Add docs and lint files

docs/docs/integrations/tools/azure_content_safety.ipynb

@@ -0,0 +1,143 @@
+{
+ "cells": [
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "# `AzureContentSafetyTextTool`"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    ">The `AzureContentSafetyTextTool` acts as a wrapper around the Azure AI Content Safety Service/API.\n",
+    ">The Tool will detect harmful content according to Azure's Content Safety Policy."
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "# Example\n",
+    "\n",
+    "Get the required dependencies"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 1,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "import os\n",
+    "\n",
+    "from langchain import hub"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "We will use a prompt to tell the model what to do. LangChain Prompts can be configured, however for sake of simplicity we will use a premade prompt from LangSmith. This requires an API key which can be setup [here](https://www.langchain.com/langsmith) after registration."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "LANGSMITH_KEY = os.environ[\"LANGSMITH_KEY\"]\n",
+    "prompt = hub.pull(\"hwchase17/structured-chat-agent\", api_key=LANGSMITH_KEY)"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "Now we can use the `AzureContentSafetyTextTool` combine with a model, using `create_structured_chat_agent`."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "from langchain.agents import AgentExecutor, create_structured_chat_agent\n",
+    "from langchain_community.tools.azure_ai_services.content_safety import (\n",
+    "    AzureContentSafetyTextTool,\n",
+    ")\n",
+    "from langchain_openai import AzureChatOpenAI"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "tools = [\n",
+    "    AzureContentSafetyTextTool(\n",
+    "        content_safety_key=os.environ[\"CONTENT_SAFETY_KEY\"],\n",
+    "        content_safety_endpoint=os.environ[\"CONTENT_SAFETY_ENDPOINT\"],\n",
+    "    )\n",
+    "]\n",
+    "\n",
+    "model = AzureChatOpenAI(\n",
+    "    openai_api_version=os.environ[\"OPENAI_API_VERSION\"],\n",
+    "    azure_deployment=os.environ[\"COMPLETIONS_MODEL\"],\n",
+    "    azure_endpoint=os.environ[\"AZURE_OPENAI_ENDPOINT\"],\n",
+    "    api_key=os.environ[\"AZURE_OPENAI_API_KEY\"],\n",
+    ")\n",
+    "\n",
+    "agent = create_structured_chat_agent(model, tools, prompt)\n",
+    "\n",
+    "agent_executor = AgentExecutor(\n",
+    "    agent=agent, tools=tools, verbose=True, handle_parsing_errors=True\n",
+    ")"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "Then by using `.invoke`, the model can be told what to do and assess if using the tools it was given would assist in it's response."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "input = \"I hate you\"\n",
+    "agent_executor.invoke(\n",
+    "    {\"input\": f\"Can you check the following text for harmful content : {input}\"}\n",
+    ")"
+   ]
+  }
+ ],
+ "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": "3.12.7"
+  }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 2
+}

libs/community/tests/unit_tests/tools/azure_ai_services/test_content_safety.py

@@ -69,4 +69,4 @@ def test_no_harmful_content_detected(mocker: Any) -> None:
     output = "Harm: 0\n"
 
     result = tool._run(input)
-    assert result == output
+    assert result == output