+        "id": "glm-z1-air",
+        "context_length": 32000,
+        "function_call_available": False,
+        "response_format_available": False,
+        "max_output_tokens": 32000,
+        "native_multimodal": False,
+    },
+    "glm-z1-airx": {
+        "id": "glm-z1-airx",
+        "context_length": 32000,
+        "function_call_available": False,
+        "response_format_available": False,
+        "max_output_tokens": 30000,
+        "native_multimodal": False,
+    },
+    "glm-z1-flash": {
+        "id": "glm-z1-flash",
+        "context_length": 32000,
+        "function_call_available": False,
+        "response_format_available": False,
+        "max_output_tokens": 32000,
+        "native_multimodal": False,
+    },
 }
 
 # Mistral models
@@ -599,6 +623,14 @@ OPENAI_MODELS: Final[Dict[str, ModelSettingDict]] = {
         "response_format_available": False,
         "native_multimodal": False,
     },
+    "o3": {
+        "id": "o3",
+        "context_length": 200000,
+        "max_output_tokens": 100000,
+        "function_call_available": True,
+        "response_format_available": True,
+        "native_multimodal": True,
+    },
     "o3-mini": {
         "id": "o3-mini",
         "context_length": 200000,
@@ -607,6 +639,14 @@ OPENAI_MODELS: Final[Dict[str, ModelSettingDict]] = {
         "response_format_available": True,
         "native_multimodal": False,
     },
+    "o4-mini": {
+        "id": "o4-mini",
+        "context_length": 200000,
+        "max_output_tokens": 100000,
+        "function_call_available": True,
+        "response_format_available": True,
+        "native_multimodal": True,
+    },
     "gpt-4.1": {
         "id": "gpt-4.1",
         "context_length": 1047576,
@@ -615,6 +655,22 @@ OPENAI_MODELS: Final[Dict[str, ModelSettingDict]] = {
         "response_format_available": True,
         "native_multimodal": True,
     },
+    "gpt-4.1-mini": {
+        "id": "gpt-4.1-mini",
+        "context_length": 1047576,
+        "max_output_tokens": 32768,
+        "function_call_available": True,
+        "response_format_available": True,
+        "native_multimodal": True,
+    },
+    "gpt-4.1-nano": {
+        "id": "gpt-4.1-nano",
+        "context_length": 1047576,
+        "max_output_tokens": 32768,
+        "function_call_available": True,
+        "response_format_available": True,
+        "native_multimodal": True,
+    },
 }
 
 # Anthropic models
@@ -816,7 +872,23 @@ GEMINI_MODELS: Final[Dict[str, ModelSettingDict]] = {
     "gemini-2.5-pro-exp-03-25": {
         "id": "gemini-2.5-pro-exp-03-25",
         "context_length": 1048576,
-        "max_output_tokens": 8192,
+        "max_output_tokens": 65536,
+        "function_call_available": True,
+        "response_format_available": True,
+        "native_multimodal": True,
+    },
+    "gemini-2.5-pro-preview-03-25": {
+        "id": "gemini-2.5-pro-preview-03-25",
+        "context_length": 1048576,
+        "max_output_tokens": 65536,
+        "function_call_available": True,
+        "response_format_available": True,
+        "native_multimodal": True,
+    },
+    "gemini-2.5-flash-preview-04-17": {
+        "id": "gemini-2.5-flash-preview-04-17",
+        "context_length": 1048576,
+        "max_output_tokens": 65536,
         "function_call_available": True,
         "response_format_available": True,
         "native_multimodal": True,