gllm-inference-binary 0.5.15__cp311-cp311-win_amd64.whl → 0.5.17__cp311-cp311-win_amd64.whl

gllm_inference/em_invoker/azure_openai_em_invoker.pyi

@@ -3,7 +3,7 @@ from gllm_core.utils.retry import RetryConfig as RetryConfig
 from gllm_inference.constants import DEFAULT_AZURE_OPENAI_API_VERSION as DEFAULT_AZURE_OPENAI_API_VERSION, INVOKER_PROPAGATED_MAX_RETRIES as INVOKER_PROPAGATED_MAX_RETRIES
 from gllm_inference.em_invoker.openai_em_invoker import OpenAIEMInvoker as OpenAIEMInvoker
 from gllm_inference.em_invoker.schema.openai import Key as Key
-from gllm_inference.schema import ModelId as ModelId, ModelProvider as ModelProvider
+from gllm_inference.schema import ModelId as ModelId, ModelProvider as ModelProvider, TruncationConfig as TruncationConfig
 from typing import Any
 
 class AzureOpenAIEMInvoker(OpenAIEMInvoker):
@@ -16,6 +16,7 @@ class AzureOpenAIEMInvoker(OpenAIEMInvoker):
         client (AsyncAzureOpenAI): The client for the Azure OpenAI API.
         default_hyperparameters (dict[str, Any]): Default hyperparameters for invoking the embedding model.
         retry_config (RetryConfig): The retry configuration for the embedding model.
+        truncation_config (TruncationConfig | None): The truncation configuration for the embedding model.
 
     Input types:
         The `AzureOpenAIEMInvoker` only supports text inputs.
@@ -68,7 +69,7 @@ class AzureOpenAIEMInvoker(OpenAIEMInvoker):
         ```
     '''
     client: Incomplete
-    def __init__(self, azure_endpoint: str, azure_deployment: str, api_key: str | None = None, api_version: str = ..., model_kwargs: dict[str, Any] | None = None, default_hyperparameters: dict[str, Any] | None = None, retry_config: RetryConfig | None = None) -> None:
+    def __init__(self, azure_endpoint: str, azure_deployment: str, api_key: str | None = None, api_version: str = ..., model_kwargs: dict[str, Any] | None = None, default_hyperparameters: dict[str, Any] | None = None, retry_config: RetryConfig | None = None, truncation_config: TruncationConfig | None = None) -> None:
         """Initializes a new instance of the AzureOpenAIEMInvoker class.
 
         Args:
@@ -83,4 +84,6 @@ class AzureOpenAIEMInvoker(OpenAIEMInvoker):
                 Defaults to None.
             retry_config (RetryConfig | None, optional): The retry configuration for the embedding model.
                 Defaults to None, in which case a default config with no retry and 30.0 seconds timeout will be used.
+            truncation_config (TruncationConfig | None, optional): Configuration for text truncation behavior.
+                Defaults to None, in which case no truncation is applied.
         """

gllm_inference/em_invoker/bedrock_em_invoker.pyi

@@ -3,7 +3,7 @@ from enum import StrEnum
 from gllm_core.utils.retry import RetryConfig as RetryConfig
 from gllm_inference.em_invoker.em_invoker import BaseEMInvoker as BaseEMInvoker
 from gllm_inference.em_invoker.schema.bedrock import InputType as InputType, Key as Key, OutputType as OutputType
-from gllm_inference.schema import ModelId as ModelId, ModelProvider as ModelProvider, Vector as Vector
+from gllm_inference.schema import ModelId as ModelId, ModelProvider as ModelProvider, TruncationConfig as TruncationConfig, Vector as Vector
 from typing import Any
 
 class ModelType(StrEnum):
@@ -24,6 +24,7 @@ class BedrockEMInvoker(BaseEMInvoker):
         client_kwargs (dict[str, Any]): The Bedrock client kwargs.
         default_hyperparameters (dict[str, Any]): Default hyperparameters for invoking the embedding model.
         retry_config (RetryConfig): The retry configuration for the embedding model.
+        truncation_config (TruncationConfig | None): The truncation configuration for the embedding model.
 
     Input types:
         The `BedrockEMInvoker` only supports text inputs.
@@ -77,7 +78,7 @@ class BedrockEMInvoker(BaseEMInvoker):
     '''
     session: Incomplete
     client_kwargs: Incomplete
-    def __init__(self, model_name: str, access_key_id: str | None = None, secret_access_key: str | None = None, region_name: str = 'us-east-1', model_kwargs: dict[str, Any] | None = None, default_hyperparameters: dict[str, Any] | None = None, retry_config: RetryConfig | None = None) -> None:
+    def __init__(self, model_name: str, access_key_id: str | None = None, secret_access_key: str | None = None, region_name: str = 'us-east-1', model_kwargs: dict[str, Any] | None = None, default_hyperparameters: dict[str, Any] | None = None, retry_config: RetryConfig | None = None, truncation_config: TruncationConfig | None = None) -> None:
         '''Initializes a new instance of the BedrockEMInvoker class.
 
         Args:
@@ -93,6 +94,8 @@ class BedrockEMInvoker(BaseEMInvoker):
                 Defaults to None.
             retry_config (RetryConfig | None, optional): The retry configuration for the embedding model.
                 Defaults to None, in which case a default config with no retry and 30.0 seconds timeout will be used.
+            truncation_config (TruncationConfig | None, optional): Configuration for text truncation behavior.
+                Defaults to None, in which case no truncation is applied.
 
         Raises:
             ValueError: If the model name is not supported.

gllm_inference/em_invoker/em_invoker.pyi

@@ -4,7 +4,7 @@ from abc import ABC
 from gllm_core.utils.retry import RetryConfig
 from gllm_inference.constants import DOCUMENT_MIME_TYPES as DOCUMENT_MIME_TYPES, INVOKER_DEFAULT_TIMEOUT as INVOKER_DEFAULT_TIMEOUT
 from gllm_inference.exceptions import parse_error_message as parse_error_message
-from gllm_inference.schema import Attachment as Attachment, AttachmentType as AttachmentType, EMContent as EMContent, ModelId as ModelId, Vector as Vector
+from gllm_inference.schema import Attachment as Attachment, AttachmentType as AttachmentType, EMContent as EMContent, ModelId as ModelId, TruncateSide as TruncateSide, TruncationConfig as TruncationConfig, Vector as Vector
 from typing import Any
 
 class BaseEMInvoker(ABC, metaclass=abc.ABCMeta):
@@ -16,12 +16,17 @@ class BaseEMInvoker(ABC, metaclass=abc.ABCMeta):
         model_id (str): The model ID of the embedding model.
         model_provider (str): The provider of the embedding model.
         model_name (str): The name of the embedding model.
-        default_hyperparameters (dict[str, Any]): Default hyperparameters for invoking the embedding model.
+        default_hyperparameters (dict[str, Any]): Default hyperparameters for invoking the
+            embedding model. Defaults to None, in which case an empty dictionary is used.
         retry_config (RetryConfig): The retry configuration for the embedding model.
+            Defaults to None, in which case a default config with no retry and 30.0 seconds timeout will be used.
+        truncation_config (TruncationConfig | None): The truncation configuration for the embedding model.
+            Defaults to None, in which case no truncation is applied.
     """
     default_hyperparameters: Incomplete
     retry_config: Incomplete
-    def __init__(self, model_id: ModelId, default_hyperparameters: dict[str, Any] | None = None, supported_attachments: set[str] | None = None, retry_config: RetryConfig | None = None) -> None:
+    truncation_config: Incomplete
+    def __init__(self, model_id: ModelId, default_hyperparameters: dict[str, Any] | None = None, supported_attachments: set[str] | None = None, retry_config: RetryConfig | None = None, truncation_config: TruncationConfig | None = None) -> None:
         """Initializes a new instance of the BaseEMInvoker class.
 
         Args:
@@ -32,6 +37,8 @@ class BaseEMInvoker(ABC, metaclass=abc.ABCMeta):
                 in which case an empty set is used (indicating that no attachments are supported).
             retry_config (RetryConfig | None, optional): The retry configuration for the embedding model.
                 Defaults to None, in which case a default config with no retry and 30.0 seconds timeout will be used.
+            truncation_config (TruncationConfig | None, optional): Configuration for text truncation behavior.
+                Defaults to None, in which case no truncation is applied.
         """
     @property
     def model_id(self) -> str:

gllm_inference/em_invoker/google_em_invoker.pyi

@@ -3,7 +3,7 @@ from gllm_core.utils.retry import RetryConfig as RetryConfig
 from gllm_inference.constants import GOOGLE_SCOPES as GOOGLE_SCOPES, SECONDS_TO_MILLISECONDS as SECONDS_TO_MILLISECONDS
 from gllm_inference.em_invoker.em_invoker import BaseEMInvoker as BaseEMInvoker
 from gllm_inference.em_invoker.schema.google import Key as Key
-from gllm_inference.schema import ModelId as ModelId, ModelProvider as ModelProvider, Vector as Vector
+from gllm_inference.schema import ModelId as ModelId, ModelProvider as ModelProvider, TruncationConfig as TruncationConfig, Vector as Vector
 from typing import Any
 
 SUPPORTED_ATTACHMENTS: Incomplete
@@ -17,7 +17,8 @@ class GoogleEMInvoker(BaseEMInvoker):
         model_name (str): The name of the embedding model.
         client_params (dict[str, Any]): The Google client instance init parameters.
         default_hyperparameters (dict[str, Any]): Default hyperparameters for invoking the embedding model.
-        retry_config (RetryConfig | None): The retry configuration for the language model.
+        retry_config (RetryConfig): The retry configuration for the embedding model.
+        truncation_config (TruncationConfig | None): The truncation configuration for the embedding model.
 
     Initialization:
         The `GoogleEMInvoker` can use either Google Gen AI or Google Vertex AI.
@@ -98,7 +99,7 @@ class GoogleEMInvoker(BaseEMInvoker):
         ```
     '''
     client_params: Incomplete
-    def __init__(self, model_name: str, api_key: str | None = None, credentials_path: str | None = None, project_id: str | None = None, location: str = 'us-central1', model_kwargs: dict[str, Any] | None = None, default_hyperparameters: dict[str, Any] | None = None, retry_config: RetryConfig | None = None) -> None:
+    def __init__(self, model_name: str, api_key: str | None = None, credentials_path: str | None = None, project_id: str | None = None, location: str = 'us-central1', model_kwargs: dict[str, Any] | None = None, default_hyperparameters: dict[str, Any] | None = None, retry_config: RetryConfig | None = None, truncation_config: TruncationConfig | None = None) -> None:
         '''Initializes a new instance of the GoogleEMInvoker class.
 
         Args:
@@ -117,6 +118,8 @@ class GoogleEMInvoker(BaseEMInvoker):
                 Defaults to None.
             retry_config (RetryConfig | None, optional): The retry configuration for the embedding model.
                 Defaults to None, in which case a default config with no retry and 30.0 seconds timeout will be used.
+            truncation_config (TruncationConfig | None, optional): Configuration for text truncation behavior.
+                Defaults to None, in which case no truncation is applied.
 
         Note:
             If neither `api_key` nor `credentials_path` is provided, Google Gen AI will be used by default.

gllm_inference/em_invoker/langchain_em_invoker.pyi

@@ -3,7 +3,7 @@ from gllm_core.utils.retry import RetryConfig
 from gllm_inference.constants import INVOKER_DEFAULT_TIMEOUT as INVOKER_DEFAULT_TIMEOUT, INVOKER_PROPAGATED_MAX_RETRIES as INVOKER_PROPAGATED_MAX_RETRIES
 from gllm_inference.em_invoker.em_invoker import BaseEMInvoker as BaseEMInvoker
 from gllm_inference.em_invoker.schema.langchain import Key as Key
-from gllm_inference.schema import ModelId as ModelId, ModelProvider as ModelProvider, Vector as Vector
+from gllm_inference.schema import ModelId as ModelId, ModelProvider as ModelProvider, TruncationConfig as TruncationConfig, Vector as Vector
 from gllm_inference.utils import load_langchain_model as load_langchain_model, parse_model_data as parse_model_data
 from langchain_core.embeddings import Embeddings as Embeddings
 from typing import Any
@@ -19,9 +19,10 @@ class LangChainEMInvoker(BaseEMInvoker):
         model_name (str): The name of the embedding model.
         em (Embeddings): The instance to interact with an embedding model defined using LangChain's Embeddings.
         retry_config (RetryConfig): The retry configuration for the embedding model.
+        truncation_config (TruncationConfig | None): The truncation configuration for the embedding model.
     """
     model: Incomplete
-    def __init__(self, model: Embeddings | None = None, model_class_path: str | None = None, model_name: str | None = None, model_kwargs: dict[str, Any] | None = None, default_hyperparameters: dict[str, Any] | None = None, retry_config: RetryConfig | None = None) -> None:
+    def __init__(self, model: Embeddings | None = None, model_class_path: str | None = None, model_name: str | None = None, model_kwargs: dict[str, Any] | None = None, default_hyperparameters: dict[str, Any] | None = None, retry_config: RetryConfig | None = None, truncation_config: TruncationConfig | None = None) -> None:
         '''Initializes a new instance of the LangChainEMInvoker class.
 
         Args:
@@ -38,4 +39,6 @@ class LangChainEMInvoker(BaseEMInvoker):
                 Defaults to None.
             retry_config (RetryConfig | None, optional): The retry configuration for the embedding model.
                 Defaults to None, in which case a default config with no retry and 30.0 seconds timeout will be used.
+            truncation_config (TruncationConfig | None, optional): Configuration for text truncation behavior.
+                Defaults to None, in which case no truncation is applied.
         '''

gllm_inference/em_invoker/openai_compatible_em_invoker.pyi

@@ -3,7 +3,7 @@ from gllm_core.utils.retry import RetryConfig as RetryConfig
 from gllm_inference.constants import INVOKER_PROPAGATED_MAX_RETRIES as INVOKER_PROPAGATED_MAX_RETRIES
 from gllm_inference.em_invoker.openai_em_invoker import OpenAIEMInvoker as OpenAIEMInvoker
 from gllm_inference.em_invoker.schema.openai_compatible import Key as Key
-from gllm_inference.schema import ModelId as ModelId, ModelProvider as ModelProvider
+from gllm_inference.schema import ModelId as ModelId, ModelProvider as ModelProvider, TruncationConfig as TruncationConfig
 from typing import Any
 
 class OpenAICompatibleEMInvoker(OpenAIEMInvoker):
@@ -16,6 +16,8 @@ class OpenAICompatibleEMInvoker(OpenAIEMInvoker):
         client (AsyncOpenAI): The OpenAI client instance.
         default_hyperparameters (dict[str, Any]): Default hyperparameters for invoking the embedding model.
         retry_config (RetryConfig): The retry configuration for the embedding model.
+        truncation_config (TruncationConfig | None): The truncation configuration for the embedding model.
+
 
     When to use:
         The `OpenAICompatibleEMInvoker` is designed to interact with endpoints that are compatible with OpenAI\'s
@@ -76,7 +78,7 @@ class OpenAICompatibleEMInvoker(OpenAIEMInvoker):
         ```
     '''
     client: Incomplete
-    def __init__(self, model_name: str, base_url: str, api_key: str | None = None, model_kwargs: dict[str, Any] | None = None, default_hyperparameters: dict[str, Any] | None = None, retry_config: RetryConfig | None = None) -> None:
+    def __init__(self, model_name: str, base_url: str, api_key: str | None = None, model_kwargs: dict[str, Any] | None = None, default_hyperparameters: dict[str, Any] | None = None, retry_config: RetryConfig | None = None, truncation_config: TruncationConfig | None = None) -> None:
         """Initializes a new instance of the OpenAICompatibleEMInvoker class.
 
         Args:
@@ -89,4 +91,6 @@ class OpenAICompatibleEMInvoker(OpenAIEMInvoker):
                 Defaults to None.
             retry_config (RetryConfig | None, optional): The retry configuration for the embedding model.
                 Defaults to None, in which case a default config with no retry and 30.0 seconds timeout will be used.
+            truncation_config (TruncationConfig | None, optional): Configuration for text truncation behavior.
+                Defaults to None, in which case no truncation is applied.
         """

gllm_inference/em_invoker/openai_em_invoker.pyi

@@ -4,6 +4,7 @@ from gllm_inference.constants import INVOKER_PROPAGATED_MAX_RETRIES as INVOKER_P
 from gllm_inference.em_invoker.em_invoker import BaseEMInvoker as BaseEMInvoker
 from gllm_inference.em_invoker.schema.openai import Key as Key
 from gllm_inference.schema import ModelId as ModelId, ModelProvider as ModelProvider, Vector as Vector
+from gllm_inference.schema.config import TruncationConfig as TruncationConfig
 from typing import Any
 
 SUPPORTED_ATTACHMENTS: Incomplete
@@ -18,6 +19,7 @@ class OpenAIEMInvoker(BaseEMInvoker):
         client (AsyncOpenAI): The client for the OpenAI API.
         default_hyperparameters (dict[str, Any]): Default hyperparameters for invoking the embedding model.
         retry_config (RetryConfig): The retry configuration for the embedding model.
+        truncation_config (TruncationConfig | None): The truncation configuration for the embedding model.
 
     Input types:
         The `OpenAIEMInvoker` only supports text inputs.
@@ -70,7 +72,7 @@ class OpenAIEMInvoker(BaseEMInvoker):
         ```
     '''
     client: Incomplete
-    def __init__(self, model_name: str, api_key: str | None = None, model_kwargs: dict[str, Any] | None = None, default_hyperparameters: dict[str, Any] | None = None, retry_config: RetryConfig | None = None) -> None:
+    def __init__(self, model_name: str, api_key: str | None = None, model_kwargs: dict[str, Any] | None = None, default_hyperparameters: dict[str, Any] | None = None, retry_config: RetryConfig | None = None, truncation_config: TruncationConfig | None = None) -> None:
         """Initializes a new instance of the OpenAIEMInvoker class.
 
         Args:
@@ -83,4 +85,6 @@ class OpenAIEMInvoker(BaseEMInvoker):
                 Defaults to None.
             retry_config (RetryConfig | None, optional): The retry configuration for the embedding model.
                 Defaults to None, in which case a default config with no retry and 30.0 seconds timeout will be used.
+            truncation_config (TruncationConfig | None, optional): Configuration for text truncation behavior.
+                Defaults to None, in which case no truncation is applied.
         """

gllm_inference/em_invoker/twelevelabs_em_invoker.pyi

@@ -3,7 +3,7 @@ from gllm_core.utils.retry import RetryConfig as RetryConfig
 from gllm_inference.constants import INVOKER_PROPAGATED_MAX_RETRIES as INVOKER_PROPAGATED_MAX_RETRIES
 from gllm_inference.em_invoker.em_invoker import BaseEMInvoker as BaseEMInvoker
 from gllm_inference.em_invoker.schema.twelvelabs import InputType as InputType, Key as Key, OutputType as OutputType
-from gllm_inference.schema import Attachment as Attachment, AttachmentType as AttachmentType, EMContent as EMContent, ModelId as ModelId, ModelProvider as ModelProvider, Vector as Vector
+from gllm_inference.schema import Attachment as Attachment, AttachmentType as AttachmentType, EMContent as EMContent, ModelId as ModelId, ModelProvider as ModelProvider, TruncationConfig as TruncationConfig, Vector as Vector
 from typing import Any
 
 SUPPORTED_ATTACHMENTS: Incomplete
@@ -18,6 +18,7 @@ class TwelveLabsEMInvoker(BaseEMInvoker):
         client (Client): The client for the TwelveLabs API.
         default_hyperparameters (dict[str, Any]): Default hyperparameters for invoking the embedding model.
         retry_config (RetryConfig): The retry configuration for the embedding model.
+        truncation_config (TruncationConfig | None): The truncation configuration for the embedding model.
 
     Input types:
         The `TwelveLabsEMInvoker` supports the following input types: text, audio, and image.
@@ -83,7 +84,7 @@ class TwelveLabsEMInvoker(BaseEMInvoker):
         ```
     '''
     client: Incomplete
-    def __init__(self, model_name: str, api_key: str | None = None, model_kwargs: dict[str, Any] | None = None, default_hyperparameters: dict[str, Any] | None = None, retry_config: RetryConfig | None = None) -> None:
+    def __init__(self, model_name: str, api_key: str | None = None, model_kwargs: dict[str, Any] | None = None, default_hyperparameters: dict[str, Any] | None = None, retry_config: RetryConfig | None = None, truncation_config: TruncationConfig | None = None) -> None:
         """Initializes a new instance of the TwelveLabsEMInvoker class.
 
         Args:
@@ -96,4 +97,6 @@ class TwelveLabsEMInvoker(BaseEMInvoker):
                 Defaults to None.
             retry_config (RetryConfig | None, optional): The retry configuration for the embedding model.
                 Defaults to None, in which case a default config with no retry and 30.0 seconds timeout will be used.
+            truncation_config (TruncationConfig | None, optional): Configuration for text truncation behavior.
+                Defaults to None, in which case no truncation is applied.
         """

gllm_inference/em_invoker/voyage_em_invoker.pyi

@@ -3,7 +3,7 @@ from gllm_core.utils.retry import RetryConfig as RetryConfig
 from gllm_inference.constants import INVOKER_PROPAGATED_MAX_RETRIES as INVOKER_PROPAGATED_MAX_RETRIES
 from gllm_inference.em_invoker.em_invoker import BaseEMInvoker as BaseEMInvoker
 from gllm_inference.em_invoker.schema.voyage import InputType as InputType, Key as Key
-from gllm_inference.schema import Attachment as Attachment, AttachmentType as AttachmentType, EMContent as EMContent, ModelId as ModelId, ModelProvider as ModelProvider, Vector as Vector
+from gllm_inference.schema import Attachment as Attachment, AttachmentType as AttachmentType, EMContent as EMContent, ModelId as ModelId, ModelProvider as ModelProvider, TruncationConfig as TruncationConfig, Vector as Vector
 from typing import Any
 
 SUPPORTED_ATTACHMENTS: Incomplete
@@ -19,6 +19,7 @@ class VoyageEMInvoker(BaseEMInvoker):
         client (Client): The client for the Voyage API.
         default_hyperparameters (dict[str, Any]): Default hyperparameters for invoking the embedding model.
         retry_config (RetryConfig): The retry configuration for the embedding model.
+        truncation_config (TruncationConfig | None): The truncation configuration for the embedding model.
 
     Input types:
         The `VoyageEMInvoker` supports the following input types: text, image, and a tuple containing text and image.
@@ -85,7 +86,7 @@ class VoyageEMInvoker(BaseEMInvoker):
         ```
     '''
     client: Incomplete
-    def __init__(self, model_name: str, api_key: str | None = None, model_kwargs: dict[str, Any] | None = None, default_hyperparameters: dict[str, Any] | None = None, retry_config: RetryConfig | None = None) -> None:
+    def __init__(self, model_name: str, api_key: str | None = None, model_kwargs: dict[str, Any] | None = None, default_hyperparameters: dict[str, Any] | None = None, retry_config: RetryConfig | None = None, truncation_config: TruncationConfig | None = None) -> None:
         """Initializes a new instance of the VoyageEMInvoker class.
 
         Args:
@@ -98,4 +99,6 @@ class VoyageEMInvoker(BaseEMInvoker):
                 Defaults to None.
             retry_config (RetryConfig | None, optional): The retry configuration for the embedding model.
                 Defaults to None, in which case a default config with no retry and 30.0 seconds timeout will be used.
+            truncation_config (TruncationConfig | None, optional): Configuration for text truncation behavior.
+                Defaults to None, in which case no truncation is applied.
         """

gllm_inference/lm_invoker/lm_invoker.pyi

@@ -14,16 +14,15 @@ class Key:
     """Defines valid keys in LM invokers JSON schema."""
     ADDITIONAL_PROPERTIES: str
     ANY_OF: str
+    ARGS_SCHEMA: str
     ARUN: str
+    COROUTINE: str
     DATA_TYPE: str
     DATA_VALUE: str
     DEFAULT: str
     DESCRIPTION: str
     FUNC: str
-    FUNCTION: str
-    META: str
     NAME: str
-    PARAMETERS: str
     PROPERTIES: str
     REQUIRED: str
     TITLE: str

gllm_inference/schema/__init__.pyi

@@ -1,6 +1,7 @@
 from gllm_inference.schema.attachment import Attachment as Attachment
 from gllm_inference.schema.code_exec_result import CodeExecResult as CodeExecResult
-from gllm_inference.schema.enums import AttachmentType as AttachmentType, EmitDataType as EmitDataType, MessageRole as MessageRole
+from gllm_inference.schema.config import TruncationConfig as TruncationConfig
+from gllm_inference.schema.enums import AttachmentType as AttachmentType, EmitDataType as EmitDataType, MessageRole as MessageRole, TruncateSide as TruncateSide
 from gllm_inference.schema.lm_output import LMOutput as LMOutput
 from gllm_inference.schema.message import Message as Message
 from gllm_inference.schema.model_id import ModelId as ModelId, ModelProvider as ModelProvider
@@ -10,4 +11,4 @@ from gllm_inference.schema.tool_call import ToolCall as ToolCall
 from gllm_inference.schema.tool_result import ToolResult as ToolResult
 from gllm_inference.schema.type_alias import EMContent as EMContent, ErrorResponse as ErrorResponse, MessageContent as MessageContent, ResponseSchema as ResponseSchema, Vector as Vector
 
-__all__ = ['Attachment', 'AttachmentType', 'CodeExecResult', 'EMContent', 'EmitDataType', 'ErrorResponse', 'InputTokenDetails', 'MessageContent', 'LMOutput', 'ModelId', 'ModelProvider', 'Message', 'MessageRole', 'OutputTokenDetails', 'Reasoning', 'ResponseSchema', 'TokenUsage', 'ToolCall', 'ToolResult', 'Vector']
+__all__ = ['Attachment', 'AttachmentType', 'CodeExecResult', 'EMContent', 'EmitDataType', 'ErrorResponse', 'InputTokenDetails', 'MessageContent', 'LMOutput', 'ModelId', 'ModelProvider', 'Message', 'MessageRole', 'OutputTokenDetails', 'Reasoning', 'ResponseSchema', 'TokenUsage', 'ToolCall', 'ToolResult', 'TruncateSide', 'TruncationConfig', 'Vector']

gllm_inference/schema/config.pyi

@@ -0,0 +1,15 @@
+from gllm_inference.schema.enums import TruncateSide as TruncateSide
+from pydantic import BaseModel
+
+class TruncationConfig(BaseModel):
+    """Configuration for text truncation behavior.
+
+    Attributes:
+        max_length (int): Maximum length of text content. Required.
+        truncate_side (TruncateSide | None): Side to truncate from when max_length is exceeded.
+            1. TruncateSide.RIGHT: Keep the beginning of the text, truncate from the end (default)
+            2. TruncateSide.LEFT: Keep the end of the text, truncate from the beginning
+            If None, defaults to TruncateSide.RIGHT
+    """
+    max_length: int
+    truncate_side: TruncateSide | None

gllm_inference/schema/enums.pyi

@@ -22,3 +22,8 @@ class MessageRole(StrEnum):
     SYSTEM = 'system'
     USER = 'user'
     ASSISTANT = 'assistant'
+
+class TruncateSide(StrEnum):
+    """Enumeration for truncation sides."""
+    RIGHT = 'RIGHT'
+    LEFT = 'LEFT'

gllm_inference.pyi

@@ -42,6 +42,7 @@ import gllm_inference.request_processor.LMRequestProcessor
 import gllm_core.utils.imports
 import gllm_inference.schema.ModelId
 import gllm_inference.schema.ModelProvider
+import gllm_inference.schema.TruncationConfig
 import openai
 import asyncio
 import enum
@@ -51,6 +52,7 @@ import gllm_inference.exceptions.parse_error_message
 import gllm_inference.schema.Attachment
 import gllm_inference.schema.AttachmentType
 import gllm_inference.schema.EMContent
+import gllm_inference.schema.TruncateSide
 import google
 import google.auth
 import google.genai
@@ -97,8 +99,6 @@ import litellm
 import inspect
 import time
 import jsonschema
-import langchain_core.utils
-import langchain_core.utils.function_calling
 import gllm_inference.schema.MessageContent
 import gllm_inference.utils.validate_string_enum
 import gllm_inference.schema.CodeExecResult

{gllm_inference_binary-0.5.15.dist-info → gllm_inference_binary-0.5.17.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: gllm-inference-binary
-Version: 0.5.15
+Version: 0.5.17
 Summary: A library containing components related to model inferences in Gen AI applications.
 Author: Henry Wicaksono
 Author-email: henry.wicaksono@gdplabs.id

{gllm_inference_binary-0.5.15.dist-info → gllm_inference_binary-0.5.17.dist-info}/RECORD

@@ -10,15 +10,15 @@ gllm_inference/catalog/lm_request_processor_catalog.pyi,sha256=GemCEjFRHNChtNOfb
 gllm_inference/catalog/prompt_builder_catalog.pyi,sha256=iViWB4SaezzjQY4UY1YxeoXUNxqxa2cTJGaD9JSx4Q8,3279
 gllm_inference/constants.pyi,sha256=kvYdaD0afopdfvijkyTSq1e5dsUKiN232wA9KlcPGs8,325
 gllm_inference/em_invoker/__init__.pyi,sha256=pmbsjmsqXwfe4WPykMnrmasKrYuylJWnf2s0pbo0ioM,997
-gllm_inference/em_invoker/azure_openai_em_invoker.pyi,sha256=QimqPII-KN9OgsfH1Iubn_tCHhtWjPQ5rilZoT6Ir-U,4688
-gllm_inference/em_invoker/bedrock_em_invoker.pyi,sha256=haqfFHUn7UrULGNj9XuM13FfcmjVY_4RgI1XpKh46s8,5176
-gllm_inference/em_invoker/em_invoker.pyi,sha256=KX4i0xBWR5j6z14nEL6T8at3StKfdf3miQ4xixtYhZk,4424
-gllm_inference/em_invoker/google_em_invoker.pyi,sha256=c0XJuLS4ji-Y9aHmbb8PRLwrbH6QA2WtdS1-2HbWFq8,6306
+gllm_inference/em_invoker/azure_openai_em_invoker.pyi,sha256=g1I3Aexg5VeDeU_zbZWCVgca2fhrUztVrpbzS5GBBYI,5072
+gllm_inference/em_invoker/bedrock_em_invoker.pyi,sha256=EbXyj_U0NK9QSnq9HSeCHJ1Hw7xg2Twqj4wcbkHuvng,5560
+gllm_inference/em_invoker/em_invoker.pyi,sha256=l_jnFRrfoVatVwKawpPA018bM0U6wMc8j_DVxkL8T4s,5133
+gllm_inference/em_invoker/google_em_invoker.pyi,sha256=DH_ddq07EfUgv5L0OTZVOhg-p3CqEpcWAjmCYJsSljM,6684
 gllm_inference/em_invoker/langchain/__init__.pyi,sha256=aOTlRvS9aG1tBErjsmhe75s4Sq-g2z9ArfGqNW7QyEs,151
 gllm_inference/em_invoker/langchain/em_invoker_embeddings.pyi,sha256=gEX21gJLngUh9fZo8v6Vbh0gpWFFqS2S-dGNZSrDjFQ,2409
-gllm_inference/em_invoker/langchain_em_invoker.pyi,sha256=sFmsRE89MIdnD8g0VSMsdLvtfZL6dfPkUtDhH_WfgLc,2823
-gllm_inference/em_invoker/openai_compatible_em_invoker.pyi,sha256=S5lRg3MeLoenOkeAG079I22kPaFXAFrltSoWcQSDK4I,5070
-gllm_inference/em_invoker/openai_em_invoker.pyi,sha256=1WTuPtu5RlZCUcBHMXR5xEkAufWCHshKA8_JW7oFakE,4321
+gllm_inference/em_invoker/langchain_em_invoker.pyi,sha256=vQO5yheucM5eb7xWcwb4U7eGXASapwgOFC_SZdyysHA,3207
+gllm_inference/em_invoker/openai_compatible_em_invoker.pyi,sha256=zEYOBDXKQhvcMGer9DYDu50_3KRDjYyN8-JgpBIFPOI,5456
+gllm_inference/em_invoker/openai_em_invoker.pyi,sha256=0TDIQa-5UwsPcVxgkze-QJJWrt-ToakAKbuAk9TW5SM,4746
 gllm_inference/em_invoker/schema/__init__.pyi,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
 gllm_inference/em_invoker/schema/bedrock.pyi,sha256=6xP5T5jxane_Ecrb-6zf_X678Tj3svQUNy0SgHQArRM,443
 gllm_inference/em_invoker/schema/google.pyi,sha256=lPzJ-f18qVar6dctdN4eQWrxWrOFHC9zJ4cuLXXMytw,153
@@ -27,8 +27,8 @@ gllm_inference/em_invoker/schema/openai.pyi,sha256=rNRqN62y5wHOKlr4T0n0m41ikAnSr
 gllm_inference/em_invoker/schema/openai_compatible.pyi,sha256=A9MOeBhI-IPuvewOk4YYOAGtgyKohERx6-9cEYtbwvs,157
 gllm_inference/em_invoker/schema/twelvelabs.pyi,sha256=D3F9_1F-UTzE6Ymxj6u0IFdL6OFVGlc7noZJr3iuA6I,389
 gllm_inference/em_invoker/schema/voyage.pyi,sha256=Aqvu6mhFkNb01aXAI5mChLKIgEnFnr-jNKq1lVWB54M,304
-gllm_inference/em_invoker/twelevelabs_em_invoker.pyi,sha256=YGWQNxv3AJ9BpN6HrQSnATiW_p0dRakkqy-JgxNIlf4,5165
-gllm_inference/em_invoker/voyage_em_invoker.pyi,sha256=R8IPBOEhIN84ukof-VkTPxPNbmbkwR_imTa5u6Qyjt0,5235
+gllm_inference/em_invoker/twelevelabs_em_invoker.pyi,sha256=l_3AUwhPlEE9gheq4sqI3o8OATt-kHwemQGdCSwaXfg,5549
+gllm_inference/em_invoker/voyage_em_invoker.pyi,sha256=vdB_qS8QKrCcb-HtXwKZS4WW1R1wGzpMBFmOKC39sjU,5619
 gllm_inference/exceptions/__init__.pyi,sha256=2F05RytXZIKaOJScb1pD0O0bATIQHVeEAYYNX4y5N2A,981
 gllm_inference/exceptions/error_parser.pyi,sha256=ggmh8DJXdwFJInNLrP24WVJt_4raxbAVxzXRQgBpndA,2441
 gllm_inference/exceptions/exceptions.pyi,sha256=ViXvIzm7tLcstjqfwC6nPziDg0UAmoUAWZVWrAJyp3w,4763
@@ -40,7 +40,7 @@ gllm_inference/lm_invoker/datasaur_lm_invoker.pyi,sha256=c4H3TOz0LIhWjokCCdQ4asi
 gllm_inference/lm_invoker/google_lm_invoker.pyi,sha256=I3plg_oVuTl0hiShFBmCYPclP4gWbzU61xUSgon24Ew,17102
 gllm_inference/lm_invoker/langchain_lm_invoker.pyi,sha256=bBGOxJfjnzOtDR4kH4PuCiOCKEPu8rTqzZodTXCHQ2k,13522
 gllm_inference/lm_invoker/litellm_lm_invoker.pyi,sha256=HHwW7i8ryXHI23JZQwscyva6aPmPOB13Muhf7gaaMUM,13376
-gllm_inference/lm_invoker/lm_invoker.pyi,sha256=YjMqbJymd_5U8MOulGXxJDSWSoEx4CebwlWnwt4Wyc4,7988
+gllm_inference/lm_invoker/lm_invoker.pyi,sha256=Sd-ywxgPcIzyI5eA7XoqdkYG9hntEnihJfj6Ack7qr0,7975
 gllm_inference/lm_invoker/openai_compatible_lm_invoker.pyi,sha256=JemahodhaUsC2gsI7YSxnW4X3uX1cU4YCFdIvdWWY88,15203
 gllm_inference/lm_invoker/openai_lm_invoker.pyi,sha256=SEHWAwpT8KmIQukurXtXOU2xyU2rp_HtM2SARsBF3dU,19892
 gllm_inference/lm_invoker/schema/__init__.pyi,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
@@ -78,10 +78,11 @@ gllm_inference/prompt_formatter/prompt_formatter.pyi,sha256=hAc6rxWc6JSYdD-OypLi
 gllm_inference/request_processor/__init__.pyi,sha256=giEme2WFQhgyKiBZHhSet0_nKSCHwGy-_2p6NRzg0Zc,231
 gllm_inference/request_processor/lm_request_processor.pyi,sha256=0fy1HyILCVDw6y46E-7tLnQTRYx4ppeRMe0QP6t9Jyw,5990
 gllm_inference/request_processor/uses_lm_mixin.pyi,sha256=znBG4AWWm_H70Qqrc1mO4ohmWotX9id81Fqe-x9Qa6Q,2371
-gllm_inference/schema/__init__.pyi,sha256=Mg9aKyvShNaB4XmqLWcZZ0arSNJhT2g1hhIqP1IBuaM,1376
+gllm_inference/schema/__init__.pyi,sha256=bYdXkfqkNAKEr48xaOKKQTbt2zLcCPiLCdSl2UTEIfE,1521
 gllm_inference/schema/attachment.pyi,sha256=9zgAjGXBjLfzPGaKi68FMW6b5mXdEA352nDe-ynOSvY,3385
 gllm_inference/schema/code_exec_result.pyi,sha256=WQ-ARoGM9r6nyRX-A0Ro1XKiqrc9R3jRYXZpu_xo5S4,573
-gllm_inference/schema/enums.pyi,sha256=SQ9mXt8j7uK333uUnUHRs-mkRxf0Z5NCtkAkgQZPIb4,629
+gllm_inference/schema/config.pyi,sha256=NVmjQK6HipIE0dKSfx12hgIC0O-S1HEcAc-TWlXAF5A,689
+gllm_inference/schema/enums.pyi,sha256=XmvxE7A-A8bX6hTikiAo_v66Z3hjMvhJGau1OUy9QDk,746
 gllm_inference/schema/lm_output.pyi,sha256=WP2LQrY0D03OJtFoaW_dGoJ_-yFUh2HbVlllgjzpYv4,1992
 gllm_inference/schema/message.pyi,sha256=jJV6A0ihEcun2OhzyMtNkiHnf7d6v5R-GdpTBGfJ0AQ,2272
 gllm_inference/schema/model_id.pyi,sha256=BIteIsEM19VIj_6wBkwKl_xd_iUpe21C7FIKh5BRC5I,5628
@@ -94,8 +95,8 @@ gllm_inference/utils/__init__.pyi,sha256=RBTWDu1TDPpTd17fixcPYFv2L_vp4-IAOX0Isxg
 gllm_inference/utils/langchain.pyi,sha256=4AwFiVAO0ZpdgmqeC4Pb5NJwBt8vVr0MSUqLeCdTscc,1194
 gllm_inference/utils/validation.pyi,sha256=-RdMmb8afH7F7q4Ao7x6FbwaDfxUHn3hA3WiOgzB-3s,397
 gllm_inference.build/.gitignore,sha256=aEiIwOuxfzdCmLZe4oB1JsBmCUxwG8x-u-HBCV9JT8E,1
-gllm_inference.cp311-win_amd64.pyd,sha256=4sBk7Ow25QwQLyXmfBPudyUJCoaTtIaRK1SlS_AESjQ,2920960
-gllm_inference.pyi,sha256=YGR7XxIbifZDVu3Ghk4SlqF8mb2UPWoR7pEXwJEloik,3570
-gllm_inference_binary-0.5.15.dist-info/METADATA,sha256=XkQGzgIhVc0VbsLTeDbn4Q1uVo8V1L_47CZC4kjNgyo,4608
-gllm_inference_binary-0.5.15.dist-info/WHEEL,sha256=-FZBVKyKauScY3vLa8vJR6hBCpAJfFykw2MOwlNKr1g,98
-gllm_inference_binary-0.5.15.dist-info/RECORD,,
+gllm_inference.cp311-win_amd64.pyd,sha256=GBFXH9usDVTlWMN3_ppWCnwcA5DwnqICDNSc8BOxnMc,2960384
+gllm_inference.pyi,sha256=6sd9bx3d5vTSkIextq6A1p7j7PyKO_RyuQb90eX-ZR4,3585
+gllm_inference_binary-0.5.17.dist-info/METADATA,sha256=XT6EE6ZK5-7X1bv4wjRjo93u_EvxAXd0cZKnin-Y54A,4608
+gllm_inference_binary-0.5.17.dist-info/WHEEL,sha256=-FZBVKyKauScY3vLa8vJR6hBCpAJfFykw2MOwlNKr1g,98
+gllm_inference_binary-0.5.17.dist-info/RECORD,,