Add Connery Tool and Toolkit

docs/docs/integrations/toolkits/connery.ipynb

@@ -0,0 +1,136 @@
+{
+ "cells": [
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "# Connery Toolkit\n",
+    "\n",
+    "Using this toolkit, you can integrate Connery Actions into your LangChain agent.\n",
+    "\n",
+    "If you want to use only one particular Connery Action in your agent,\n",
+    "check out the [Connery Action Tool](/docs/integrations/tools/connery) documentation.\n",
+    "\n",
+    "## What is Connery?\n",
+    "\n",
+    "Connery is an open-source plugin infrastructure for AI.\n",
+    "\n",
+    "With Connery, you can easily create a custom plugin with a set of actions and seamlessly integrate them into your LangChain agent.\n",
+    "Connery will take care of critical aspects such as runtime, authorization, secret management, access management, audit logs, and other vital features.\n",
+    "\n",
+    "Furthermore, Connery, supported by our community, provides a diverse collection of ready-to-use open-source plugins for added convenience.\n",
+    "\n",
+    "Learn more about Connery:\n",
+    "\n",
+    "- GitHub: https://github.com/connery-io/connery-platform\n",
+    "- Documentation: https://docs.connery.io\n",
+    "\n",
+    "## Prerequisites\n",
+    "\n",
+    "To use Connery Actions in your LangChain agent, you need to do some preparation:\n",
+    "\n",
+    "1. Set up the Connery runner using the [Quickstart](https://docs.connery.io/docs/platform/quick-start/) guide.\n",
+    "2. Install all the plugins with the actions you want to use in your agent.\n",
+    "3. Set environment variables `CONNERY_RUNNER_URL` and `CONNERY_RUNNER_API_KEY` so the toolkit can communicate with the Connery Runner.\n",
+    "\n",
+    "## Example of using Connery Toolkit\n",
+    "\n",
+    "In the example below, we create an agent that uses two Connery Actions to summarize a public webpage and send the summary by email:\n",
+    "\n",
+    "1. **Summarize public webpage** action from the [Summarization](https://github.com/connery-io/summarization-plugin) plugin.\n",
+    "2. **Send email** action from the [Gmail](https://github.com/connery-io/gmail) plugin.\n",
+    "\n",
+    "You can see a LangSmith trace of this example [here](https://smith.langchain.com/public/4af5385a-afe9-46f6-8a53-57fe2d63c5bc/r)."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 1,
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "\n",
+      "\n",
+      "\u001b[1m> Entering new AgentExecutor chain...\u001b[0m\n",
+      "\u001b[32;1m\u001b[1;3m\n",
+      "Invoking: `CA72DFB0AB4DF6C830B43E14B0782F70` with `{'publicWebpageUrl': 'http://www.paulgraham.com/vb.html'}`\n",
+      "\n",
+      "\n",
+      "\u001b[0m\u001b[33;1m\u001b[1;3m{'summary': 'The author reflects on the concept of life being short and how having children made them realize the true brevity of life. They discuss how time can be converted into discrete quantities and how limited certain experiences are. The author emphasizes the importance of prioritizing and eliminating unnecessary things in life, as well as actively pursuing meaningful experiences. They also discuss the negative impact of getting caught up in online arguments and the need to be aware of how time is being spent. The author suggests pruning unnecessary activities, not waiting to do things that matter, and savoring the time one has.'}\u001b[0m\u001b[32;1m\u001b[1;3m\n",
+      "Invoking: `CABC80BB79C15067CA983495324AE709` with `{'recipient': '[email protected]', 'subject': 'Summary of the webpage', 'body': 'Here is a short summary of the webpage http://www.paulgraham.com/vb.html:\\n\\nThe author reflects on the concept of life being short and how having children made them realize the true brevity of life. They discuss how time can be converted into discrete quantities and how limited certain experiences are. The author emphasizes the importance of prioritizing and eliminating unnecessary things in life, as well as actively pursuing meaningful experiences. They also discuss the negative impact of getting caught up in online arguments and the need to be aware of how time is being spent. The author suggests pruning unnecessary activities, not waiting to do things that matter, and savoring the time one has.\\n\\nYou can find the full webpage [here](http://www.paulgraham.com/vb.html).'}`\n",
+      "\n",
+      "\n",
+      "\u001b[0m\u001b[33;1m\u001b[1;3m{'messageId': '<[email protected]>'}\u001b[0m\u001b[32;1m\u001b[1;3mI have sent the email with the summary of the webpage to [email protected]. Please check your inbox.\u001b[0m\n",
+      "\n",
+      "\u001b[1m> Finished chain.\u001b[0m\n",
+      "I have sent the email with the summary of the webpage to [email protected]. Please check your inbox.\n"
+     ]
+    }
+   ],
+   "source": [
+    "import os\n",
+    "\n",
+    "from langchain.agents import AgentType, initialize_agent\n",
+    "from langchain.chat_models import ChatOpenAI\n",
+    "from langchain_community.agent_toolkits.connery import ConneryToolkit\n",
+    "from langchain_community.tools.connery import ConneryService\n",
+    "\n",
+    "# Specify your Connery Runner credentials.\n",
+    "os.environ[\"CONNERY_RUNNER_URL\"] = \"\"\n",
+    "os.environ[\"CONNERY_RUNNER_API_KEY\"] = \"\"\n",
+    "\n",
+    "# Specify OpenAI API key.\n",
+    "os.environ[\"OPENAI_API_KEY\"] = \"\"\n",
+    "\n",
+    "# Specify your email address to receive the email with the summary from example below.\n",
+    "recepient_email = \"[email protected]\"\n",
+    "\n",
+    "# Create a Connery Toolkit with all the available actions from the Connery Runner.\n",
+    "connery_service = ConneryService()\n",
+    "connery_toolkit = ConneryToolkit.create_instance(connery_service)\n",
+    "\n",
+    "# Use OpenAI Functions agent to execute the prompt using actions from the Connery Toolkit.\n",
+    "llm = ChatOpenAI(temperature=0)\n",
+    "agent = initialize_agent(\n",
+    "    connery_toolkit.get_tools(), llm, AgentType.OPENAI_FUNCTIONS, verbose=True\n",
+    ")\n",
+    "result = agent.run(\n",
+    "    f\"\"\"Make a short summary of the webpage http://www.paulgraham.com/vb.html in three sentences\n",
+    "and send it to {recepient_email}. Include the link to the webpage into the body of the email.\"\"\"\n",
+    ")\n",
+    "print(result)"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "NOTE: Connery Action is a structured tool, so you can only use it in the agents supporting structured tools."
+   ]
+  }
+ ],
+ "metadata": {
+  "kernelspec": {
+   "display_name": "Python 3",
+   "language": "python",
+   "name": "python3"
+  },
+  "language_info": {
+   "codemirror_mode": {
+    "name": "ipython",
+    "version": 3
+   },
+   "file_extension": ".py",
+   "mimetype": "text/x-python",
+   "name": "python",
+   "nbconvert_exporter": "python",
+   "pygments_lexer": "ipython3",
+   "version": "3.10.13"
+  }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 2
+}

docs/docs/integrations/tools/connery.ipynb

@@ -0,0 +1,165 @@
+{
+ "cells": [
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "# Connery Action Tool\n",
+    "\n",
+    "Using this tool, you can integrate individual Connery Action into your LangChain agent.\n",
+    "\n",
+    "If you want to use more than one Connery Action in your agent,\n",
+    "check out the [Connery Toolkit](/docs/integrations/toolkits/connery) documentation.\n",
+    "\n",
+    "## What is Connery?\n",
+    "\n",
+    "Connery is an open-source plugin infrastructure for AI.\n",
+    "\n",
+    "With Connery, you can easily create a custom plugin with a set of actions and seamlessly integrate them into your LangChain agent.\n",
+    "Connery will take care of critical aspects such as runtime, authorization, secret management, access management, audit logs, and other vital features.\n",
+    "\n",
+    "Furthermore, Connery, supported by our community, provides a diverse collection of ready-to-use open-source plugins for added convenience.\n",
+    "\n",
+    "Learn more about Connery:\n",
+    "\n",
+    "- GitHub: https://github.com/connery-io/connery-platform\n",
+    "- Documentation: https://docs.connery.io\n",
+    "\n",
+    "## Prerequisites\n",
+    "\n",
+    "To use Connery Actions in your LangChain agent, you need to do some preparation:\n",
+    "\n",
+    "1. Set up the Connery runner using the [Quickstart](https://docs.connery.io/docs/platform/quick-start/) guide.\n",
+    "2. Install all the plugins with the actions you want to use in your agent.\n",
+    "3. Set environment variables `CONNERY_RUNNER_URL` and `CONNERY_RUNNER_API_KEY` so the toolkit can communicate with the Connery Runner.\n",
+    "\n",
+    "## Example of using Connery Action Tool\n",
+    "\n",
+    "In the example below, we fetch action by its ID from the Connery Runner and then call it with the specified parameters.\n",
+    "\n",
+    "Here, we use the ID of the **Send email** action from the [Gmail](https://github.com/connery-io/gmail) plugin."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 11,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "import os\n",
+    "\n",
+    "from langchain.agents import AgentType, initialize_agent\n",
+    "from langchain.chat_models import ChatOpenAI\n",
+    "from langchain_community.tools.connery import ConneryService\n",
+    "\n",
+    "# Specify your Connery Runner credentials.\n",
+    "os.environ[\"CONNERY_RUNNER_URL\"] = \"\"\n",
+    "os.environ[\"CONNERY_RUNNER_API_KEY\"] = \"\"\n",
+    "\n",
+    "# Specify OpenAI API key.\n",
+    "os.environ[\"OPENAI_API_KEY\"] = \"\"\n",
+    "\n",
+    "# Specify your email address to receive the emails from examples below.\n",
+    "recepient_email = \"[email protected]\"\n",
+    "\n",
+    "# Get the SendEmail action from the Connery Runner by ID.\n",
+    "connery_service = ConneryService()\n",
+    "send_email_action = connery_service.get_action(\"CABC80BB79C15067CA983495324AE709\")"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "Run the action manually."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "manual_run_result = send_email_action.run(\n",
+    "    {\n",
+    "        \"recipient\": recepient_email,\n",
+    "        \"subject\": \"Test email\",\n",
+    "        \"body\": \"This is a test email sent from Connery.\",\n",
+    "    }\n",
+    ")\n",
+    "print(manual_run_result)"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "Run the action using the OpenAI Functions agent.\n",
+    "\n",
+    "You can see a LangSmith trace of this example [here](https://smith.langchain.com/public/a37d216f-c121-46da-a428-0e09dc19b1dc/r)."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 15,
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "\n",
+      "\n",
+      "\u001b[1m> Entering new AgentExecutor chain...\u001b[0m\n",
+      "\u001b[32;1m\u001b[1;3m\n",
+      "Invoking: `CABC80BB79C15067CA983495324AE709` with `{'recipient': '[email protected]', 'subject': 'Late for Meeting', 'body': 'Dear Team,\\n\\nI wanted to inform you that I will be late for the meeting today. I apologize for any inconvenience caused. Please proceed with the meeting without me and I will join as soon as I can.\\n\\nBest regards,\\n[Your Name]'}`\n",
+      "\n",
+      "\n",
+      "\u001b[0m\u001b[36;1m\u001b[1;3m{'messageId': '<[email protected]>'}\u001b[0m\u001b[32;1m\u001b[1;3mI have sent an email to [email protected] informing them that you will be late for the meeting.\u001b[0m\n",
+      "\n",
+      "\u001b[1m> Finished chain.\u001b[0m\n",
+      "I have sent an email to [email protected] informing them that you will be late for the meeting.\n"
+     ]
+    }
+   ],
+   "source": [
+    "llm = ChatOpenAI(temperature=0)\n",
+    "agent = initialize_agent(\n",
+    "    [send_email_action], llm, AgentType.OPENAI_FUNCTIONS, verbose=True\n",
+    ")\n",
+    "agent_run_result = agent.run(\n",
+    "    f\"Send an email to the {recepient_email} and say that I will be late for the meeting.\"\n",
+    ")\n",
+    "print(agent_run_result)"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "NOTE: Connery Action is a structured tool, so you can only use it in the agents supporting structured tools."
+   ]
+  }
+ ],
+ "metadata": {
+  "kernelspec": {
+   "display_name": "Python 3",
+   "language": "python",
+   "name": "python3"
+  },
+  "language_info": {
+   "codemirror_mode": {
+    "name": "ipython",
+    "version": 3
+   },
+   "file_extension": ".py",
+   "mimetype": "text/x-python",
+   "name": "python",
+   "nbconvert_exporter": "python",
+   "pygments_lexer": "ipython3",
+   "version": "3.10.13"
+  }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 2
+}

libs/community/langchain_community/agent_toolkits/__init__.py

@@ -18,6 +18,7 @@
 from langchain_community.agent_toolkits.azure_cognitive_services import (
     AzureCognitiveServicesToolkit,
 )
+from langchain_community.agent_toolkits.connery import ConneryToolkit
 from langchain_community.agent_toolkits.file_management.toolkit import (
     FileManagementToolkit,
 )
@@ -49,6 +50,7 @@
     "AINetworkToolkit",
     "AmadeusToolkit",
     "AzureCognitiveServicesToolkit",
+    "ConneryToolkit",
     "FileManagementToolkit",
     "GmailToolkit",
     "JiraToolkit",

libs/community/langchain_community/agent_toolkits/connery/__init__.py

@@ -0,0 +1,7 @@
+"""
+This module contains the ConneryToolkit.
+"""
+
+from .toolkit import ConneryToolkit
+
+__all__ = ["ConneryToolkit"]

libs/community/langchain_community/agent_toolkits/connery/toolkit.py

@@ -0,0 +1,51 @@
+from typing import List
+
+from langchain_core.pydantic_v1 import root_validator
+from langchain_core.tools import BaseTool
+
+from langchain_community.agent_toolkits.base import BaseToolkit
+from langchain_community.tools.connery import ConneryService
+
+
+class ConneryToolkit(BaseToolkit):
+    """
+    A LangChain Toolkit with a list of Connery Actions as tools.
+    """
+
+    tools: List[BaseTool]
+
+    def get_tools(self) -> List[BaseTool]:
+        """
+        Returns the list of Connery Actions.
+        """
+        return self.tools
+
+    @root_validator()
+    def validate_attributes(cls, values: dict) -> dict:
+        """
+        Validate the attributes of the ConneryToolkit class.
+        Parameters:
+            values (dict): The arguments to validate.
+        Returns:
+            dict: The validated arguments.
+        """
+
+        if not values.get("tools"):
+            raise ValueError("The attribute 'tools' must be set.")
+
+        return values
+
+    @classmethod
+    def create_instance(cls, connery_service: ConneryService) -> "ConneryToolkit":
+        """
+        Creates a Connery Toolkit using a Connery Service.
+        Parameters:
+            connery_service (ConneryService): The Connery Service
+            to to get the list of Connery Actions.
+        Returns:
+            ConneryToolkit: The Connery Toolkit.
+        """
+
+        instance = cls(tools=connery_service.list_actions())
+
+        return instance