ag2 0.10.2__py3-none-any.whl

autogen/interop/interoperability.py

@@ -0,0 +1,71 @@
+# Copyright (c) 2023 - 2025, AG2ai, Inc., AG2ai open-source projects maintainers and core contributors
+#
+# SPDX-License-Identifier: Apache-2.0
+from typing import Any
+
+from ..doc_utils import export_module
+from ..tools import Tool
+from .interoperable import Interoperable
+from .registry import InteroperableRegistry
+
+__all__ = ["Interoperable"]
+
+
+@export_module("autogen.interop")
+class Interoperability:
+    """A class to handle interoperability between different tool types.
+
+    This class allows the conversion of tools to various interoperability classes and provides functionality
+    for retrieving and registering interoperability classes.
+    """
+
+    registry = InteroperableRegistry.get_instance()
+
+    @classmethod
+    def convert_tool(cls, *, tool: Any, type: str, **kwargs: Any) -> Tool:
+        """Converts a given tool to an instance of a specified interoperability type.
+
+        Args:
+            tool (Any): The tool object to be converted.
+            type (str): The type of interoperability to convert the tool to.
+            **kwargs (Any): Additional arguments to be passed during conversion.
+
+        Returns:
+            Tool: The converted tool.
+
+        Raises:
+            ValueError: If the interoperability class for the provided type is not found.
+        """
+        interop = cls.get_interoperability_class(type)
+        return interop.convert_tool(tool, **kwargs)
+
+    @classmethod
+    def get_interoperability_class(cls, type: str) -> type[Interoperable]:
+        """Retrieves the interoperability class corresponding to the specified type.
+
+        Args:
+            type (str): The type of the interoperability class to retrieve.
+
+        Returns:
+            type[Interoperable]: The interoperability class type.
+
+        Raises:
+            ValueError: If no interoperability class is found for the provided type.
+        """
+        supported_types = cls.registry.get_supported_types()
+        if type not in supported_types:
+            supported_types_formatted = ", ".join(["'t'" for t in supported_types])
+            raise ValueError(
+                f"Interoperability class {type} is not supported, supported types: {supported_types_formatted}"
+            )
+
+        return cls.registry.get_class(type)
+
+    @classmethod
+    def get_supported_types(cls) -> list[str]:
+        """Returns a sorted list of all supported interoperability types.
+
+        Returns:
+            List[str]: A sorted list of strings representing the supported interoperability types.
+        """
+        return sorted(cls.registry.get_supported_types())

autogen/interop/interoperable.py

@@ -0,0 +1,46 @@
+# Copyright (c) 2023 - 2025, AG2ai, Inc., AG2ai open-source projects maintainers and core contributors
+#
+# SPDX-License-Identifier: Apache-2.0
+
+from typing import Any, Protocol, runtime_checkable
+
+from ..doc_utils import export_module
+from ..tools import Tool
+
+__all__ = ["Interoperable"]
+
+
+@runtime_checkable
+@export_module("autogen.interop")
+class Interoperable(Protocol):
+    """A Protocol defining the interoperability interface for tool conversion.
+
+    This protocol ensures that any class implementing it provides the method
+    `convert_tool` to convert a given tool into a desired format or type.
+    """
+
+    @classmethod
+    def convert_tool(cls, tool: Any, **kwargs: Any) -> Tool:
+        """Converts a given tool to a desired format or type.
+
+        This method should be implemented by any class adhering to the `Interoperable` protocol.
+
+        Args:
+            tool (Any): The tool object to be converted.
+            **kwargs (Any): Additional parameters to pass during the conversion process.
+
+        Returns:
+            Tool: The converted tool in the desired format or type.
+        """
+        ...
+
+    @classmethod
+    def get_unsupported_reason(cls) -> str | None:
+        """Returns the reason for the tool being unsupported.
+
+        This method should be implemented by any class adhering to the `Interoperable` protocol.
+
+        Returns:
+            str: The reason for the interoperability class being unsupported.
+        """
+        ...

autogen/interop/langchain/__init__.py

@@ -0,0 +1,8 @@
+# Copyright (c) 2023 - 2025, AG2ai, Inc., AG2ai open-source projects maintainers and core contributors
+#
+# SPDX-License-Identifier: Apache-2.0
+
+from .langchain_chat_model_factory import LangChainChatModelFactory
+from .langchain_tool import LangChainInteroperability
+
+__all__ = ["LangChainChatModelFactory", "LangChainInteroperability"]

autogen/interop/langchain/langchain_chat_model_factory.py

@@ -0,0 +1,156 @@
+# Copyright (c) 2023 - 2025, AG2ai, Inc., AG2ai open-source projects maintainers and core contributors
+#
+# SPDX-License-Identifier: Apache-2.0
+
+from abc import ABC, abstractmethod
+from collections.abc import Callable
+from typing import Any, TypeVar
+
+from ...doc_utils import export_module
+from ...import_utils import optional_import_block, require_optional_import
+from ...llm_config import LLMConfig
+from ...oai import get_first_llm_config
+
+with optional_import_block():
+    from langchain_anthropic import ChatAnthropic
+    from langchain_core.language_models import BaseChatModel
+    from langchain_google_genai import ChatGoogleGenerativeAI
+    from langchain_ollama import ChatOllama
+    from langchain_openai import AzureChatOpenAI, ChatOpenAI
+
+
+__all__ = ["LangChainChatModelFactory"]
+
+T = TypeVar("T", bound="LangChainChatModelFactory")
+
+
+@require_optional_import(
+    ["langchain_anthropic", "langchain_google_genai", "langchain_ollama", "langchain_openai", "langchain_core"],
+    "browser-use",
+    except_for=["__init__", "register_factory"],
+)
+@export_module("autogen.interop")
+class LangChainChatModelFactory(ABC):
+    _factories: set["LangChainChatModelFactory"] = set()
+
+    @classmethod
+    def create_base_chat_model(cls, llm_config: LLMConfig | dict[str, Any]) -> "BaseChatModel":  # type: ignore [no-any-unimported]
+        first_llm_config = get_first_llm_config(llm_config)
+        for factory in LangChainChatModelFactory._factories:
+            if factory.accepts(first_llm_config):
+                return factory.create(first_llm_config)
+
+        raise ValueError("Could not find a factory for the given config.")
+
+    @classmethod
+    def register_factory(cls) -> Callable[[type[T]], type[T]]:
+        def decorator(factory: type[T]) -> type[T]:
+            cls._factories.add(factory())
+            return factory
+
+        return decorator
+
+    @classmethod
+    def prepare_config(cls, first_llm_config: dict[str, Any]) -> dict[str, Any]:
+        for pop_keys in ["api_type", "response_format"]:
+            first_llm_config.pop(pop_keys, None)
+        return first_llm_config
+
+    @classmethod
+    @abstractmethod
+    def create(cls, first_llm_config: dict[str, Any]) -> "BaseChatModel":  # type: ignore [no-any-unimported]
+        ...
+
+    @classmethod
+    @abstractmethod
+    def get_api_type(cls) -> str: ...
+
+    @classmethod
+    def accepts(cls, first_llm_config: dict[str, Any]) -> bool:
+        return first_llm_config.get("api_type", "openai") == cls.get_api_type()  # type: ignore [no-any-return]
+
+
+@LangChainChatModelFactory.register_factory()
+class ChatOpenAIFactory(LangChainChatModelFactory):
+    @classmethod
+    def create(cls, first_llm_config: dict[str, Any]) -> "ChatOpenAI":  # type: ignore [no-any-unimported]
+        first_llm_config = cls.prepare_config(first_llm_config)
+
+        return ChatOpenAI(**first_llm_config)
+
+    @classmethod
+    def get_api_type(cls) -> str:
+        return "openai"
+
+
+@LangChainChatModelFactory.register_factory()
+class DeepSeekFactory(ChatOpenAIFactory):
+    @classmethod
+    def create(cls, first_llm_config: dict[str, Any]) -> "ChatOpenAI":  # type: ignore [no-any-unimported]
+        if "base_url" not in first_llm_config:
+            raise ValueError("base_url is required for deepseek api type.")
+        return super().create(first_llm_config)
+
+    @classmethod
+    def get_api_type(cls) -> str:
+        return "deepseek"
+
+
+@LangChainChatModelFactory.register_factory()
+class ChatAnthropicFactory(LangChainChatModelFactory):
+    @classmethod
+    def create(cls, first_llm_config: dict[str, Any]) -> "ChatAnthropic":  # type: ignore [no-any-unimported]
+        first_llm_config = cls.prepare_config(first_llm_config)
+
+        return ChatAnthropic(**first_llm_config)
+
+    @classmethod
+    def get_api_type(cls) -> str:
+        return "anthropic"
+
+
+@LangChainChatModelFactory.register_factory()
+class ChatGoogleGenerativeAIFactory(LangChainChatModelFactory):
+    @classmethod
+    def create(cls, first_llm_config: dict[str, Any]) -> "ChatGoogleGenerativeAI":  # type: ignore [no-any-unimported]
+        first_llm_config = cls.prepare_config(first_llm_config)
+
+        return ChatGoogleGenerativeAI(**first_llm_config)
+
+    @classmethod
+    def get_api_type(cls) -> str:
+        return "google"
+
+
+@LangChainChatModelFactory.register_factory()
+class AzureChatOpenAIFactory(LangChainChatModelFactory):
+    @classmethod
+    def create(cls, first_llm_config: dict[str, Any]) -> "AzureChatOpenAI":  # type: ignore [no-any-unimported]
+        first_llm_config = cls.prepare_config(first_llm_config)
+        for param in ["base_url", "api_version"]:
+            if param not in first_llm_config:
+                raise ValueError(f"{param} is required for azure api type.")
+        first_llm_config["azure_endpoint"] = first_llm_config.pop("base_url")
+
+        return AzureChatOpenAI(**first_llm_config)
+
+    @classmethod
+    def get_api_type(cls) -> str:
+        return "azure"
+
+
+@LangChainChatModelFactory.register_factory()
+class ChatOllamaFactory(LangChainChatModelFactory):
+    @classmethod
+    def create(cls, first_llm_config: dict[str, Any]) -> "ChatOllama":  # type: ignore [no-any-unimported]
+        first_llm_config = cls.prepare_config(first_llm_config)
+        first_llm_config["base_url"] = first_llm_config.pop("client_host", None)
+        if "num_ctx" not in first_llm_config:
+            # In all Browser Use examples, num_ctx is set to 32000
+            first_llm_config["num_ctx"] = 32000
+
+        return ChatOllama(**first_llm_config)
+
+    @classmethod
+    def get_api_type(cls) -> str:
+        return "ollama"

autogen/interop/langchain/langchain_tool.py

@@ -0,0 +1,78 @@
+# Copyright (c) 2023 - 2025, AG2ai, Inc., AG2ai open-source projects maintainers and core contributors
+#
+# SPDX-License-Identifier: Apache-2.0
+
+from typing import Any
+
+from ...doc_utils import export_module
+from ...import_utils import optional_import_block, require_optional_import
+from ...tools import Tool
+from ..registry import register_interoperable_class
+
+__all__ = ["LangChainInteroperability"]
+
+with optional_import_block():
+    from langchain_core.tools import BaseTool as LangchainTool
+
+
+@register_interoperable_class("langchain")
+@export_module("autogen.interop")
+class LangChainInteroperability:
+    """A class implementing the `Interoperable` protocol for converting Langchain tools
+    into a general `Tool` format.
+
+    This class takes a `LangchainTool` and converts it into a standard `Tool` object,
+    ensuring compatibility between Langchain tools and other systems that expect
+    the `Tool` format.
+    """
+
+    @classmethod
+    @require_optional_import("langchain_core", "interop-langchain")
+    def convert_tool(cls, tool: Any, **kwargs: Any) -> Tool:
+        """Converts a given Langchain tool into a general `Tool` format.
+
+        This method verifies that the provided tool is a valid `LangchainTool`,
+        processes the tool's input and description, and returns a standardized
+        `Tool` object.
+
+        Args:
+            tool (Any): The tool to convert, expected to be an instance of `LangchainTool`.
+            **kwargs (Any): Additional arguments, which are not supported by this method.
+
+        Returns:
+            Tool: A standardized `Tool` object converted from the Langchain tool.
+
+        Raises:
+            ValueError: If the provided tool is not an instance of `LangchainTool`, or if
+                        any additional arguments are passed.
+        """
+        if not isinstance(tool, LangchainTool):
+            raise ValueError(f"Expected an instance of `langchain_core.tools.BaseTool`, got {type(tool)}")
+        if kwargs:
+            raise ValueError(f"The LangchainInteroperability does not support any additional arguments, got {kwargs}")
+
+        # needed for type checking
+        langchain_tool: LangchainTool = tool  # type: ignore[no-any-unimported]
+
+        model_type = langchain_tool.get_input_schema()
+
+        def func(tool_input: model_type) -> Any:  # type: ignore[valid-type]
+            return langchain_tool.run(tool_input.model_dump())  # type: ignore[attr-defined]
+
+        return Tool(
+            name=langchain_tool.name,
+            description=langchain_tool.description,
+            func_or_tool=func,
+        )
+
+    @classmethod
+    def get_unsupported_reason(cls) -> str | None:
+        with optional_import_block() as result:
+            import langchain_core.tools  # noqa: F401
+
+        if not result.is_successful:
+            return (
+                "Please install `interop-langchain` extra to use this module:\n\n\tpip install ag2[interop-langchain]"
+            )
+
+        return None

autogen/interop/litellm/__init__.py

@@ -0,0 +1,7 @@
+# Copyright (c) 2023 - 2025, AG2ai, Inc., AG2ai open-source projects maintainers and core contributors
+#
+# SPDX-License-Identifier: Apache-2.0
+
+from .litellm_config_factory import LiteLLmConfigFactory
+
+__all__ = ["LiteLLmConfigFactory"]

autogen/interop/litellm/litellm_config_factory.py

@@ -0,0 +1,178 @@
+# Copyright (c) 2023 - 2025, AG2ai, Inc., AG2ai open-source projects maintainers and core contributors
+#
+# SPDX-License-Identifier: Apache-2.0
+
+import os
+from abc import ABC, abstractmethod
+from collections.abc import Callable
+from typing import Any, TypeVar
+
+from ...doc_utils import export_module
+from ...llm_config import LLMConfig
+from ...oai import get_first_llm_config
+
+__all__ = ["LiteLLmConfigFactory"]
+
+T = TypeVar("T", bound="LiteLLmConfigFactory")
+
+
+def get_crawl4ai_version() -> str | None:
+    """Get the installed crawl4ai version."""
+    try:
+        import crawl4ai
+
+        version = getattr(crawl4ai, "__version__", None)
+        return version if isinstance(version, str) else None
+    except (ImportError, AttributeError):
+        return None
+
+
+def is_crawl4ai_v05_or_higher() -> bool:
+    """Check if crawl4ai version is 0.5 or higher."""
+    version = get_crawl4ai_version()
+    if version is None:
+        return False
+
+    # Parse version string (e.g., "0.5.0" -> [0, 5, 0])
+    try:
+        version_parts = [int(x) for x in version.split(".")]
+        # Check if version >= 0.5.0
+        return version_parts >= [0, 5, 0]
+    except (ValueError, IndexError):
+        return False
+
+
+@export_module("autogen.interop")
+class LiteLLmConfigFactory(ABC):
+    _factories: set["LiteLLmConfigFactory"] = set()
+
+    @classmethod
+    def create_lite_llm_config(cls, llm_config: LLMConfig | dict[str, Any]) -> dict[str, Any]:
+        """Create a lite LLM config compatible with the installed crawl4ai version.
+
+        For crawl4ai >=0.5: Returns config with llmConfig parameter
+        For crawl4ai <0.5: Returns config with provider parameter (legacy)
+        """
+        first_llm_config = get_first_llm_config(llm_config)
+        for factory in LiteLLmConfigFactory._factories:
+            if factory.accepts(first_llm_config):
+                base_config = factory.create(first_llm_config)
+
+                # Check crawl4ai version and adapt config accordingly
+                if is_crawl4ai_v05_or_higher():
+                    return cls._adapt_for_crawl4ai_v05(base_config)
+                else:
+                    return base_config  # Use legacy format
+
+        raise ValueError("Could not find a factory for the given config.")
+
+    @classmethod
+    def _adapt_for_crawl4ai_v05(cls, base_config: dict[str, Any]) -> dict[str, Any]:
+        """Adapt the config for crawl4ai >=0.5 by moving deprecated parameters
+        into an llmConfig object.
+        """
+        adapted_config = base_config.copy()
+
+        # Extract deprecated parameters
+        llm_config_params = {}
+
+        if "provider" in adapted_config:
+            llm_config_params["provider"] = adapted_config.pop("provider")
+
+        if "api_token" in adapted_config:
+            llm_config_params["api_token"] = adapted_config.pop("api_token")
+
+        # Add other parameters that should be in llmConfig
+        for param in ["base_url", "api_base", "api_version"]:
+            if param in adapted_config:
+                llm_config_params[param] = adapted_config.pop(param)
+
+        # Create the llmConfig object if we have parameters for it
+        if llm_config_params:
+            adapted_config["llmConfig"] = llm_config_params
+
+        return adapted_config
+
+    @classmethod
+    def register_factory(cls) -> Callable[[type[T]], type[T]]:
+        def decorator(factory: type[T]) -> type[T]:
+            cls._factories.add(factory())
+            return factory
+
+        return decorator
+
+    @classmethod
+    def create(cls, first_llm_config: dict[str, Any]) -> dict[str, Any]:
+        model = first_llm_config.pop("model")
+        api_type = first_llm_config.pop("api_type", "openai")
+
+        first_llm_config["provider"] = f"{api_type}/{model}"
+        return first_llm_config
+
+    @classmethod
+    @abstractmethod
+    def get_api_type(cls) -> str: ...
+
+    @classmethod
+    def accepts(cls, first_llm_config: dict[str, Any]) -> bool:
+        return first_llm_config.get("api_type", "openai") == cls.get_api_type()  # type: ignore [no-any-return]
+
+
+@LiteLLmConfigFactory.register_factory()
+class DefaultLiteLLmConfigFactory(LiteLLmConfigFactory):
+    @classmethod
+    def get_api_type(cls) -> str:
+        raise NotImplementedError("DefaultLiteLLmConfigFactory does not have an API type.")
+
+    @classmethod
+    def accepts(cls, first_llm_config: dict[str, Any]) -> bool:
+        non_base_api_types = ["google", "ollama"]
+        return first_llm_config.get("api_type", "openai") not in non_base_api_types
+
+    @classmethod
+    def create(cls, first_llm_config: dict[str, Any]) -> dict[str, Any]:
+        api_type = first_llm_config.get("api_type", "openai")
+        if api_type != "openai" and "api_key" not in first_llm_config:
+            raise ValueError("API key is required.")
+        first_llm_config["api_token"] = first_llm_config.pop("api_key", os.getenv("OPENAI_API_KEY"))
+
+        first_llm_config = super().create(first_llm_config)
+
+        return first_llm_config
+
+
+@LiteLLmConfigFactory.register_factory()
+class GoogleLiteLLmConfigFactory(LiteLLmConfigFactory):
+    @classmethod
+    def get_api_type(cls) -> str:
+        return "google"
+
+    @classmethod
+    def create(cls, first_llm_config: dict[str, Any]) -> dict[str, Any]:
+        # api type must be changed before calling super().create
+        # litellm uses gemini as the api type for google
+        first_llm_config["api_type"] = "gemini"
+        first_llm_config["api_token"] = first_llm_config.pop("api_key")
+        first_llm_config = super().create(first_llm_config)
+
+        return first_llm_config
+
+    @classmethod
+    def accepts(cls, first_llm_config: dict[str, Any]) -> bool:
+        api_type: str = first_llm_config.get("api_type", "")
+        return api_type == cls.get_api_type() or api_type == "gemini"
+
+
+@LiteLLmConfigFactory.register_factory()
+class OllamaLiteLLmConfigFactory(LiteLLmConfigFactory):
+    @classmethod
+    def get_api_type(cls) -> str:
+        return "ollama"
+
+    @classmethod
+    def create(cls, first_llm_config: dict[str, Any]) -> dict[str, Any]:
+        first_llm_config = super().create(first_llm_config)
+        if "client_host" in first_llm_config:
+            first_llm_config["api_base"] = first_llm_config.pop("client_host")
+
+        return first_llm_config

autogen/interop/pydantic_ai/__init__.py

@@ -0,0 +1,7 @@
+# Copyright (c) 2023 - 2025, AG2ai, Inc., AG2ai open-source projects maintainers and core contributors
+#
+# SPDX-License-Identifier: Apache-2.0
+
+from .pydantic_ai import PydanticAIInteroperability
+
+__all__ = ["PydanticAIInteroperability"]