Add Cybersecurity PoC Agent Notebook

examples/cookbooks/Chile_Government_Services_Assistant.ipynb

@@ -0,0 +1,300 @@
+{
+  "cells": [
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "ZH_nR-SvvkDG"
+      },
+      "source": [
+        "# Chile Government Services Assistant - AI Chatbot"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "w8B741JgvpFj"
+      },
+      "source": [
+        "This notebook demonstrates how to use an AI-powered assistant to answer questions about Chilean government services and procedures, using the Firecrawl API and a friendly, step-by-step conversational approach."
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "y8jiJYf4FA0m"
+      },
+      "source": [
+        "[![Open in Colab](https://colab.research.google.com/assets/colab-badge.svg)](https://colab.research.google.com/github/DhivyaBharathy-web/PraisonAI/blob/main/examples/cookbooks/Chile_Government_Services_Assistant.ipynb)\n"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "RRw8sPG89KNb"
+      },
+      "source": [
+        "# Install dependencies"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "id": "rW8ltqCICV8o"
+      },
+      "outputs": [],
+      "source": [
+        "!pip install flask firecrawl praisonaiagents google-genai python-dotenv deep-translator"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "XGjyt-B_EfbM"
+      },
+      "source": [
+        "# Set API Keys"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "id": "qf8B_YltDiIe"
+      },
+      "outputs": [],
+      "source": [
+        "import os\n",
+        "\n",
+        "os.environ['FIRECRAWL_API_KEY'] = \"your api key here\"\n",
+        "os.environ['OPENAI_API_KEY'] = \"your api key here\""
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "ccO0vwvCEqUJ"
+      },
+      "source": [
+        "# Import Libraries & Translator"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "id": "0prDQ5TpDnFu"
+      },
+      "outputs": [],
+      "source": [
+        "from firecrawl import FirecrawlApp, ScrapeOptions\n",
+        "from deep_translator import GoogleTranslator\n",
+        "import re\n",
+        "\n",
+        "def translate_to_spanish(text):\n",
+        "    try:\n",
+        "        return GoogleTranslator(source='auto', target='es').translate(text)\n",
+        "    except Exception as e:\n",
+        "        print(\"Translation to Spanish failed:\", e)\n",
+        "        return text\n",
+        "\n",
+        "def translate_to_english(text):\n",
+        "    try:\n",
+        "        # Remove Markdown images and None values before translation\n",
+        "        text = str(text).replace(\"None\", \"\")\n",
+        "        text = re.sub(r'!\\[.*?\\]\\(.*?\\)', '', text)\n",
+        "        return GoogleTranslator(source='auto', target='en').translate(text)\n",
+        "    except Exception as e:\n",
+        "        print(\"Translation to English failed:\", e)\n",
+        "        return text"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "WxOlCHMmEuK2"
+      },
+      "source": [
+        "# Firecrawl Tool Class"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "id": "G4RyzJ5mDp0t"
+      },
+      "outputs": [],
+      "source": [
+        "class FirecrawlTool:\n",
+        "    def __init__(self, api_key, instruction: str, template: str):\n",
+        "        if not api_key:\n",
+        "            raise ValueError(\"Firecrawl API key not provided.\")\n",
+        "        self.app = FirecrawlApp(api_key=api_key)\n",
+        "        self.instruction = instruction\n",
+        "        self.template = template\n",
+        "\n",
+        "    def search(self, search: str) -> str:\n",
+        "        if not search or len(search) < 5:\n",
+        "            return \"Error: Please provide a valid search query (at least 5 characters).\"\n",
+        "        response_md = \"\"\n",
+        "        try:\n",
+        "            search_result = self.app.search(\n",
+        "                query=self.instruction + search,\n",
+        "                limit=2,\n",
+        "                country=\"cl\",\n",
+        "                lang=\"es\",  # Always search in Spanish for best results\n",
+        "                scrape_options=ScrapeOptions(formats=[\"markdown\", \"links\"])\n",
+        "            )\n",
+        "            if search_result and hasattr(search_result, 'data') and search_result.data:\n",
+        "                filtered_results = [\n",
+        "                    result for result in search_result.data\n",
+        "                    if str(result.get(\"url\", \"\")).startswith(\"https://www.chileatiende.gob.cl/fichas\") and not str(result.get(\"url\", \"\")).endswith(\"pdf\")\n",
+        "                ]\n",
+        "                if filtered_results:\n",
+        "                    for num, result in enumerate(filtered_results, start=1):\n",
+        "                        response_md += self.template.format(\n",
+        "                            result_number=num,\n",
+        "                            page_title=str(result.get(\"title\", \"\")),\n",
+        "                            page_url=str(result.get(\"url\", \"\")),\n",
+        "                            page_content=str(result.get(\"markdown\", \"\"))\n",
+        "                        )\n",
+        "                    return response_md\n",
+        "                else:\n",
+        "                    return None\n",
+        "            else:\n",
+        "                return None\n",
+        "        except Exception as e:\n",
+        "            return f\"Error during search: {e}\""
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "MjkjTWn_ExS0"
+      },
+      "source": [
+        "# Firecrawl Prompt Template"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "id": "AfivymU8Dufz"
+      },
+      "outputs": [],
+      "source": [
+        "FIRECRAWL_INSTRUCTION = \"ChileAtiende: \"\n",
+        "FIRECRAWL_TEMPLATE = \"\"\"\n",
+        "# Result {result_number}\n",
+        "\n",
+        "## Page Name:\n",
+        "\"{page_title}\"\n",
+        "\n",
+        "## URL:\n",
+        "{page_url}\n",
+        "\n",
+        "## Content:\n",
+        "{page_content}\n",
+        "\n",
+        "\"\"\""
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "zK8AA_DlEz9K"
+      },
+      "source": [
+        "# Initialize Firecrawl Tool"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "id": "c3NKK0ZjDwKT"
+      },
+      "outputs": [],
+      "source": [
+        "firecrawl_tool = FirecrawlTool(\n",
+        "    api_key=os.environ['FIRECRAWL_API_KEY'],\n",
+        "    instruction=FIRECRAWL_INSTRUCTION,\n",
+        "    template=FIRECRAWL_TEMPLATE\n",
+        ")"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "uzXYIF_gE3XV"
+      },
+      "source": [
+        "# Main Chat Loop"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "colab": {
+          "base_uri": "https://localhost:8080/"
+        },
+        "id": "TXMgZQNkDx7n",
+        "outputId": "76303cd1-a576-483f-a22d-9857e5e6d797"
+      },
+      "outputs": [
+        {
+          "name": "stdout",
+          "output_type": "stream",
+          "text": [
+            "Hello! I am your ChileAtiende assistant, Tomás. How can I help you today?\n",
+            "You can ask me, for example: How to renew your ID card, How to apply for the Winter Bonus, etc.\n",
+            "\n",
+            "You: exit\n",
+            "Tomás: It was a pleasure to help you. Goodbye!\n"
+          ]
+        }
+      ],
+      "source": [
+        "print(\"Hello! I am your ChileAtiende assistant, Tomás. How can I help you today?\")\n",
+        "print(\"You can ask me, for example: How to renew your ID card, How to apply for the Winter Bonus, etc.\")\n",
+        "\n",
+        "while True:\n",
+        "    user_input = input(\"\\nYou: \")\n",
+        "    if user_input.lower() in [\"exit\", \"quit\"]:\n",
+        "        print(\"Tomás: It was a pleasure to help you. Goodbye!\")\n",
+        "        break\n",
+        "\n",
+        "    # Translate English input to Spanish for Firecrawl\n",
+        "    spanish_query = translate_to_spanish(user_input)\n",
+        "    spanish_answer = firecrawl_tool.search(spanish_query)\n",
+        "\n",
+        "    # Only translate if we got a real answer\n",
+        "    if spanish_answer and isinstance(spanish_answer, str) and spanish_answer.strip() and \"Error\" not in spanish_answer:\n",
+        "        try:\n",
+        "            english_answer = translate_to_english(spanish_answer)\n",
+        "            print(\"\\nTomás (in English):\\n\", english_answer)\n",
+        "        except Exception as e:\n",
+        "            print(f\"\\nTomás: I found information, but couldn't translate it. Here it is in Spanish:\\n{spanish_answer}\\n(Translation error: {e})\")\n",
+        "    else:\n",
+        "        print(\"\\nTomás: Sorry, I couldn't find relevant information. Try rephrasing your question or ask about another service.\")"
+      ]
+    }
+  ],
+  "metadata": {
+    "colab": {
+      "provenance": []
+    },
+    "kernelspec": {
+      "display_name": "Python 3",
+      "name": "python3"
+    },
+    "language_info": {
+      "name": "python"
+    }
+  },
+  "nbformat": 4,
+  "nbformat_minor": 0
+}