vectorvein 0.1.57__tar.gz → 0.1.59__tar.gz

{vectorvein-0.1.57 → vectorvein-0.1.59}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: vectorvein
-Version: 0.1.57
+Version: 0.1.59
 Summary: VectorVein python SDK
 Author-Email: Anderson <andersonby@163.com>
 License: MIT

{vectorvein-0.1.57 → vectorvein-0.1.59}/pyproject.toml

@@ -17,7 +17,7 @@ description = "VectorVein python SDK"
 name = "vectorvein"
 readme = "README.md"
 requires-python = ">=3.10"
-version = "0.1.57"
+version = "0.1.59"
 
 [project.license]
 text = "MIT"

{vectorvein-0.1.57 → vectorvein-0.1.59}/src/vectorvein/chat_clients/anthropic_client.py

@@ -250,6 +250,7 @@ class AnthropicChatClient(BaseChatClient):
         response_format: dict | None = None,
         stream_options: ChatCompletionStreamOptionsParam | None = None,
         top_p: float | NotGiven | None = NOT_GIVEN,
+        skip_cutoff: bool = False,
         **kwargs,
     ) -> ChatCompletionMessage:
         pass
@@ -267,6 +268,7 @@ class AnthropicChatClient(BaseChatClient):
         response_format: dict | None = None,
         stream_options: ChatCompletionStreamOptionsParam | None = None,
         top_p: float | NotGiven | None = NOT_GIVEN,
+        skip_cutoff: bool = False,
         **kwargs,
     ) -> Generator[ChatCompletionDeltaMessage, None, None]:
         pass
@@ -284,6 +286,7 @@ class AnthropicChatClient(BaseChatClient):
         response_format: dict | None = None,
         stream_options: ChatCompletionStreamOptionsParam | None = None,
         top_p: float | NotGiven | None = NOT_GIVEN,
+        skip_cutoff: bool = False,
         **kwargs,
     ) -> ChatCompletionMessage | Generator[ChatCompletionDeltaMessage, Any, None]:
         pass
@@ -300,6 +303,7 @@ class AnthropicChatClient(BaseChatClient):
         response_format: dict | None = None,
         stream_options: ChatCompletionStreamOptionsParam | None = None,
         top_p: float | NotGiven | None = NOT_GIVEN,
+        skip_cutoff: bool = False,
         **kwargs,
     ):
         if model is not None:
@@ -349,6 +353,7 @@ class AnthropicChatClient(BaseChatClient):
                         response_format=response_format,
                         stream_options=stream_options,
                         top_p=top_p,
+                        skip_cutoff=skip_cutoff,
                         **kwargs,
                     )
                     for chunk in response:
@@ -374,8 +379,8 @@ class AnthropicChatClient(BaseChatClient):
                     tools=_tools,
                     tool_choice=_tool_choice,
                     response_format=response_format,
-                    stream_options=stream_options,
                     top_p=top_p,
+                    skip_cutoff=skip_cutoff,
                     **kwargs,
                 )
 
@@ -399,7 +404,7 @@ class AnthropicChatClient(BaseChatClient):
         else:
             system_prompt = ""
 
-        if self.context_length_control == ContextLengthControlType.Latest:
+        if not skip_cutoff and self.context_length_control == ContextLengthControlType.Latest:
             messages = cutoff_messages(
                 messages,
                 max_count=self.model_setting.context_length,
@@ -626,6 +631,7 @@ class AsyncAnthropicChatClient(BaseAsyncChatClient):
         response_format: dict | None = None,
         stream_options: ChatCompletionStreamOptionsParam | None = None,
         top_p: float | NotGiven | None = NOT_GIVEN,
+        skip_cutoff: bool = False,
         **kwargs,
     ) -> ChatCompletionMessage:
         pass
@@ -643,6 +649,7 @@ class AsyncAnthropicChatClient(BaseAsyncChatClient):
         response_format: dict | None = None,
         stream_options: ChatCompletionStreamOptionsParam | None = None,
         top_p: float | NotGiven | None = NOT_GIVEN,
+        skip_cutoff: bool = False,
         **kwargs,
     ) -> AsyncGenerator[ChatCompletionDeltaMessage, Any]:
         pass
@@ -660,6 +667,7 @@ class AsyncAnthropicChatClient(BaseAsyncChatClient):
         response_format: dict | None = None,
         stream_options: ChatCompletionStreamOptionsParam | None = None,
         top_p: float | NotGiven | None = NOT_GIVEN,
+        skip_cutoff: bool = False,
         **kwargs,
     ) -> ChatCompletionMessage | AsyncGenerator[ChatCompletionDeltaMessage, Any]:
         pass
@@ -676,6 +684,7 @@ class AsyncAnthropicChatClient(BaseAsyncChatClient):
         response_format: dict | None = None,
         stream_options: ChatCompletionStreamOptionsParam | None = None,
         top_p: float | NotGiven | None = NOT_GIVEN,
+        skip_cutoff: bool = False,
         **kwargs,
     ):
         if model is not None:
@@ -725,6 +734,8 @@ class AsyncAnthropicChatClient(BaseAsyncChatClient):
                         tool_choice=_tool_choice,
                         response_format=response_format,
                         stream_options=stream_options,
+                        top_p=top_p,
+                        skip_cutoff=skip_cutoff,
                         **kwargs,
                     )
                     async for chunk in response:
@@ -751,6 +762,8 @@ class AsyncAnthropicChatClient(BaseAsyncChatClient):
                     tools=_tools,
                     tool_choice=_tool_choice,
                     response_format=response_format,
+                    top_p=top_p,
+                    skip_cutoff=skip_cutoff,
                     **kwargs,
                 )
 
@@ -774,7 +787,7 @@ class AsyncAnthropicChatClient(BaseAsyncChatClient):
         else:
             system_prompt = ""
 
-        if self.context_length_control == ContextLengthControlType.Latest:
+        if not skip_cutoff and self.context_length_control == ContextLengthControlType.Latest:
             messages = cutoff_messages(
                 messages,
                 max_count=self.model_setting.context_length,

{vectorvein-0.1.57 → vectorvein-0.1.59}/src/vectorvein/chat_clients/base_client.py

@@ -74,6 +74,7 @@ class BaseChatClient(ABC):
         response_format: dict | None = None,
         stream_options: ChatCompletionStreamOptionsParam | None = None,
         top_p: float | NotGiven | None = NOT_GIVEN,
+        skip_cutoff: bool = False,
         **kwargs,
     ) -> ChatCompletionMessage:
         pass
@@ -92,6 +93,7 @@ class BaseChatClient(ABC):
         response_format: dict | None = None,
         stream_options: ChatCompletionStreamOptionsParam | None = None,
         top_p: float | NotGiven | None = NOT_GIVEN,
+        skip_cutoff: bool = False,
         **kwargs,
     ) -> Generator[ChatCompletionDeltaMessage, Any, None]:
         pass
@@ -110,6 +112,7 @@ class BaseChatClient(ABC):
         response_format: dict | None = None,
         stream_options: ChatCompletionStreamOptionsParam | None = None,
         top_p: float | NotGiven | None = NOT_GIVEN,
+        skip_cutoff: bool = False,
         **kwargs,
     ) -> ChatCompletionMessage | Generator[ChatCompletionDeltaMessage, Any, None]:
         pass
@@ -127,6 +130,7 @@ class BaseChatClient(ABC):
         response_format: dict | None = None,
         stream_options: ChatCompletionStreamOptionsParam | None = None,
         top_p: float | NotGiven | None = NOT_GIVEN,
+        skip_cutoff: bool = False,
         **kwargs,
     ) -> ChatCompletionMessage | Generator[ChatCompletionDeltaMessage, Any, None]:
         pass
@@ -212,6 +216,7 @@ class BaseAsyncChatClient(ABC):
         response_format: dict | None = None,
         stream_options: ChatCompletionStreamOptionsParam | None = None,
         top_p: float | NotGiven | None = NOT_GIVEN,
+        skip_cutoff: bool = False,
         **kwargs,
     ) -> ChatCompletionMessage:
         pass
@@ -230,6 +235,7 @@ class BaseAsyncChatClient(ABC):
         response_format: dict | None = None,
         stream_options: ChatCompletionStreamOptionsParam | None = None,
         top_p: float | NotGiven | None = NOT_GIVEN,
+        skip_cutoff: bool = False,
         **kwargs,
     ) -> AsyncGenerator[ChatCompletionDeltaMessage, None]:
         pass
@@ -248,6 +254,7 @@ class BaseAsyncChatClient(ABC):
         response_format: dict | None = None,
         stream_options: ChatCompletionStreamOptionsParam | None = None,
         top_p: float | NotGiven | None = NOT_GIVEN,
+        skip_cutoff: bool = False,
         **kwargs,
     ) -> ChatCompletionMessage | AsyncGenerator[ChatCompletionDeltaMessage, None]:
         pass
@@ -265,6 +272,7 @@ class BaseAsyncChatClient(ABC):
         response_format: dict | None = None,
         stream_options: ChatCompletionStreamOptionsParam | None = None,
         top_p: float | NotGiven | None = NOT_GIVEN,
+        skip_cutoff: bool = False,
         **kwargs,
     ) -> ChatCompletionMessage | AsyncGenerator[ChatCompletionDeltaMessage, None]:
         pass

{vectorvein-0.1.57 → vectorvein-0.1.59}/src/vectorvein/chat_clients/gemini_client.py

@@ -66,6 +66,7 @@ class GeminiChatClient(BaseChatClient):
         response_format: dict | None = None,
         stream_options: ChatCompletionStreamOptionsParam | None = None,
         top_p: float | NotGiven | None = NOT_GIVEN,
+        skip_cutoff: bool = False,
         **kwargs,
     ) -> ChatCompletionMessage:
         pass
@@ -83,6 +84,7 @@ class GeminiChatClient(BaseChatClient):
         response_format: dict | None = None,
         stream_options: ChatCompletionStreamOptionsParam | None = None,
         top_p: float | NotGiven | None = NOT_GIVEN,
+        skip_cutoff: bool = False,
         **kwargs,
     ) -> Generator[ChatCompletionDeltaMessage, None, None]:
         pass
@@ -100,6 +102,7 @@ class GeminiChatClient(BaseChatClient):
         response_format: dict | None = None,
         stream_options: ChatCompletionStreamOptionsParam | None = None,
         top_p: float | NotGiven | None = NOT_GIVEN,
+        skip_cutoff: bool = False,
         **kwargs,
     ) -> ChatCompletionMessage | Generator[ChatCompletionDeltaMessage, Any, None]:
         pass
@@ -116,6 +119,7 @@ class GeminiChatClient(BaseChatClient):
         response_format: dict | None = None,
         stream_options: ChatCompletionStreamOptionsParam | None = None,
         top_p: float | NotGiven | None = NOT_GIVEN,
+        skip_cutoff: bool = False,
         **kwargs,
     ):
         if model is not None:
@@ -133,7 +137,7 @@ class GeminiChatClient(BaseChatClient):
         else:
             system_prompt = ""
 
-        if self.context_length_control == ContextLengthControlType.Latest:
+        if not skip_cutoff and self.context_length_control == ContextLengthControlType.Latest:
             messages = cutoff_messages(
                 messages,
                 max_count=self.model_setting.context_length,
@@ -197,7 +201,7 @@ class GeminiChatClient(BaseChatClient):
                 if self.http_client:
                     client = self.http_client
                 else:
-                    client = httpx.Client()
+                    client = httpx.Client(timeout=300)
                 with client.stream("POST", url, headers=headers, params=params, json=request_body) as response:
                     for chunk in response.iter_lines():
                         message = {"content": "", "tool_calls": []}
@@ -236,7 +240,7 @@ class GeminiChatClient(BaseChatClient):
             if self.http_client:
                 client = self.http_client
             else:
-                client = httpx.Client()
+                client = httpx.Client(timeout=300)
             response = client.post(url, json=request_body, headers=headers, params=params, timeout=None).json()
             if "error" in response:
                 raise Exception(response["error"])
@@ -313,6 +317,7 @@ class AsyncGeminiChatClient(BaseAsyncChatClient):
         response_format: dict | None = None,
         stream_options: ChatCompletionStreamOptionsParam | None = None,
         top_p: float | NotGiven | None = NOT_GIVEN,
+        skip_cutoff: bool = False,
         **kwargs,
     ) -> ChatCompletionMessage:
         pass
@@ -330,6 +335,7 @@ class AsyncGeminiChatClient(BaseAsyncChatClient):
         response_format: dict | None = None,
         stream_options: ChatCompletionStreamOptionsParam | None = None,
         top_p: float | NotGiven | None = NOT_GIVEN,
+        skip_cutoff: bool = False,
         **kwargs,
     ) -> AsyncGenerator[ChatCompletionDeltaMessage, Any]:
         pass
@@ -347,6 +353,7 @@ class AsyncGeminiChatClient(BaseAsyncChatClient):
         response_format: dict | None = None,
         stream_options: ChatCompletionStreamOptionsParam | None = None,
         top_p: float | NotGiven | None = NOT_GIVEN,
+        skip_cutoff: bool = False,
         **kwargs,
     ) -> ChatCompletionMessage | AsyncGenerator[ChatCompletionDeltaMessage, Any]:
         pass
@@ -363,6 +370,7 @@ class AsyncGeminiChatClient(BaseAsyncChatClient):
         response_format: dict | None = None,
         stream_options: ChatCompletionStreamOptionsParam | None = None,
         top_p: float | NotGiven | None = NOT_GIVEN,
+        skip_cutoff: bool = False,
         **kwargs,
     ):
         if model is not None:
@@ -380,7 +388,7 @@ class AsyncGeminiChatClient(BaseAsyncChatClient):
         else:
             system_prompt = ""
 
-        if self.context_length_control == ContextLengthControlType.Latest:
+        if not skip_cutoff and self.context_length_control == ContextLengthControlType.Latest:
             messages = cutoff_messages(
                 messages,
                 max_count=self.model_setting.context_length,
@@ -444,7 +452,7 @@ class AsyncGeminiChatClient(BaseAsyncChatClient):
                 if self.http_client:
                     client = self.http_client
                 else:
-                    client = httpx.AsyncClient()
+                    client = httpx.AsyncClient(timeout=300)
                 async with client.stream("POST", url, headers=headers, params=params, json=request_body) as response:
                     async for chunk in response.aiter_lines():
                         message = {"content": "", "tool_calls": []}
@@ -483,7 +491,7 @@ class AsyncGeminiChatClient(BaseAsyncChatClient):
             if self.http_client:
                 client = self.http_client
             else:
-                client = httpx.AsyncClient()
+                client = httpx.AsyncClient(timeout=300)
             async with client:
                 response = await client.post(url, json=request_body, headers=headers, params=params, timeout=None)
                 response = response.json()

{vectorvein-0.1.57 → vectorvein-0.1.59}/src/vectorvein/chat_clients/minimax_client.py

@@ -92,6 +92,7 @@ class MiniMaxChatClient(BaseChatClient):
         response_format: dict | None = None,
         stream_options: ChatCompletionStreamOptionsParam | None = None,
         top_p: float | NotGiven | None = NOT_GIVEN,
+        skip_cutoff: bool = False,
         **kwargs,
     ) -> ChatCompletionMessage:
         pass
@@ -109,6 +110,7 @@ class MiniMaxChatClient(BaseChatClient):
         response_format: dict | None = None,
         stream_options: ChatCompletionStreamOptionsParam | None = None,
         top_p: float | NotGiven | None = NOT_GIVEN,
+        skip_cutoff: bool = False,
         **kwargs,
     ) -> Generator[ChatCompletionDeltaMessage, None, None]:
         pass
@@ -126,6 +128,7 @@ class MiniMaxChatClient(BaseChatClient):
         response_format: dict | None = None,
         stream_options: ChatCompletionStreamOptionsParam | None = None,
         top_p: float | NotGiven | None = NOT_GIVEN,
+        skip_cutoff: bool = False,
         **kwargs,
     ) -> ChatCompletionMessage | Generator[ChatCompletionDeltaMessage, Any, None]:
         pass
@@ -142,6 +145,7 @@ class MiniMaxChatClient(BaseChatClient):
         response_format: dict | None = None,
         stream_options: ChatCompletionStreamOptionsParam | None = None,
         top_p: float | NotGiven | None = NOT_GIVEN,
+        skip_cutoff: bool = False,
         **kwargs,
     ):
         if model is not None:
@@ -166,7 +170,7 @@ class MiniMaxChatClient(BaseChatClient):
                 self.endpoint_id = endpoint_choice
             self.endpoint = settings.get_endpoint(self.endpoint_id)
 
-        if self.context_length_control == ContextLengthControlType.Latest:
+        if not skip_cutoff and self.context_length_control == ContextLengthControlType.Latest:
             messages = cutoff_messages(
                 messages,
                 max_count=self.model_setting.context_length,
@@ -337,6 +341,7 @@ class AsyncMiniMaxChatClient(BaseAsyncChatClient):
         response_format: dict | None = None,
         stream_options: ChatCompletionStreamOptionsParam | None = None,
         top_p: float | NotGiven | None = NOT_GIVEN,
+        skip_cutoff: bool = False,
         **kwargs,
     ) -> ChatCompletionMessage:
         pass
@@ -354,6 +359,7 @@ class AsyncMiniMaxChatClient(BaseAsyncChatClient):
         response_format: dict | None = None,
         stream_options: ChatCompletionStreamOptionsParam | None = None,
         top_p: float | NotGiven | None = NOT_GIVEN,
+        skip_cutoff: bool = False,
         **kwargs,
     ) -> AsyncGenerator[ChatCompletionDeltaMessage, Any]:
         pass
@@ -371,6 +377,7 @@ class AsyncMiniMaxChatClient(BaseAsyncChatClient):
         response_format: dict | None = None,
         stream_options: ChatCompletionStreamOptionsParam | None = None,
         top_p: float | NotGiven | None = NOT_GIVEN,
+        skip_cutoff: bool = False,
         **kwargs,
     ) -> ChatCompletionMessage | AsyncGenerator[ChatCompletionDeltaMessage, Any]:
         pass
@@ -387,6 +394,7 @@ class AsyncMiniMaxChatClient(BaseAsyncChatClient):
         response_format: dict | None = None,
         stream_options: ChatCompletionStreamOptionsParam | None = None,
         top_p: float | NotGiven | None = NOT_GIVEN,
+        skip_cutoff: bool = False,
         **kwargs,
     ):
         if model is not None:
@@ -411,7 +419,7 @@ class AsyncMiniMaxChatClient(BaseAsyncChatClient):
                 self.endpoint_id = endpoint_choice
             self.endpoint = settings.get_endpoint(self.endpoint_id)
 
-        if self.context_length_control == ContextLengthControlType.Latest:
+        if not skip_cutoff and self.context_length_control == ContextLengthControlType.Latest:
             messages = cutoff_messages(
                 messages,
                 max_count=self.model_setting.context_length,

{vectorvein-0.1.57 → vectorvein-0.1.59}/src/vectorvein/chat_clients/openai_compatible_client.py

@@ -99,6 +99,7 @@ class OpenAICompatibleChatClient(BaseChatClient):
         response_format: dict | None = None,
         stream_options: ChatCompletionStreamOptionsParam | None | OpenAINotGiven = NOT_GIVEN,
         top_p: float | NotGiven | None = NOT_GIVEN,
+        skip_cutoff: bool = False,
         **kwargs,
     ) -> ChatCompletionMessage:
         pass
@@ -116,6 +117,7 @@ class OpenAICompatibleChatClient(BaseChatClient):
         response_format: dict | None = None,
         stream_options: ChatCompletionStreamOptionsParam | None | OpenAINotGiven = NOT_GIVEN,
         top_p: float | NotGiven | None = NOT_GIVEN,
+        skip_cutoff: bool = False,
         **kwargs,
     ) -> Generator[ChatCompletionDeltaMessage, None, None]:
         pass
@@ -133,6 +135,7 @@ class OpenAICompatibleChatClient(BaseChatClient):
         response_format: dict | None = None,
         stream_options: ChatCompletionStreamOptionsParam | None | OpenAINotGiven = NOT_GIVEN,
         top_p: float | NotGiven | None = NOT_GIVEN,
+        skip_cutoff: bool = False,
         **kwargs,
     ) -> ChatCompletionMessage | Generator[ChatCompletionDeltaMessage, Any, None]:
         pass
@@ -149,6 +152,7 @@ class OpenAICompatibleChatClient(BaseChatClient):
         response_format: dict | None = None,
         stream_options: ChatCompletionStreamOptionsParam | None | OpenAINotGiven = NOT_GIVEN,
         top_p: float | NotGiven | None = NOT_GIVEN,
+        skip_cutoff: bool = False,
         **kwargs,
     ):
         if model is not None:
@@ -165,7 +169,7 @@ class OpenAICompatibleChatClient(BaseChatClient):
         if self.model_id is None:
             self.model_id = self.model_setting.id
 
-        if self.context_length_control == ContextLengthControlType.Latest:
+        if not skip_cutoff and self.context_length_control == ContextLengthControlType.Latest:
             messages = cutoff_messages(
                 messages,
                 max_count=self.model_setting.context_length,
@@ -361,6 +365,7 @@ class AsyncOpenAICompatibleChatClient(BaseAsyncChatClient):
         response_format: dict | None = None,
         stream_options: ChatCompletionStreamOptionsParam | None | OpenAINotGiven = NOT_GIVEN,
         top_p: float | NotGiven | None = NOT_GIVEN,
+        skip_cutoff: bool = False,
         **kwargs,
     ) -> ChatCompletionMessage:
         pass
@@ -378,6 +383,7 @@ class AsyncOpenAICompatibleChatClient(BaseAsyncChatClient):
         response_format: dict | None = None,
         stream_options: ChatCompletionStreamOptionsParam | None | OpenAINotGiven = NOT_GIVEN,
         top_p: float | NotGiven | None = NOT_GIVEN,
+        skip_cutoff: bool = False,
         **kwargs,
     ) -> AsyncGenerator[ChatCompletionDeltaMessage, Any]:
         pass
@@ -395,6 +401,7 @@ class AsyncOpenAICompatibleChatClient(BaseAsyncChatClient):
         response_format: dict | None = None,
         stream_options: ChatCompletionStreamOptionsParam | None | OpenAINotGiven = NOT_GIVEN,
         top_p: float | NotGiven | None = NOT_GIVEN,
+        skip_cutoff: bool = False,
         **kwargs,
     ) -> ChatCompletionMessage | AsyncGenerator[ChatCompletionDeltaMessage, Any]:
         pass
@@ -411,6 +418,7 @@ class AsyncOpenAICompatibleChatClient(BaseAsyncChatClient):
         response_format: dict | None = None,
         stream_options: ChatCompletionStreamOptionsParam | None | OpenAINotGiven = NOT_GIVEN,
         top_p: float | NotGiven | None = NOT_GIVEN,
+        skip_cutoff: bool = False,
         **kwargs,
     ):
         if model is not None:
@@ -427,7 +435,7 @@ class AsyncOpenAICompatibleChatClient(BaseAsyncChatClient):
         if self.model_id is None:
             self.model_id = self.model_setting.id
 
-        if self.context_length_control == ContextLengthControlType.Latest:
+        if not skip_cutoff and self.context_length_control == ContextLengthControlType.Latest:
             messages = cutoff_messages(
                 messages,
                 max_count=self.model_setting.context_length,