LLM_Engineering_OLD/week1/community-contributions/mock-dashboard-summary/day1-dashboard-metrics-summary.ipynb

{
 "cells": [
  {
   "cell_type": "markdown",
   "id": "de3b5d4c",
   "metadata": {},
   "source": [
    "# 🧠 Grafana Dashboard Summarizer\n",
    "Simulate reading a Grafana dashboard JSON and summarize its panels using GPT or plain logic."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "0abf3aaf",
   "metadata": {},
   "outputs": [],
   "source": [
    "import os\n",
    "from dotenv import load_dotenv\n",
    "from IPython.display import Markdown, display\n",
    "from openai import OpenAI\n",
    "import json\n",
    "import pandas as pd"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "ad82ca65",
   "metadata": {},
   "outputs": [],
   "source": [
    "\n",
    "\n",
    "with open(\"mock_grafana_dashboard.json\", \"r\") as f:\n",
    "    data = json.load(f)\n",
    "\n",
    "dashboard = data[\"dashboard\"]\n",
    "panels = dashboard[\"panels\"]\n",
    "print(f\"Dashboard Title: {dashboard['title']}\")\n",
    "print(f\"Total Panels: {len(panels)}\\n\")\n",
    "for p in panels:\n",
    "    print(f\"- {p['title']} ({p['type']})\")\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "1bf45c0f",
   "metadata": {},
   "outputs": [],
   "source": [
    "# Extracting panel data\n",
    "\n",
    "panel_data = []\n",
    "for p in panels:\n",
    "    thresholds = p.get(\"fieldConfig\", {}).get(\"defaults\", {}).get(\"thresholds\", {}).get(\"steps\", [])\n",
    "    panel_data.append({\n",
    "        \"Title\": p[\"title\"],\n",
    "        \"Type\": p[\"type\"],\n",
    "        \"Unit\": p.get(\"fieldConfig\", {}).get(\"defaults\", {}).get(\"unit\", \"N/A\"),\n",
    "        \"Thresholds\": thresholds\n",
    "    })\n",
    "\n",
    "df = pd.DataFrame(panel_data)\n",
    "df\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "90b67133",
   "metadata": {},
   "outputs": [],
   "source": [
    "\n",
    "summary_prompt = f\"\"\"\n",
    "You are a helpful assistant summarizing a system monitoring dashboard.\n",
    "\n",
    "Dashboard: {dashboard['title']}\n",
    "Panels:\n",
    "\"\"\"\n",
    "for idx, row in df.iterrows():\n",
    "    summary_prompt += f\"- {row['Title']} [{row['Type']}] - Unit: {row['Unit']}, Thresholds: {row['Thresholds']}\\n\"\n",
    "\n",
    "print(summary_prompt)\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "69a4208c",
   "metadata": {},
   "outputs": [],
   "source": [
    "\n",
    "\n",
    "load_dotenv(override=True)\n",
    "api_key = os.getenv('OPENAI_API_KEY')\n",
    "# Check the key\n",
    "\n",
    "if not api_key:\n",
    "    print(\"No API key was found - please head over to the troubleshooting notebook in this folder to identify & fix!\")\n",
    "elif not api_key.startswith(\"sk-proj-\"):\n",
    "    print(\"An API key was found, but it doesn't start sk-proj-; please check you're using the right key - see troubleshooting notebook\")\n",
    "elif api_key.strip() != api_key:\n",
    "    print(\"An API key was found, but it looks like it might have space or tab characters at the start or end - please remove them - see troubleshooting notebook\")\n",
    "else:\n",
    "    print(\"API key found and looks good so far!\")\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "2eee5a32",
   "metadata": {},
   "outputs": [],
   "source": [
    "openai = OpenAI()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "660eedb7",
   "metadata": {},
   "outputs": [],
   "source": [
    "def summarize():\n",
    "    response = openai.chat.completions.create(\n",
    "    model=\"gpt-4o-mini\",\n",
    "    messages=[\n",
    "        {\"role\": \"system\", \"content\": \"You are a Grafana dashboard summarizer.\"},\n",
    "        {\"role\": \"user\", \"content\": summary_prompt}\n",
    "    ]\n",
    ")\n",
    "    return response.choices[0].message.content"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "55f57d56",
   "metadata": {},
   "outputs": [],
   "source": [
    "\n",
    "summary = summarize()\n",
    "display(Markdown(summary))"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "10dbfd6c",
   "metadata": {},
   "outputs": [],
   "source": []
  }
 ],
 "metadata": {
  "kernelspec": {
   "display_name": "arunllms",
   "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": "3.11.11"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 5
}