vectorvein 0.2.81__tar.gz → 0.2.83__tar.gz

{vectorvein-0.2.81 → vectorvein-0.2.83}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: vectorvein
-Version: 0.2.81
+Version: 0.2.83
 Summary: VectorVein Python SDK
 Author-Email: Anderson <andersonby@163.com>
 License: MIT

{vectorvein-0.2.81 → vectorvein-0.2.83}/pyproject.toml

@@ -17,7 +17,7 @@ description = "VectorVein Python SDK"
 name = "vectorvein"
 readme = "README.md"
 requires-python = ">=3.10"
-version = "0.2.81"
+version = "0.2.83"
 
 [project.license]
 text = "MIT"

{vectorvein-0.2.81 → vectorvein-0.2.83}/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-0.2.81 → vectorvein-0.2.83}/src/vectorvein/types/defaults.py

@@ -339,6 +339,70 @@ QWEN_MODELS: Final[Dict[str, ModelSettingDict]] = {
         "response_format_available": False,
         "native_multimodal": True,
     },
+    "qwen3-235b-a22b": {
+        "id": "qwen3-235b-a22b",
+        "context_length": 131072,
+        "max_output_tokens": 8192,
+        "function_call_available": True,
+        "response_format_available": True,
+        "native_multimodal": False,
+    },
+    "qwen3-32b": {
+        "id": "qwen3-32b",
+        "context_length": 131072,
+        "max_output_tokens": 8192,
+        "function_call_available": True,
+        "response_format_available": True,
+        "native_multimodal": False,
+    },
+    "qwen3-30b-a3b": {
+        "id": "qwen3-30b-a3b",
+        "context_length": 131072,
+        "max_output_tokens": 8192,
+        "function_call_available": True,
+        "response_format_available": True,
+        "native_multimodal": False,
+    },
+    "qwen3-14b": {
+        "id": "qwen3-14b",
+        "context_length": 131072,
+        "max_output_tokens": 8192,
+        "function_call_available": True,
+        "response_format_available": True,
+        "native_multimodal": False,
+    },
+    "qwen3-8b": {
+        "id": "qwen3-8b",
+        "context_length": 131072,
+        "max_output_tokens": 8192,
+        "function_call_available": True,
+        "response_format_available": True,
+        "native_multimodal": False,
+    },
+    "qwen3-4b": {
+        "id": "qwen3-4b",
+        "context_length": 131072,
+        "max_output_tokens": 8192,
+        "function_call_available": True,
+        "response_format_available": True,
+        "native_multimodal": False,
+    },
+    "qwen3-1.7b": {
+        "id": "qwen3-1.7b",
+        "context_length": 32768,
+        "max_output_tokens": 8192,
+        "function_call_available": True,
+        "response_format_available": True,
+        "native_multimodal": False,
+    },
+    "qwen3-0.6b": {
+        "id": "qwen3-0.6b",
+        "context_length": 32768,
+        "max_output_tokens": 8192,
+        "function_call_available": True,
+        "response_format_available": True,
+        "native_multimodal": False,
+    },
 }
 
 # Yi models