mirror of
https://github.com/hwchase17/langchain.git
synced 2025-10-29 06:41:10 +00:00
community[minor]: Connery Tool and Toolkit (#14506)
## Summary This PR implements the "Connery Action Tool" and "Connery Toolkit". Using them, you can integrate Connery actions into your LangChain agents and chains. Connery is an open-source plugin infrastructure for AI. With Connery, you can easily create a custom plugin with a set of actions and seamlessly integrate them into your LangChain agents and chains. Connery will handle the rest: runtime, authorization, secret management, access management, audit logs, and other vital features. Additionally, Connery and our community offer a wide range of ready-to-use open-source plugins for your convenience. Learn more about Connery: - GitHub: https://github.com/connery-io/connery-platform - Documentation: https://docs.connery.io - Twitter: https://twitter.com/connery_io ## TODOs - [x] API wrapper - [x] Integration tests - [x] Connery Action Tool - [x] Docs - [x] Example - [x] Integration tests - [x] Connery Toolkit - [x] Docs - [x] Example - [x] Formatting (`make format`) - [x] Linting (`make lint`) - [x] Testing (`make test`)
This commit is contained in:
Volodymyr Machula
committed by
GitHub
GitHub
parent
8457c31c04
commit
32c5be8b73
165
docs/docs/integrations/tools/connery.ipynb
Normal file
165
docs/docs/integrations/tools/connery.ipynb
Normal file
@@ -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\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/runner/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 = \"test@example.com\"\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': 'test@example.com', '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': '<d34a694d-50e0-3988-25da-e86b4c51d7a7@gmail.com>'}\u001b[0m\u001b[32;1m\u001b[1;3mI have sent an email to test@example.com 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 test@example.com 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
|
||||
}
|
||||
Reference in New Issue
Block a user