gllm-inference-binary 0.5.55__cp312-cp312-macosx_13_0_arm64.whl

gllm_inference/em_invoker/google_em_invoker.pyi

@@ -0,0 +1,129 @@
+from _typeshed import Incomplete
+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.exceptions import BaseInvokerError as BaseInvokerError, convert_http_status_to_base_invoker_error as convert_http_status_to_base_invoker_error
+from gllm_inference.exceptions.provider_error_map import GOOGLE_ERROR_MAPPING as GOOGLE_ERROR_MAPPING
+from gllm_inference.schema import ModelId as ModelId, ModelProvider as ModelProvider, TruncationConfig as TruncationConfig, Vector as Vector
+from typing import Any
+
+SUPPORTED_ATTACHMENTS: Incomplete
+
+class GoogleEMInvoker(BaseEMInvoker):
+    '''An embedding model invoker to interact with Google 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_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): 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.
+
+        Google Gen AI is recommended for quick prototyping and development.
+        It requires a Gemini API key for authentication.
+
+        Usage example:
+        ```python
+        em_invoker = GoogleEMInvoker(
+            model_name="text-embedding-004",
+            api_key="your_api_key"
+        )
+        ```
+
+        Google Vertex AI is recommended to build production-ready applications.
+        It requires a service account JSON file for authentication.
+
+        Usage example:
+        ```python
+        em_invoker = GoogleEMInvoker(
+            model_name="text-embedding-004",
+            credentials_path="path/to/service_account.json"
+        )
+        ```
+
+        If neither `api_key` nor `credentials_path` is provided, Google Gen AI will be used by default.
+        The `GOOGLE_API_KEY` environment variable will be used for authentication.
+
+    Input types:
+        The `GoogleEMInvoker` only supports text inputs.
+
+    Output format:
+        The `GoogleEMInvoker` can embed either:
+        1. A single content.
+           1. A single content is a single text.
+           2. The output will be a `Vector`, representing the embedding of the content.
+
+           # Example 1: Embedding a text content.
+           ```python
+           text = "This is a text"
+           result = await em_invoker.invoke(text)
+           ```
+
+           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 of texts.
+           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
+           text1 = "This is a text"
+           text2 = "This is another text"
+           text3 = "This is yet another text"
+           result = await em_invoker.invoke([text1, text2, text3])
+           ```
+
+           The above examples will return a `list[Vector]` with a size of (3, embedding_size).
+
+    Retry and timeout:
+        The `GoogleEMInvoker` 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 = GoogleEMInvoker(..., retry_config=retry_config)
+        ```
+    '''
+    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, truncation_config: TruncationConfig | None = None) -> None:
+        '''Initializes a new instance of the GoogleEMInvoker class.
+
+        Args:
+            model_name (str): The name of the model to use.
+            api_key (str | None, optional): Required for Google Gen AI authentication. Cannot be used together
+                with `credentials_path`. Defaults to None.
+            credentials_path (str | None, optional): Required for Google Vertex AI authentication. Path to the service
+                account credentials JSON file. Cannot be used together with `api_key`. Defaults to None.
+            project_id (str | None, optional): The Google Cloud project ID for Vertex AI. Only used when authenticating
+                with `credentials_path`. Defaults to None, in which case it will be loaded from the credentials file.
+            location (str, optional): The location of the Google Cloud project for Vertex AI. Only used when
+                authenticating with `credentials_path`. Defaults to "us-central1".
+            model_kwargs (dict[str, Any] | None, optional): Additional keyword arguments for the Google 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.
+
+        Note:
+            If neither `api_key` nor `credentials_path` is provided, Google Gen AI will be used by default.
+            The `GOOGLE_API_KEY` environment variable will be used for authentication.
+        '''

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/langchain/__init__.pyi

@@ -0,0 +1,3 @@
+from gllm_inference.em_invoker.langchain.em_invoker_embeddings import EMInvokerEmbeddings as EMInvokerEmbeddings
+
+__all__ = ['EMInvokerEmbeddings']

gllm_inference/em_invoker/langchain/em_invoker_embeddings.pyi

@@ -0,0 +1,84 @@
+from gllm_inference.em_invoker.em_invoker import BaseEMInvoker as BaseEMInvoker
+from gllm_inference.schema import Attachment as Attachment, Vector as Vector
+from gllm_inference.utils.io_utils import DEFAULT_BASE64_ALLOWED_MIMETYPES as DEFAULT_BASE64_ALLOWED_MIMETYPES, base64_to_bytes as base64_to_bytes
+from langchain_core.embeddings import Embeddings
+from pydantic import BaseModel
+from typing import Any
+
+class EMInvokerEmbeddings(BaseModel, Embeddings, arbitrary_types_allowed=True):
+    '''An adapter class that enables an `EMInvoker` to be used as a LangChain `Embeddings`.
+
+    Attributes:
+        em_invoker (BaseEMInvoker): The `EMInvoker` instance to be interacted with.
+        use_base64 (bool):
+            Whether to apply strict base64 encoding to the input.
+            1, If `True`, only inputs with specific MIME types (e.g. images,
+              audio, and video) will be converted into base64 strings before being sent.
+            2. If `False`, each input is treated as a raw string.
+
+            This ensures "strict" handling: base64 encoding is not applied
+            universally, but only when required for those MIME types.
+
+    Usage example:
+    ```python
+    from gllm_inference.em_invoker.langchain import EMInvokerEmbeddings
+    from gllm_inference.em_invoker import OpenAIEMInvoker
+
+    em_invoker = OpenAIEMInvoker(...)
+    embeddings = EMInvokerEmbeddings(em_invoker=em_invoker)
+    ```
+    '''
+    em_invoker: BaseEMInvoker
+    use_base64: bool
+    async def aembed_documents(self, texts: list[str], **kwargs: Any) -> list[Vector]:
+        """Asynchronously embed documents using the `EMInvoker`.
+
+        Args:
+            texts (list[str]): The list of texts to embed.
+            **kwargs (Any): Additional keyword arguments to pass to the EMInvoker's `invoke` method.
+
+        Returns:
+            list[Vector]: List of embeddings, one for each text.
+
+        Raises:
+            ValueError: If `texts` is not a list of strings.
+        """
+    async def aembed_query(self, text: str, **kwargs: Any) -> Vector:
+        """Asynchronously embed query using the `EMInvoker`.
+
+        Args:
+            text (str): The text to embed.
+            **kwargs (Any): Additional keyword arguments to pass to the EMInvoker's `invoke` method.
+
+        Returns:
+            Vector: Embeddings for the text.
+
+        Raises:
+            ValueError: If `text` is not a string.
+        """
+    def embed_documents(self, texts: list[str], **kwargs: Any) -> list[Vector]:
+        """Embed documents using the `EMInvoker`.
+
+        Args:
+            texts (list[str]): The list of texts to embed.
+            **kwargs (Any): Additional keyword arguments to pass to the EMInvoker's `invoke` method.
+
+        Returns:
+            list[Vector]: List of embeddings, one for each text.
+
+        Raises:
+            ValueError: If `texts` is not a list of strings.
+        """
+    def embed_query(self, text: str, **kwargs: Any) -> Vector:
+        """Embed query using the `EMInvoker`.
+
+        Args:
+            text (str): The text to embed.
+            **kwargs (Any): Additional keyword arguments to pass to the EMInvoker's `invoke` method.
+
+        Returns:
+            Vector: Embeddings for the text.
+
+        Raises:
+            ValueError: If `text` is not a string.
+        """

gllm_inference/em_invoker/langchain_em_invoker.pyi

@@ -0,0 +1,46 @@
+from _typeshed import Incomplete
+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.exceptions import BaseInvokerError as BaseInvokerError, InvokerRuntimeError as InvokerRuntimeError, build_debug_info as build_debug_info
+from gllm_inference.exceptions.provider_error_map import ALL_PROVIDER_ERROR_MAPPINGS as ALL_PROVIDER_ERROR_MAPPINGS, LANGCHAIN_ERROR_CODE_MAPPING as LANGCHAIN_ERROR_CODE_MAPPING
+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
+
+SUPPORTED_ATTACHMENTS: Incomplete
+
+class LangChainEMInvoker(BaseEMInvoker):
+    """A language model invoker to interact with LangChain's Embeddings.
+
+    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.
+        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, truncation_config: TruncationConfig | None = None) -> None:
+        '''Initializes a new instance of the LangChainEMInvoker class.
+
+        Args:
+            model (Embeddings | None, optional): The LangChain\'s Embeddings instance. If provided, will take
+                precedence over the `model_class_path` parameter. Defaults to None.
+            model_class_path (str | None, optional): The LangChain\'s Embeddings class path. Must be formatted as
+                "<package>.<class>" (e.g. "langchain_openai.OpenAIEmbeddings"). Ignored if `model` is provided.
+                Defaults to None.
+            model_name (str | None, optional): The model name. Only used if `model_class_path` is provided.
+                Defaults to None.
+            model_kwargs (dict[str, Any] | None, optional): The additional keyword arguments. Only used if
+                `model_class_path` is provided. 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.
+        '''

gllm_inference/em_invoker/openai_compatible_em_invoker.pyi

@@ -0,0 +1,41 @@
+from _typeshed import Incomplete
+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, TruncationConfig as TruncationConfig
+from typing import Any
+
+DEPRECATION_MESSAGE: str
+
+class OpenAICompatibleEMInvoker(OpenAIEMInvoker):
+    """An embedding model invoker to interact with endpoints compatible with OpenAI's embedding API contract.
+
+    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_kwargs (dict[str, Any]): The keyword arguments for the OpenAI client.
+        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.
+
+    This class is deprecated and will be removed in v0.6. Please use the `OpenAIEMInvoker` class instead.
+    """
+    client_kwargs: 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, truncation_config: TruncationConfig | None = None) -> None:
+        """Initializes a new instance of the OpenAICompatibleEMInvoker class.
+
+        Args:
+            model_name (str): The name of the embedding model hosted on the OpenAI compatible endpoint.
+            base_url (str): The base URL for the OpenAI compatible endpoint.
+            api_key (str | None, optional): The API key for authenticating with the OpenAI compatible endpoint.
+                Defaults to None, in which case the `OPENAI_API_KEY` environment variable will be used.
+            model_kwargs (dict[str, Any] | None, optional): Additional model parameters. 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.
+        """

gllm_inference/em_invoker/openai_em_invoker.pyi

@@ -0,0 +1,118 @@
+from _typeshed import Incomplete
+from gllm_core.utils.retry import RetryConfig as RetryConfig
+from gllm_inference.constants import INVOKER_PROPAGATED_MAX_RETRIES as INVOKER_PROPAGATED_MAX_RETRIES, OPENAI_DEFAULT_URL as OPENAI_DEFAULT_URL
+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
+
+class OpenAIEMInvoker(BaseEMInvoker):
+    '''An embedding model invoker to interact with OpenAI 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_kwargs (dict[str, Any]): The keyword arguments for the OpenAI client.
+        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.
+
+    Basic usage:
+        The `OpenAIEMInvoker` can be used as follows:
+        ```python
+        em_invoker = OpenAIEMInvoker(model_name="text-embedding-3-small")
+        result = await em_invoker.invoke("Hi there!")
+        ```
+
+    OpenAI compatible endpoints:
+        The `OpenAIEMInvoker` can also be used to interact with endpoints that are compatible with
+        OpenAI\'s Embeddings API schema. This includes but are not limited to:
+        1. Text Embeddings Inference (https://github.com/huggingface/text-embeddings-inference)
+        2. vLLM (https://vllm.ai/)
+        Please note that the supported features and capabilities may vary between different endpoints and
+        language models. Using features that are not supported by the endpoint will result in an error.
+
+        This customization can be done by setting the `base_url` parameter to the base URL of the endpoint:
+        ```python
+        em_invoker = OpenAIEMInvoker(
+            model_name="<model-name>",
+            api_key="<your-api-key>",
+            base_url="<https://base-url>",
+        )
+        result = await em_invoker.invoke("Hi there!")
+        ```
+
+    Input types:
+        The `OpenAIEMInvoker` only supports text inputs.
+
+    Output format:
+        The `OpenAIEMInvoker` can embed either:
+        1. A single content.
+           1. A single content is a single text.
+           2. The output will be a `Vector`, representing the embedding of the content.
+
+           # Example 1: Embedding a text content.
+           ```python
+           text = "This is a text"
+           result = await em_invoker.invoke(text)
+           ```
+
+           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 of texts.
+           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
+           text1 = "This is a text"
+           text2 = "This is another text"
+           text3 = "This is yet another text"
+           result = await em_invoker.invoke([text1, text2, text3])
+           ```
+
+           The above examples will return a `list[Vector]` with a size of (3, embedding_size).
+
+    Retry and timeout:
+        The `OpenAIEMInvoker` 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 = OpenAIEMInvoker(..., retry_config=retry_config)
+        ```
+    '''
+    client_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 OpenAIEMInvoker class.
+
+        Args:
+            model_name (str): The name of the OpenAI embedding model to be used.
+            api_key (str | None, optional): The API key for authenticating with OpenAI. Defaults to None, in which
+                case the `OPENAI_API_KEY` environment variable will be used. If the endpoint does not require an
+                API key, a dummy value can be passed (e.g. "<empty>").
+            base_url (str, optional): The base URL of a custom endpoint that is compatible with OpenAI\'s
+                Embeddings API schema. Defaults to OpenAI\'s default URL.
+            model_kwargs (dict[str, Any] | None, optional): Additional keyword arguments for the OpenAI 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.
+        '''

gllm_inference/em_invoker/schema/bedrock.pyi

@@ -0,0 +1,29 @@
+class Key:
+    """Defines valid keys in Bedrock."""
+    ACCEPT: str
+    BASE64_STRING: str
+    CONTENT_TYPE: str
+    HTTP_STATUS_CODE: str
+    INPUT_TEXT: str
+    INPUT_TYPE: str
+    INPUT_TYPE_MARENGO: str
+    MEDIA_SOURCE: str
+    MODEL_ID: str
+    RESPONSE_METADATA: str
+    TEXT_TRUNCATE: str
+    TEXTS: str
+
+class InputType:
+    """Defines valid input types in Bedrock."""
+    APPLICATION_JSON: str
+    IMAGE: str
+    SEARCH_DOCUMENT: str
+    SEARCH_QUERY: str
+    TEXT: str
+
+class OutputType:
+    """Defines valid output types in Bedrock."""
+    BODY: str
+    DATA: str
+    EMBEDDING: str
+    EMBEDDINGS: str

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/google.pyi

@@ -0,0 +1,9 @@
+class Key:
+    """Defines valid keys in Google."""
+    API_KEY: str
+    CREDENTIALS: str
+    HTTP_OPTIONS: str
+    LOCATION: str
+    PROJECT: str
+    TIMEOUT: str
+    VERTEXAI: str

gllm_inference/em_invoker/schema/jina.pyi

@@ -0,0 +1,29 @@
+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'
+    EMBEDDINGS = 'embeddings'
+    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/em_invoker/schema/langchain.pyi

@@ -0,0 +1,5 @@
+class Key:
+    """Defines valid keys in LangChain."""
+    ERROR_CODE: str
+    MAX_RETRIES: str
+    TIMEOUT: str

gllm_inference/em_invoker/schema/openai.pyi

@@ -0,0 +1,7 @@
+class Key:
+    """Defines valid keys in OpenAI."""
+    API_KEY: str
+    BASE_URL: str
+    MAX_RETRIES: str
+    MODEL: str
+    TIMEOUT: str

gllm_inference/em_invoker/schema/openai_compatible.pyi

@@ -0,0 +1,7 @@
+class Key:
+    """Defines valid keys in OpenAI Compatible."""
+    API_KEY: str
+    BASE_URL: str
+    MAX_RETRIES: str
+    MODEL: str
+    TIMEOUT: str