gllm-inference-binary 0.5.41__cp313-cp313-win_amd64.whl → 0.5.43__cp313-cp313-win_amd64.whl

gllm_inference/builder/build_em_invoker.pyi

@@ -1,7 +1,7 @@
 from _typeshed import Incomplete
-from gllm_inference.em_invoker import AzureOpenAIEMInvoker as AzureOpenAIEMInvoker, BedrockEMInvoker as BedrockEMInvoker, GoogleEMInvoker as GoogleEMInvoker, LangChainEMInvoker as LangChainEMInvoker, OpenAICompatibleEMInvoker as OpenAICompatibleEMInvoker, OpenAIEMInvoker as OpenAIEMInvoker, TwelveLabsEMInvoker as TwelveLabsEMInvoker, VoyageEMInvoker as VoyageEMInvoker
+from gllm_inference.em_invoker import AzureOpenAIEMInvoker as AzureOpenAIEMInvoker, BedrockEMInvoker as BedrockEMInvoker, CohereEMInvoker as CohereEMInvoker, GoogleEMInvoker as GoogleEMInvoker, JinaEMInvoker as JinaEMInvoker, LangChainEMInvoker as LangChainEMInvoker, OpenAICompatibleEMInvoker as OpenAICompatibleEMInvoker, OpenAIEMInvoker as OpenAIEMInvoker, TwelveLabsEMInvoker as TwelveLabsEMInvoker, VoyageEMInvoker as VoyageEMInvoker
 from gllm_inference.em_invoker.em_invoker import BaseEMInvoker as BaseEMInvoker
-from gllm_inference.schema.model_id import ModelId as ModelId, ModelProvider as ModelProvider
+from gllm_inference.schema.model_id import ModelId as ModelId, ModelProvider as ModelProvider, OPTIONAL_PATH_PROVIDERS as OPTIONAL_PATH_PROVIDERS
 from typing import Any
 
 PROVIDER_TO_EM_INVOKER_MAP: dict[str, type[BaseEMInvoker]]
@@ -71,6 +71,16 @@ def build_em_invoker(model_id: str | ModelId, credentials: str | dict[str, Any]
         ```
         Providing credentials through environment variable is not supported for Google Vertex AI.
 
+        # Using Jina
+        ```python
+        em_invoker = build_em_invoker(
+            model_id="jina/jina-embeddings-v2-large",
+            credentials="jina-api-key"
+        )
+        ```
+        The credentials can also be provided through the `JINA_API_KEY` environment variable. For the list of supported
+        models, please refer to the following page: https://jina.ai/models
+
         # Using OpenAI
         ```python
         em_invoker = build_em_invoker(
@@ -128,6 +138,7 @@ def build_em_invoker(model_id: str | ModelId, credentials: str | dict[str, Any]
         variables credentials, please refer to the following page:
         https://python.langchain.com/docs/integrations/text_embedding/
 
+
     Security warning:
         Please provide the EM invoker credentials ONLY to the `credentials` parameter. Do not put any kind of
         credentials in the `config` parameter as the content of the `config` parameter will be logged.

gllm_inference/constants.pyi

@@ -2,10 +2,12 @@ from _typeshed import Incomplete
 
 AZURE_OPENAI_URL_SUFFIX: str
 DOCUMENT_MIME_TYPES: Incomplete
+EMBEDDING_ENDPOINT: str
 GOOGLE_SCOPES: Incomplete
 GRPC_ENABLE_RETRIES_KEY: str
-INVOKER_PROPAGATED_MAX_RETRIES: int
-INVOKER_DEFAULT_TIMEOUT: float
 HEX_REPR_LENGTH: int
+INVOKER_DEFAULT_TIMEOUT: float
+INVOKER_PROPAGATED_MAX_RETRIES: int
+JINA_DEFAULT_URL: str
 OPENAI_DEFAULT_URL: str
 SECONDS_TO_MILLISECONDS: int

gllm_inference/em_invoker/__init__.pyi

@@ -1,10 +1,12 @@
 from gllm_inference.em_invoker.azure_openai_em_invoker import AzureOpenAIEMInvoker as AzureOpenAIEMInvoker
 from gllm_inference.em_invoker.bedrock_em_invoker import BedrockEMInvoker as BedrockEMInvoker
+from gllm_inference.em_invoker.cohere_em_invoker import CohereEMInvoker as CohereEMInvoker
 from gllm_inference.em_invoker.google_em_invoker import GoogleEMInvoker as GoogleEMInvoker
+from gllm_inference.em_invoker.jina_em_invoker import JinaEMInvoker as JinaEMInvoker
 from gllm_inference.em_invoker.langchain_em_invoker import LangChainEMInvoker as LangChainEMInvoker
 from gllm_inference.em_invoker.openai_compatible_em_invoker import OpenAICompatibleEMInvoker as OpenAICompatibleEMInvoker
 from gllm_inference.em_invoker.openai_em_invoker import OpenAIEMInvoker as OpenAIEMInvoker
 from gllm_inference.em_invoker.twelevelabs_em_invoker import TwelveLabsEMInvoker as TwelveLabsEMInvoker
 from gllm_inference.em_invoker.voyage_em_invoker import VoyageEMInvoker as VoyageEMInvoker
 
-__all__ = ['AzureOpenAIEMInvoker', 'BedrockEMInvoker', 'GoogleEMInvoker', 'LangChainEMInvoker', 'OpenAIEMInvoker', 'OpenAICompatibleEMInvoker', 'TwelveLabsEMInvoker', 'VoyageEMInvoker']
+__all__ = ['AzureOpenAIEMInvoker', 'BedrockEMInvoker', 'CohereEMInvoker', 'GoogleEMInvoker', 'JinaEMInvoker', 'LangChainEMInvoker', 'OpenAIEMInvoker', 'OpenAICompatibleEMInvoker', 'TwelveLabsEMInvoker', 'VoyageEMInvoker']

gllm_inference/em_invoker/cohere_em_invoker.pyi

@@ -0,0 +1,128 @@
+from _typeshed import Incomplete
+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.cohere import CohereInputType as CohereInputType, Key as Key
+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 gllm_inference.utils import validate_string_enum as validate_string_enum
+from typing import Any
+
+SUPPORTED_ATTACHMENTS: Incomplete
+MULTIMODAL_MODEL_VERSION: Incomplete
+
+class CohereEMInvoker(BaseEMInvoker):
+    '''An embedding model invoker to interact with Cohere embedding models.
+
+    Attributes:
+        model_id (str): The model ID of the embedding model.
+        model_provider (str): The provider of the embedding model (Cohere).
+        model_name (str): The name of the Cohere embedding model.
+        client (AsyncClient): The asynchronous client for the Cohere 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_type (CohereInputType): The input type for the embedding model. Supported values include:
+            1. `CohereInputType.SEARCH_DOCUMENT`,
+            2. `CohereInputType.SEARCH_QUERY`,
+            3. `CohereInputType.CLASSIFICATION`,
+            4. `CohereInputType.CLUSTERING`,
+            5. `CohereInputType.IMAGE`.
+
+    Initialization:
+        You can initialize the `CohereEMInvoker` as follows:
+        ```python
+        em_invoker = CohereEMInvoker(
+            model_name="embed-english-v4.0",
+            input_type="search_document"
+        )
+        ```
+
+        Note: The `input_type` parameter can be one of the following:
+        1. "search_document"
+        2. "search_query"
+        3. "classification"
+        4. "clustering"
+        5. "image"
+
+        This parameter is optional and defaults to "search_document". For more information about
+        input_type, please refer to https://docs.cohere.com/docs/embeddings#the-input_type-parameter.
+
+    Input types:
+        The `CohereEMInvoker` supports the following input types: text and image.
+        Non-text inputs must be passed as an `Attachment` object.
+
+    Output format:
+        The `CohereEMInvoker` can embed either:
+        1. A single content.
+           1. A single content is either a text or an image.
+           2. The output will be a `Vector`, representing the embedding of the content.
+
+           # Example 1: Embedding a text content.
+           ```python
+           text = "What animal is in this image?"
+           result = await em_invoker.invoke(text)
+           ```
+
+           # Example 2: Embedding an image content.
+           ```python
+           image = Attachment.from_path("path/to/local/image.png")
+           result = await em_invoker.invoke(image)
+           ```
+
+           The above examples will return a `Vector` with a size of (embedding_size,).
+
+        2. A list of contents.
+           1. A list of contents is a list that consists of any of the above single contents.
+           2. The output will be a `list[Vector]`, where each element is a `Vector` representing the
+              embedding of each single content.
+
+           # Example: Embedding a list of contents.
+           ```python
+           text = "What animal is in this image?"
+           image = Attachment.from_path("path/to/local/image.png")
+           result = await em_invoker.invoke([text, image])
+           ```
+
+           The above examples will return a `list[Vector]` with a size of (2, embedding_size).
+
+    Retry and timeout:
+        The `CohereEMInvoker` supports retry and timeout configuration.
+        By default, the max retries is set to 0 and the timeout is set to 30.0 seconds.
+        They can be customized by providing a custom `RetryConfig` object to the `retry_config` parameter.
+
+        Retry config examples:
+        ```python
+        retry_config = RetryConfig(max_retries=0, timeout=None)  # No retry, no timeout
+        retry_config = RetryConfig(max_retries=0, timeout=10.0)  # No retry, 10.0 seconds timeout
+        retry_config = RetryConfig(max_retries=5, timeout=None)  # 5 max retries, no timeout
+        retry_config = RetryConfig(max_retries=5, timeout=10.0)  # 5 max retries, 10.0 seconds timeout
+        ```
+
+        Usage example:
+        ```python
+        em_invoker = CohereEMInvoker(..., retry_config=retry_config)
+        ```
+
+    '''
+    input_type: Incomplete
+    client: Incomplete
+    def __init__(self, model_name: str, api_key: str | None = None, base_url: 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, input_type: CohereInputType = ...) -> None:
+        '''Initializes a new instance of the CohereEMInvoker class.
+
+        Args:
+            model_name (str): The name of the Cohere embedding model to be used.
+            api_key (str | None, optional): The API key for authenticating with Cohere. Defaults to None, in which
+                case the `COHERE_API_KEY` environment variable will be used.
+            base_url (str | None, optional): The base URL for a custom Cohere-compatible endpoint.
+                Defaults to None, in which case Cohere\'s default URL will be used.
+            model_kwargs (dict[str, Any] | None, optional): Additional keyword arguments for the Cohere client.
+                Defaults to None.
+            default_hyperparameters (dict[str, Any] | None, optional): Default hyperparameters for invoking the model.
+                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.
+            input_type (CohereInputType, optional): The input type for the embedding model.
+                Defaults to `CohereInputType.SEARCH_DOCUMENT`. Valid values are: "search_document", "search_query",
+                "classification", "clustering", and "image".
+        '''

gllm_inference/em_invoker/jina_em_invoker.pyi

@@ -0,0 +1,103 @@
+from _typeshed import Incomplete
+from gllm_core.utils.retry import RetryConfig as RetryConfig
+from gllm_inference.constants import EMBEDDING_ENDPOINT as EMBEDDING_ENDPOINT, JINA_DEFAULT_URL as JINA_DEFAULT_URL
+from gllm_inference.em_invoker.em_invoker import BaseEMInvoker as BaseEMInvoker
+from gllm_inference.em_invoker.schema.jina import InputType as InputType, Key as Key
+from gllm_inference.exceptions import BaseInvokerError as BaseInvokerError, ProviderInternalError as ProviderInternalError
+from gllm_inference.exceptions.error_parser import convert_http_status_to_base_invoker_error as convert_http_status_to_base_invoker_error
+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
+MULTIMODAL_MODELS: Incomplete
+
+class JinaEMInvoker(BaseEMInvoker):
+    '''An embedding model invoker to interact with Jina AI embedding models.
+
+    Attributes:
+        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.
+        client (AsyncClient): The client for the Jina AI 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 `JinaEMInvoker` supports the following input types: text and image.
+        Non-text inputs must be passed as a `Attachment` object.
+
+    Output format:
+        The `JinaEMInvoker` can embed either:
+        1. A single content.
+           1. A single content is either a text or an image.
+           2. The output will be a `Vector`, representing the embedding of the content.
+
+           # Example 1: Embedding a text content.
+           ```python
+           text = "What animal is in this image?"
+           result = await em_invoker.invoke(text)
+           ```
+
+           # Example 2: Embedding an image content.
+           ```python
+           image = Attachment.from_path("path/to/local/image.png")
+           result = await em_invoker.invoke(image)
+           ```
+
+           The above examples will return a `Vector` with a size of (embedding_size,).
+
+        2. A list of contents.
+           1. A list of contents is a list that consists of any of the above single contents.
+           2. The output will be a `list[Vector]`, where each element is a `Vector` representing the
+              embedding of each single content.
+
+           # Example: Embedding a list of contents.
+           ```python
+           text = "What animal is in this image?"
+           image = Attachment.from_path("path/to/local/image.png")
+           result = await em_invoker.invoke([text, image])
+           ```
+
+           The above examples will return a `list[Vector]` with a size of (2, embedding_size).
+
+    Retry and timeout:
+        The `JinaEMInvoker` supports retry and timeout configuration.
+        By default, the max retries is set to 0 and the timeout is set to 30.0 seconds.
+        They can be customized by providing a custom `RetryConfig` object to the `retry_config` parameter.
+
+        Retry config examples:
+        ```python
+        retry_config = RetryConfig(max_retries=0, timeout=None)  # No retry, no timeout
+        retry_config = RetryConfig(max_retries=0, timeout=10.0)  # No retry, 10.0 seconds timeout
+        retry_config = RetryConfig(max_retries=5, timeout=None)  # 5 max retries, no timeout
+        retry_config = RetryConfig(max_retries=5, timeout=10.0)  # 5 max retries, 10.0 seconds timeout
+        ```
+
+        Usage example:
+        ```python
+        em_invoker = JinaEMInvoker(..., retry_config=retry_config)
+        ```
+    '''
+    client: Incomplete
+    model_kwargs: Incomplete
+    def __init__(self, model_name: str, api_key: str | None = None, base_url: 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 JinaEMInvoker class.
+
+        Args:
+            model_name (str): The name of the Jina embedding model to be used.
+            api_key (str | None, optional): The API key for authenticating with Jina AI.
+                Defaults to None, in which case the `JINA_API_KEY` environment variable will be used.
+            base_url (str, optional): The base URL for the Jina AI API. Defaults to "https://api.jina.ai/v1".
+            model_kwargs (dict[str, Any] | None, optional): Additional keyword arguments for the HTTP client.
+                Defaults to None.
+            default_hyperparameters (dict[str, Any] | None, optional): Default hyperparameters for invoking the model.
+                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 neither `api_key` nor `JINA_API_KEY` environment variable is provided.
+        '''

gllm_inference/em_invoker/schema/cohere.pyi

@@ -0,0 +1,20 @@
+from enum import StrEnum
+
+class Key(StrEnum):
+    """Defines valid keys in Cohere."""
+    BASE_URL = 'base_url'
+    IMAGE_URL = 'image_url'
+    INPUT_TYPE = 'input_type'
+    MAX_RETRIES = 'max_retries'
+    MODEL = 'model'
+    TIMEOUT = 'timeout'
+    TYPE = 'type'
+    URL = 'url'
+
+class CohereInputType(StrEnum):
+    """Defines valid embedding input types for Cohere embedding API."""
+    CLASSIFICATION = 'classification'
+    CLUSTERING = 'clustering'
+    IMAGE = 'image'
+    SEARCH_DOCUMENT = 'search_document'
+    SEARCH_QUERY = 'search_query'

gllm_inference/em_invoker/schema/jina.pyi

@@ -0,0 +1,28 @@
+from enum import StrEnum
+
+class InputType(StrEnum):
+    """Defines the supported input types for the Jina AI embedding API."""
+    IMAGE_URL = 'image_url'
+    TEXT = 'text'
+
+class Key(StrEnum):
+    """Defines key constants used in the Jina AI API payloads."""
+    DATA = 'data'
+    EMBEDDING = 'embedding'
+    ERROR = 'error'
+    IMAGE_URL = 'image_url'
+    INPUT = 'input'
+    JSON = 'json'
+    MESSAGE = 'message'
+    MODEL = 'model'
+    RESPONSE = 'response'
+    STATUS = 'status'
+    TASK = 'task'
+    TEXT = 'text'
+    TYPE = 'type'
+    URL = 'url'
+
+class OutputType(StrEnum):
+    """Defines the expected output types returned by the Jina AI embedding API."""
+    DATA = 'data'
+    EMBEDDING = 'embedding'

gllm_inference/exceptions/provider_error_map.pyi

@@ -13,6 +13,7 @@ class ExtendedHTTPStatus(IntEnum):
 HTTP_STATUS_TO_EXCEPTION_MAP: dict[int, type[BaseInvokerError]]
 ANTHROPIC_ERROR_MAPPING: Incomplete
 BEDROCK_ERROR_MAPPING: Incomplete
+COHERE_ERROR_MAPPING: Incomplete
 GOOGLE_ERROR_MAPPING: Incomplete
 LANGCHAIN_ERROR_CODE_MAPPING: Incomplete
 LITELLM_ERROR_MAPPING: Incomplete

gllm_inference/schema/model_id.pyi

@@ -12,8 +12,10 @@ class ModelProvider(StrEnum):
     ANTHROPIC = 'anthropic'
     AZURE_OPENAI = 'azure-openai'
     BEDROCK = 'bedrock'
+    COHERE = 'cohere'
     DATASAUR = 'datasaur'
     GOOGLE = 'google'
+    JINA = 'jina'
     LANGCHAIN = 'langchain'
     LITELLM = 'litellm'
     OPENAI = 'openai'
@@ -45,6 +47,11 @@ class ModelId(BaseModel):
         model_id = ModelId.from_string("bedrock/us.anthropic.claude-sonnet-4-20250514-v1:0")
         ```
 
+        # Using Cohere
+        ```python
+        model_id = ModelId.from_string("cohere/embed-english-v3.0")
+        ```
+
         # Using Datasaur
         ```python
         model_id = ModelId.from_string("datasaur/https://deployment.datasaur.ai/api/deployment/teamId/deploymentId/")
@@ -55,6 +62,13 @@ class ModelId(BaseModel):
         model_id = ModelId.from_string("google/gemini-2.5-flash-lite")
         ```
 
+        # Using Jina
+        ```python
+        model_id = ModelId.from_string("jina/jina-embeddings-v2-large")
+        ```
+        For the list of supported models, please refer to the following page:
+        https://jina.ai/models
+
         # Using OpenAI
         ```python
         model_id = ModelId.from_string("openai/gpt-5-nano")
@@ -94,6 +108,7 @@ class ModelId(BaseModel):
         ```python
         model_id = ModelId.from_string("langchain/langchain_openai.ChatOpenAI:gpt-4o-mini")
         ```
+
         For the list of supported providers, please refer to the following table:
         https://python.langchain.com/docs/integrations/chat/#featured-providers
 

gllm_inference.pyi

@@ -14,7 +14,9 @@ import gllm_core
 import gllm_core.utils
 import gllm_inference.em_invoker.AzureOpenAIEMInvoker
 import gllm_inference.em_invoker.BedrockEMInvoker
+import gllm_inference.em_invoker.CohereEMInvoker
 import gllm_inference.em_invoker.GoogleEMInvoker
+import gllm_inference.em_invoker.JinaEMInvoker
 import gllm_inference.em_invoker.LangChainEMInvoker
 import gllm_inference.em_invoker.OpenAICompatibleEMInvoker
 import gllm_inference.em_invoker.OpenAIEMInvoker
@@ -50,16 +52,21 @@ import gllm_inference.exceptions.BaseInvokerError
 import gllm_inference.exceptions.convert_http_status_to_base_invoker_error
 import gllm_inference.schema.Vector
 import aioboto3
-import asyncio.CancelledError
-import gllm_inference.exceptions.convert_to_base_invoker_error
+import base64
 import gllm_inference.schema.Attachment
 import gllm_inference.schema.AttachmentType
 import gllm_inference.schema.EMContent
+import gllm_inference.utils.validate_string_enum
+import cohere
+import asyncio.CancelledError
+import gllm_inference.exceptions.convert_to_base_invoker_error
 import gllm_inference.schema.TruncateSide
 import google
 import google.auth
 import google.genai
 import google.genai.types
+import httpx
+import gllm_inference.exceptions.ProviderInternalError
 import concurrent
 import concurrent.futures
 import concurrent.futures.ThreadPoolExecutor
@@ -71,9 +78,7 @@ import gllm_inference.utils.load_langchain_model
 import gllm_inference.utils.parse_model_data
 import openai
 import io
-import httpx
 import twelvelabs
-import base64
 import sys
 import voyageai
 import voyageai.client_async
@@ -111,7 +116,6 @@ import jsonschema
 import gllm_inference.lm_invoker.batch.BatchOperations
 import gllm_inference.schema.Activity
 import gllm_inference.schema.MessageContent
-import gllm_inference.utils.validate_string_enum
 import __future__
 import gllm_inference.schema.ActivityEvent
 import gllm_inference.schema.CodeEvent

{gllm_inference_binary-0.5.41.dist-info → gllm_inference_binary-0.5.43.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.2
 Name: gllm-inference-binary
-Version: 0.5.41
+Version: 0.5.43
 Summary: A library containing components related to model inferences in Gen AI applications.
 Author-email: Henry Wicaksono <henry.wicaksono@gdplabs.id>, Resti Febrina <resti.febrina@gdplabs.id>
 Requires-Python: <3.14,>=3.11
@@ -30,6 +30,8 @@ Provides-Extra: anthropic
 Requires-Dist: anthropic<0.61.0,>=0.60.0; extra == "anthropic"
 Provides-Extra: bedrock
 Requires-Dist: aioboto3<16.0.0,>=15.0.0; extra == "bedrock"
+Provides-Extra: cohere
+Requires-Dist: cohere<6.0.0,>=5.18.0; extra == "cohere"
 Provides-Extra: datasaur
 Requires-Dist: openai<2.0.0,>=1.98.0; extra == "datasaur"
 Provides-Extra: google

{gllm_inference_binary-0.5.41.dist-info → gllm_inference_binary-0.5.43.dist-info}/RECORD

@@ -1,9 +1,9 @@
-gllm_inference.cp313-win_amd64.pyd,sha256=uQdGAS_-xI9CJ-JpL9vYtwZhbumBcRgeq6PkUA6wSCI,3563520
-gllm_inference.pyi,sha256=NskQYpOC23IIFjCyeiQUcUyDHS65WGLN30RNyoDrhZI,4750
+gllm_inference.cp313-win_amd64.pyd,sha256=sTq5zg0Q1e7Ht2gLViCkrKP-qASuNCM9S27SUMbAy98,3670016
+gllm_inference.pyi,sha256=1LjTXA3c1aB5HyEpUvV9dsED8cBDfdOJNqQhzwbYq1o,4915
 gllm_inference/__init__.pyi,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
-gllm_inference/constants.pyi,sha256=1OBoHfeWfW9bXH9kStNEH__MGnGp--jLfyheAeQnogY,302
+gllm_inference/constants.pyi,sha256=PncjVw-mkzcJ3ln1ohvVZGdJ-TD-VZy1Ygn4Va8Z7i0,350
 gllm_inference/builder/__init__.pyi,sha256=-bw1uDx7CAM7pkvjvb1ZXku9zXlQ7aEAyC83KIn3bz8,506
-gllm_inference/builder/build_em_invoker.pyi,sha256=r4p0T9g_831Fq0youhxdMrQMWkzARw-PSahMu83ZzQo,5762
+gllm_inference/builder/build_em_invoker.pyi,sha256=3vO_pLokR4BAZflOMu6qzXoKx6vibT16uwJETH5Y_yc,6283
 gllm_inference/builder/build_lm_invoker.pyi,sha256=HvQICF-qvOTzfXZUqhi7rlwcpkMZpxaC-8QZmhnXKzI,7466
 gllm_inference/builder/build_lm_request_processor.pyi,sha256=H7Rg88e7PTTCtuyY64r333moTmh4-ypOwgnG10gkEdY,4232
 gllm_inference/builder/build_output_parser.pyi,sha256=sgSTrzUmSRxPzUUum0fDU7A3NXYoYhpi6bEx4Q2XMnA,965
@@ -11,11 +11,13 @@ gllm_inference/catalog/__init__.pyi,sha256=HWgPKWIzprpMHRKe_qN9BZSIQhVhrqiyjLjIX
 gllm_inference/catalog/catalog.pyi,sha256=eWPqgQKi-SJGHabi_XOTEKpAj96OSRypKsb5ZEC1VWU,4911
 gllm_inference/catalog/lm_request_processor_catalog.pyi,sha256=FiveqPDkV58XbDO2znXL-Ix5tFbZwNiVnitlEa90YOY,5536
 gllm_inference/catalog/prompt_builder_catalog.pyi,sha256=iViWB4SaezzjQY4UY1YxeoXUNxqxa2cTJGaD9JSx4Q8,3279
-gllm_inference/em_invoker/__init__.pyi,sha256=pmbsjmsqXwfe4WPykMnrmasKrYuylJWnf2s0pbo0ioM,997
+gllm_inference/em_invoker/__init__.pyi,sha256=uCWfCjh5a5DciRFcUdbHndewokM3J5hp3mbhmM5wQC8,1211
 gllm_inference/em_invoker/azure_openai_em_invoker.pyi,sha256=TXC5Kgf1eZqK2FHKAyeG3LB1SEsSEStnbk9bI1mjC5k,5049
 gllm_inference/em_invoker/bedrock_em_invoker.pyi,sha256=kQETh2r-WR_H3APtt4QavmfwGOR3KB4k6USNYvFateY,5831
+gllm_inference/em_invoker/cohere_em_invoker.pyi,sha256=4eLqeKLoK8vJB61bGdttfWUUvNDBToBqNA6KQYBMT8s,6793
 gllm_inference/em_invoker/em_invoker.pyi,sha256=YDYJ8TGScsz5Gg-OBnEENN1tI1RYvwoddypxUr6SAWw,5191
 gllm_inference/em_invoker/google_em_invoker.pyi,sha256=zZYjeLp9ncwIVM4UHqDJSVOFn1eXiaz9Ba24-_fCF2c,6953
+gllm_inference/em_invoker/jina_em_invoker.pyi,sha256=wrivFiPFRWBSw-TEAkaQKBvBRhlzN6CBaZkc0HOslRw,5754
 gllm_inference/em_invoker/langchain_em_invoker.pyi,sha256=nhX6LynrjhfySEt_44OlLoSBd15hoz3giWyNM9CYLKY,3544
 gllm_inference/em_invoker/openai_compatible_em_invoker.pyi,sha256=SbvCbOhdpkq6IyPhGd_IlxD8hbXDZID2rIehY6mJOIs,2923
 gllm_inference/em_invoker/openai_em_invoker.pyi,sha256=dwZr9rjrjm060HEnyaPR9-jFJpxSi7fWx7i9ZB4aEY4,6313
@@ -25,7 +27,9 @@ gllm_inference/em_invoker/langchain/__init__.pyi,sha256=aOTlRvS9aG1tBErjsmhe75s4
 gllm_inference/em_invoker/langchain/em_invoker_embeddings.pyi,sha256=BBSDazMOckO9Aw17tC3LGUTPqLb01my1xUZLtKZlwJY,3388
 gllm_inference/em_invoker/schema/__init__.pyi,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
 gllm_inference/em_invoker/schema/bedrock.pyi,sha256=HoNgVi0T21aFd1JrCnSLu4yryv8k8RnYdR3-tIdHFgA,498
+gllm_inference/em_invoker/schema/cohere.pyi,sha256=Wio6h0sbY93GygqETtflRaaucFzYSeLZRg7jyxMDK0s,567
 gllm_inference/em_invoker/schema/google.pyi,sha256=bzdtu4DFH2kATLybIeNl_Lznj99H-6u2Fvx3Zx52oZg,190
+gllm_inference/em_invoker/schema/jina.pyi,sha256=EFo4d8HuzPEZDV5F0PwUIkYPrCTEiCqHq17ICzYxKeg,739
 gllm_inference/em_invoker/schema/langchain.pyi,sha256=SZ13HDcvAOGmDTi2b72H6Y1J5GePR21JdnM6gYrwcGs,117
 gllm_inference/em_invoker/schema/openai.pyi,sha256=rNRqN62y5wHOKlr4T0n0m41ikAnSrD72CTnoHxo6kEM,146
 gllm_inference/em_invoker/schema/openai_compatible.pyi,sha256=A9MOeBhI-IPuvewOk4YYOAGtgyKohERx6-9cEYtbwvs,157
@@ -34,7 +38,7 @@ gllm_inference/em_invoker/schema/voyage.pyi,sha256=Aqvu6mhFkNb01aXAI5mChLKIgEnFn
 gllm_inference/exceptions/__init__.pyi,sha256=nXOqwsuwUgsnBcJEANVuxbZ1nDfcJ6-pKUfKeZwltkk,1218
 gllm_inference/exceptions/error_parser.pyi,sha256=4aiJZhBzBOqlhdmpvaCvildGy7_XxlJzQpe3PzGt8eE,2040
 gllm_inference/exceptions/exceptions.pyi,sha256=6y3ECgHAStqMGgQv8Dv-Ui-5PDD07mSj6qaRZeSWea4,5857
-gllm_inference/exceptions/provider_error_map.pyi,sha256=4AsAgbXAh91mxEW2YiomEuhBoeSNeAIo9WbT9WK8gQk,1233
+gllm_inference/exceptions/provider_error_map.pyi,sha256=vWa4ZIHn7qIghECGvO-dS2KzOmf3c10GRWKZ4YDPnSQ,1267
 gllm_inference/lm_invoker/__init__.pyi,sha256=jG1xc5fTOeIgeKKVYSnsMzQThKk9kTW38yO_MYtv540,1387
 gllm_inference/lm_invoker/anthropic_lm_invoker.pyi,sha256=JSgKUk9d1ZHlitv_ZjHlAk2hIW-J7u6yslVHflIeUro,16726
 gllm_inference/lm_invoker/azure_openai_lm_invoker.pyi,sha256=FYfRNPG-oD4wIfitjTHnGib1uMZL7Pid0gbrRsymAHU,14601
@@ -106,7 +110,7 @@ gllm_inference/schema/lm_input.pyi,sha256=HxQiZgY7zcXh_Dw8nK8LSeBTZEHMPZVwmPmnfg
 gllm_inference/schema/lm_output.pyi,sha256=DIV8BiIOPaSnMKxzKzH_Mp7j7-MScWCvmllegJDLqFg,2479
 gllm_inference/schema/mcp.pyi,sha256=4SgQ83pEowfWm2p-w9lupV4NayqqVBOy7SuYxIFeWRs,1045
 gllm_inference/schema/message.pyi,sha256=jJV6A0ihEcun2OhzyMtNkiHnf7d6v5R-GdpTBGfJ0AQ,2272
-gllm_inference/schema/model_id.pyi,sha256=NuaS4XlKDRJJezj45CEzn8reDDeII9XeRARmM5SZPqA,5408
+gllm_inference/schema/model_id.pyi,sha256=3PeAHrCyMAZJPCa7CfaArmOHdh2oDdUu6lkyx9mKG9g,5819
 gllm_inference/schema/reasoning.pyi,sha256=jbPxkDRHt0Vt-zdcc8lTT1l2hIE1Jm3HIHeNd0hfXGo,577
 gllm_inference/schema/token_usage.pyi,sha256=WJiGQyz5qatzBK2b-sABLCyTRLCBbAvxCRcqSJOzu-8,3025
 gllm_inference/schema/tool_call.pyi,sha256=OWT9LUqs_xfUcOkPG0aokAAqzLYYDkfnjTa0zOWvugk,403
@@ -117,7 +121,7 @@ gllm_inference/utils/io_utils.pyi,sha256=Eg7dvHWdXslTKdjh1j3dG50i7r35XG2zTmJ9XXv
 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_binary-0.5.41.dist-info/METADATA,sha256=8KVy2fPehAniiRxbGTA0N14cLIFFttOQj9gtrTbupEI,5770
-gllm_inference_binary-0.5.41.dist-info/WHEEL,sha256=O_u6PJIQ2pIcyIInxVQ9r-yArMuUZbBIaF1kpYVkYxA,96
-gllm_inference_binary-0.5.41.dist-info/top_level.txt,sha256=FpOjtN80F-qVNgbScXSEyqa0w09FYn6301iq6qt69IQ,15
-gllm_inference_binary-0.5.41.dist-info/RECORD,,
+gllm_inference_binary-0.5.43.dist-info/METADATA,sha256=j6Vv5yVz4dPzbuM8DunV5vgKTdrKrnobNAyv4oJxVaI,5851
+gllm_inference_binary-0.5.43.dist-info/WHEEL,sha256=O_u6PJIQ2pIcyIInxVQ9r-yArMuUZbBIaF1kpYVkYxA,96
+gllm_inference_binary-0.5.43.dist-info/top_level.txt,sha256=FpOjtN80F-qVNgbScXSEyqa0w09FYn6301iq6qt69IQ,15
+gllm_inference_binary-0.5.43.dist-info/RECORD,,