{
 "cells": [
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## Welcome to the Second Lab - Week 1, Day 3\n",
    "\n",
    "Today we will work with lots of models! This is a way to get comfortable with APIs."
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "<table style=\"margin: 0; text-align: left; width:100%\">\n",
    "    <tr>\n",
    "        <td style=\"width: 150px; height: 150px; vertical-align: middle;\">\n",
    "            <img src=\"../assets/stop.png\" width=\"150\" height=\"150\" style=\"display: block;\" />\n",
    "        </td>\n",
    "        <td>\n",
    "            <h2 style=\"color:#ff7800;\">Important point - please read</h2>\n",
    "            <span style=\"color:#ff7800;\">The way I collaborate with you may be different to other courses you've taken. I prefer not to type code while you watch. Rather, I execute Jupyter Labs, like this, and give you an intuition for what's going on. My suggestion is that you carefully execute this yourself, <b>after</b> watching the lecture. Add print statements to understand what's going on, and then come up with your own variations.<br/><br/>If you have time, I'd love it if you submit a PR for changes in the community_contributions folder - instructions in the resources. Also, if you have a Github account, use this to showcase your variations. Not only is this essential practice, but it demonstrates your skills to others, including perhaps future clients or employers...\n",
    "            </span>\n",
    "        </td>\n",
    "    </tr>\n",
    "</table>"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 4,
   "metadata": {},
   "outputs": [],
   "source": [
    "# Start with imports - ask ChatGPT to explain any package that you don't know\n",
    "\n",
    "import os\n",
    "import json\n",
    "from dotenv import load_dotenv\n",
    "from openai import OpenAI\n",
    "from anthropic import Anthropic\n",
    "from IPython.display import Markdown, display"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 20,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "True"
      ]
     },
     "execution_count": 20,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "# Always remember to do this!\n",
    "load_dotenv(override=True)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "OpenAI API Key exists and begins abc\n",
      "Anthropic API Key exists and begins abc\n",
      "Google API Key exists and begins AI\n",
      "DeepSeek API Key exists and begins abc\n",
      "Groq API Key exists and begins abc\n",
      "Hugging Face Token exists and begins hf_N\n"
     ]
    }
   ],
   "source": [
    "# Print the key prefixes to help with any debugging\n",
    "\n",
    "openai_api_key = os.getenv('OPENAI_API_KEY')\n",
    "anthropic_api_key = os.getenv('ANTHROPIC_API_KEY')\n",
    "google_api_key = os.getenv('GOOGLE_API_KEY')\n",
    "deepseek_api_key = os.getenv('DEEPSEEK_API_KEY')\n",
    "groq_api_key = os.getenv('GROQ_API_KEY')\n",
    "\n",
    "if openai_api_key:\n",
    "    print(f\"OpenAI API Key exists and begins {openai_api_key[:8]}\")\n",
    "else:\n",
    "    print(\"OpenAI API Key not set\")\n",
    "    \n",
    "if anthropic_api_key:\n",
    "    print(f\"Anthropic API Key exists and begins {anthropic_api_key[:7]}\")\n",
    "else:\n",
    "    print(\"Anthropic API Key not set (and this is optional)\")\n",
    "\n",
    "if google_api_key:\n",
    "    print(f\"Google API Key exists and begins {google_api_key[:2]}\")\n",
    "else:\n",
    "    print(\"Google API Key not set (and this is optional)\")\n",
    "\n",
    "if deepseek_api_key:\n",
    "    print(f\"DeepSeek API Key exists and begins {deepseek_api_key[:3]}\")\n",
    "else:\n",
    "    print(\"DeepSeek API Key not set (and this is optional)\")\n",
    "\n",
    "if groq_api_key:\n",
    "    print(f\"Groq API Key exists and begins {groq_api_key[:4]}\")\n",
    "else:\n",
    "    print(\"Groq API Key not set (and this is optional)\")\n",
    "\n",
    "hf_token = os.getenv('HF_TOKEN')\n",
    "if hf_token:\n",
    "    print(f\"Hugging Face Token exists and begins {hf_token[:4]}\")\n",
    "else:\n",
    "    print(\"Hugging Face Token not set (and this is optional)\")\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "request = \"Please come up with a challenging, nuanced question that I can ask a number of LLMs to evaluate their intelligence. \"\n",
    "request += \"Answer only with the question, no explanation.\""
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 9,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "'Please come up with a challenging, nuanced question that I can ask a number of LLMs to evaluate their intelligence. Answer only with the question, no explanation.'"
      ]
     },
     "execution_count": 9,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "request"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "If a truly benevolent superintelligence were to emerge, what would be the most profound and unexpected way it might choose to guide humanity towards its optimal future, knowing that direct intervention often creates dependency or unforeseen negative consequences?\n"
     ]
    }
   ],
   "source": [
    "from google import genai\n",
    "\n",
    "client = genai.Client()\n",
    "response = client.models.generate_content(\n",
    "    model=\"gemini-2.5-flash\",\n",
    "    contents=request,\n",
    ")\n",
    "print(response.text)\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 17,
   "metadata": {},
   "outputs": [],
   "source": [
    "question = response.text\n",
    "competitors = []\n",
    "answers = []\n",
    "messages = [{\"role\": \"user\", \"content\": question}]"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## Note - update since the videos\n",
    "\n",
    "I've updated the model names to use the latest models below, like GPT 5 and Claude Sonnet 4.5. It's worth noting that these models can be quite slow - like 1-2 minutes - but they do a great job! Feel free to switch them for faster models if you'd prefer, like the ones I use in the video."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 32,
   "metadata": {},
   "outputs": [],
   "source": [
    "import os\n",
    "from openai import OpenAI\n",
    "\n",
    "client = OpenAI(\n",
    "    base_url=\"https://router.huggingface.co/v1\",\n",
    "    api_key=os.getenv(\"HF_TOKEN\"),\n",
    ")"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 34,
   "metadata": {},
   "outputs": [
    {
     "ename": "PermissionDeniedError",
     "evalue": "Error code: 403 - {'error': 'This authentication method does not have sufficient permissions to call Inference Providers on behalf of user haomd2'}",
     "output_type": "error",
     "traceback": [
      "\u001b[31m---------------------------------------------------------------------------\u001b[39m",
      "\u001b[31mPermissionDeniedError\u001b[39m                     Traceback (most recent call last)",
      "\u001b[36mCell\u001b[39m\u001b[36m \u001b[39m\u001b[32mIn[34]\u001b[39m\u001b[32m, line 5\u001b[39m\n\u001b[32m      1\u001b[39m \u001b[38;5;66;03m# The API we know well\u001b[39;00m\n\u001b[32m      2\u001b[39m \u001b[38;5;66;03m# I've updated this with the latest model, but it can take some time because it likes to think!\u001b[39;00m\n\u001b[32m      3\u001b[39m \u001b[38;5;66;03m# Replace the model with gpt-4.1-mini if you'd prefer not to wait 1-2 mins\u001b[39;00m\n\u001b[32m----> \u001b[39m\u001b[32m5\u001b[39m completion = \u001b[43mclient\u001b[49m\u001b[43m.\u001b[49m\u001b[43mchat\u001b[49m\u001b[43m.\u001b[49m\u001b[43mcompletions\u001b[49m\u001b[43m.\u001b[49m\u001b[43mcreate\u001b[49m\u001b[43m(\u001b[49m\n\u001b[32m      6\u001b[39m \u001b[43m    \u001b[49m\u001b[43mmodel\u001b[49m\u001b[43m=\u001b[49m\u001b[33;43m\"\u001b[39;49m\u001b[33;43mQwen/Qwen3-8B\u001b[39;49m\u001b[33;43m\"\u001b[39;49m\u001b[43m,\u001b[49m\n\u001b[32m      7\u001b[39m \u001b[43m    \u001b[49m\u001b[43mmessages\u001b[49m\u001b[43m=\u001b[49m\u001b[43m[\u001b[49m\n\u001b[32m      8\u001b[39m \u001b[43m        \u001b[49m\u001b[43m{\u001b[49m\n\u001b[32m      9\u001b[39m \u001b[43m            \u001b[49m\u001b[33;43m\"\u001b[39;49m\u001b[33;43mrole\u001b[39;49m\u001b[33;43m\"\u001b[39;49m\u001b[43m:\u001b[49m\u001b[43m \u001b[49m\u001b[33;43m\"\u001b[39;49m\u001b[33;43muser\u001b[39;49m\u001b[33;43m\"\u001b[39;49m\u001b[43m,\u001b[49m\n\u001b[32m     10\u001b[39m \u001b[43m            \u001b[49m\u001b[33;43m\"\u001b[39;49m\u001b[33;43mcontent\u001b[39;49m\u001b[33;43m\"\u001b[39;49m\u001b[43m:\u001b[49m\u001b[43m \u001b[49m\u001b[33;43m\"\u001b[39;49m\u001b[33;43mWhat is the capital of France?\u001b[39;49m\u001b[33;43m\"\u001b[39;49m\n\u001b[32m     11\u001b[39m \u001b[43m        \u001b[49m\u001b[43m}\u001b[49m\n\u001b[32m     12\u001b[39m \u001b[43m    \u001b[49m\u001b[43m]\u001b[49m\u001b[43m,\u001b[49m\n\u001b[32m     13\u001b[39m \u001b[43m)\u001b[49m\n\u001b[32m     14\u001b[39m answer = completion.choices[\u001b[32m0\u001b[39m].message.content\n\u001b[32m     16\u001b[39m display(Markdown(answer))\n",
      "\u001b[36mFile \u001b[39m\u001b[32mc:\\Users\\haoma\\source\\repos\\ai-agent\\agents\\.venv\\Lib\\site-packages\\openai\\_utils\\_utils.py:287\u001b[39m, in \u001b[36mrequired_args.<locals>.inner.<locals>.wrapper\u001b[39m\u001b[34m(*args, **kwargs)\u001b[39m\n\u001b[32m    285\u001b[39m             msg = \u001b[33mf\u001b[39m\u001b[33m\"\u001b[39m\u001b[33mMissing required argument: \u001b[39m\u001b[38;5;132;01m{\u001b[39;00mquote(missing[\u001b[32m0\u001b[39m])\u001b[38;5;132;01m}\u001b[39;00m\u001b[33m\"\u001b[39m\n\u001b[32m    286\u001b[39m     \u001b[38;5;28;01mraise\u001b[39;00m \u001b[38;5;167;01mTypeError\u001b[39;00m(msg)\n\u001b[32m--> \u001b[39m\u001b[32m287\u001b[39m \u001b[38;5;28;01mreturn\u001b[39;00m \u001b[43mfunc\u001b[49m\u001b[43m(\u001b[49m\u001b[43m*\u001b[49m\u001b[43margs\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[43m*\u001b[49m\u001b[43m*\u001b[49m\u001b[43mkwargs\u001b[49m\u001b[43m)\u001b[49m\n",
      "\u001b[36mFile \u001b[39m\u001b[32mc:\\Users\\haoma\\source\\repos\\ai-agent\\agents\\.venv\\Lib\\site-packages\\openai\\resources\\chat\\completions\\completions.py:925\u001b[39m, in \u001b[36mCompletions.create\u001b[39m\u001b[34m(self, messages, model, audio, frequency_penalty, function_call, functions, logit_bias, logprobs, max_completion_tokens, max_tokens, metadata, modalities, n, parallel_tool_calls, prediction, presence_penalty, reasoning_effort, response_format, seed, service_tier, stop, store, stream, stream_options, temperature, tool_choice, tools, top_logprobs, top_p, user, web_search_options, extra_headers, extra_query, extra_body, timeout)\u001b[39m\n\u001b[32m    882\u001b[39m \u001b[38;5;129m@required_args\u001b[39m([\u001b[33m\"\u001b[39m\u001b[33mmessages\u001b[39m\u001b[33m\"\u001b[39m, \u001b[33m\"\u001b[39m\u001b[33mmodel\u001b[39m\u001b[33m\"\u001b[39m], [\u001b[33m\"\u001b[39m\u001b[33mmessages\u001b[39m\u001b[33m\"\u001b[39m, \u001b[33m\"\u001b[39m\u001b[33mmodel\u001b[39m\u001b[33m\"\u001b[39m, \u001b[33m\"\u001b[39m\u001b[33mstream\u001b[39m\u001b[33m\"\u001b[39m])\n\u001b[32m    883\u001b[39m \u001b[38;5;28;01mdef\u001b[39;00m\u001b[38;5;250m \u001b[39m\u001b[34mcreate\u001b[39m(\n\u001b[32m    884\u001b[39m     \u001b[38;5;28mself\u001b[39m,\n\u001b[32m   (...)\u001b[39m\u001b[32m    922\u001b[39m     timeout: \u001b[38;5;28mfloat\u001b[39m | httpx.Timeout | \u001b[38;5;28;01mNone\u001b[39;00m | NotGiven = NOT_GIVEN,\n\u001b[32m    923\u001b[39m ) -> ChatCompletion | Stream[ChatCompletionChunk]:\n\u001b[32m    924\u001b[39m     validate_response_format(response_format)\n\u001b[32m--> \u001b[39m\u001b[32m925\u001b[39m     \u001b[38;5;28;01mreturn\u001b[39;00m \u001b[38;5;28;43mself\u001b[39;49m\u001b[43m.\u001b[49m\u001b[43m_post\u001b[49m\u001b[43m(\u001b[49m\n\u001b[32m    926\u001b[39m \u001b[43m        \u001b[49m\u001b[33;43m\"\u001b[39;49m\u001b[33;43m/chat/completions\u001b[39;49m\u001b[33;43m\"\u001b[39;49m\u001b[43m,\u001b[49m\n\u001b[32m    927\u001b[39m \u001b[43m        \u001b[49m\u001b[43mbody\u001b[49m\u001b[43m=\u001b[49m\u001b[43mmaybe_transform\u001b[49m\u001b[43m(\u001b[49m\n\u001b[32m    928\u001b[39m \u001b[43m            \u001b[49m\u001b[43m{\u001b[49m\n\u001b[32m    929\u001b[39m \u001b[43m                \u001b[49m\u001b[33;43m\"\u001b[39;49m\u001b[33;43mmessages\u001b[39;49m\u001b[33;43m\"\u001b[39;49m\u001b[43m:\u001b[49m\u001b[43m \u001b[49m\u001b[43mmessages\u001b[49m\u001b[43m,\u001b[49m\n\u001b[32m    930\u001b[39m \u001b[43m                \u001b[49m\u001b[33;43m\"\u001b[39;49m\u001b[33;43mmodel\u001b[39;49m\u001b[33;43m\"\u001b[39;49m\u001b[43m:\u001b[49m\u001b[43m \u001b[49m\u001b[43mmodel\u001b[49m\u001b[43m,\u001b[49m\n\u001b[32m    931\u001b[39m \u001b[43m                \u001b[49m\u001b[33;43m\"\u001b[39;49m\u001b[33;43maudio\u001b[39;49m\u001b[33;43m\"\u001b[39;49m\u001b[43m:\u001b[49m\u001b[43m \u001b[49m\u001b[43maudio\u001b[49m\u001b[43m,\u001b[49m\n\u001b[32m    932\u001b[39m \u001b[43m                \u001b[49m\u001b[33;43m\"\u001b[39;49m\u001b[33;43mfrequency_penalty\u001b[39;49m\u001b[33;43m\"\u001b[39;49m\u001b[43m:\u001b[49m\u001b[43m \u001b[49m\u001b[43mfrequency_penalty\u001b[49m\u001b[43m,\u001b[49m\n\u001b[32m    933\u001b[39m \u001b[43m                \u001b[49m\u001b[33;43m\"\u001b[39;49m\u001b[33;43mfunction_call\u001b[39;49m\u001b[33;43m\"\u001b[39;49m\u001b[43m:\u001b[49m\u001b[43m \u001b[49m\u001b[43mfunction_call\u001b[49m\u001b[43m,\u001b[49m\n\u001b[32m    934\u001b[39m \u001b[43m                \u001b[49m\u001b[33;43m\"\u001b[39;49m\u001b[33;43mfunctions\u001b[39;49m\u001b[33;43m\"\u001b[39;49m\u001b[43m:\u001b[49m\u001b[43m \u001b[49m\u001b[43mfunctions\u001b[49m\u001b[43m,\u001b[49m\n\u001b[32m    935\u001b[39m \u001b[43m                \u001b[49m\u001b[33;43m\"\u001b[39;49m\u001b[33;43mlogit_bias\u001b[39;49m\u001b[33;43m\"\u001b[39;49m\u001b[43m:\u001b[49m\u001b[43m \u001b[49m\u001b[43mlogit_bias\u001b[49m\u001b[43m,\u001b[49m\n\u001b[32m    936\u001b[39m \u001b[43m                \u001b[49m\u001b[33;43m\"\u001b[39;49m\u001b[33;43mlogprobs\u001b[39;49m\u001b[33;43m\"\u001b[39;49m\u001b[43m:\u001b[49m\u001b[43m \u001b[49m\u001b[43mlogprobs\u001b[49m\u001b[43m,\u001b[49m\n\u001b[32m    937\u001b[39m \u001b[43m                \u001b[49m\u001b[33;43m\"\u001b[39;49m\u001b[33;43mmax_completion_tokens\u001b[39;49m\u001b[33;43m\"\u001b[39;49m\u001b[43m:\u001b[49m\u001b[43m \u001b[49m\u001b[43mmax_completion_tokens\u001b[49m\u001b[43m,\u001b[49m\n\u001b[32m    938\u001b[39m \u001b[43m                \u001b[49m\u001b[33;43m\"\u001b[39;49m\u001b[33;43mmax_tokens\u001b[39;49m\u001b[33;43m\"\u001b[39;49m\u001b[43m:\u001b[49m\u001b[43m \u001b[49m\u001b[43mmax_tokens\u001b[49m\u001b[43m,\u001b[49m\n\u001b[32m    939\u001b[39m \u001b[43m                \u001b[49m\u001b[33;43m\"\u001b[39;49m\u001b[33;43mmetadata\u001b[39;49m\u001b[33;43m\"\u001b[39;49m\u001b[43m:\u001b[49m\u001b[43m \u001b[49m\u001b[43mmetadata\u001b[49m\u001b[43m,\u001b[49m\n\u001b[32m    940\u001b[39m \u001b[43m                \u001b[49m\u001b[33;43m\"\u001b[39;49m\u001b[33;43mmodalities\u001b[39;49m\u001b[33;43m\"\u001b[39;49m\u001b[43m:\u001b[49m\u001b[43m \u001b[49m\u001b[43mmodalities\u001b[49m\u001b[43m,\u001b[49m\n\u001b[32m    941\u001b[39m \u001b[43m                \u001b[49m\u001b[33;43m\"\u001b[39;49m\u001b[33;43mn\u001b[39;49m\u001b[33;43m\"\u001b[39;49m\u001b[43m:\u001b[49m\u001b[43m \u001b[49m\u001b[43mn\u001b[49m\u001b[43m,\u001b[49m\n\u001b[32m    942\u001b[39m \u001b[43m                \u001b[49m\u001b[33;43m\"\u001b[39;49m\u001b[33;43mparallel_tool_calls\u001b[39;49m\u001b[33;43m\"\u001b[39;49m\u001b[43m:\u001b[49m\u001b[43m \u001b[49m\u001b[43mparallel_tool_calls\u001b[49m\u001b[43m,\u001b[49m\n\u001b[32m    943\u001b[39m \u001b[43m                \u001b[49m\u001b[33;43m\"\u001b[39;49m\u001b[33;43mprediction\u001b[39;49m\u001b[33;43m\"\u001b[39;49m\u001b[43m:\u001b[49m\u001b[43m \u001b[49m\u001b[43mprediction\u001b[49m\u001b[43m,\u001b[49m\n\u001b[32m    944\u001b[39m \u001b[43m                \u001b[49m\u001b[33;43m\"\u001b[39;49m\u001b[33;43mpresence_penalty\u001b[39;49m\u001b[33;43m\"\u001b[39;49m\u001b[43m:\u001b[49m\u001b[43m \u001b[49m\u001b[43mpresence_penalty\u001b[49m\u001b[43m,\u001b[49m\n\u001b[32m    945\u001b[39m \u001b[43m                \u001b[49m\u001b[33;43m\"\u001b[39;49m\u001b[33;43mreasoning_effort\u001b[39;49m\u001b[33;43m\"\u001b[39;49m\u001b[43m:\u001b[49m\u001b[43m \u001b[49m\u001b[43mreasoning_effort\u001b[49m\u001b[43m,\u001b[49m\n\u001b[32m    946\u001b[39m \u001b[43m                \u001b[49m\u001b[33;43m\"\u001b[39;49m\u001b[33;43mresponse_format\u001b[39;49m\u001b[33;43m\"\u001b[39;49m\u001b[43m:\u001b[49m\u001b[43m \u001b[49m\u001b[43mresponse_format\u001b[49m\u001b[43m,\u001b[49m\n\u001b[32m    947\u001b[39m \u001b[43m                \u001b[49m\u001b[33;43m\"\u001b[39;49m\u001b[33;43mseed\u001b[39;49m\u001b[33;43m\"\u001b[39;49m\u001b[43m:\u001b[49m\u001b[43m \u001b[49m\u001b[43mseed\u001b[49m\u001b[43m,\u001b[49m\n\u001b[32m    948\u001b[39m \u001b[43m                \u001b[49m\u001b[33;43m\"\u001b[39;49m\u001b[33;43mservice_tier\u001b[39;49m\u001b[33;43m\"\u001b[39;49m\u001b[43m:\u001b[49m\u001b[43m \u001b[49m\u001b[43mservice_tier\u001b[49m\u001b[43m,\u001b[49m\n\u001b[32m    949\u001b[39m \u001b[43m                \u001b[49m\u001b[33;43m\"\u001b[39;49m\u001b[33;43mstop\u001b[39;49m\u001b[33;43m\"\u001b[39;49m\u001b[43m:\u001b[49m\u001b[43m \u001b[49m\u001b[43mstop\u001b[49m\u001b[43m,\u001b[49m\n\u001b[32m    950\u001b[39m \u001b[43m                \u001b[49m\u001b[33;43m\"\u001b[39;49m\u001b[33;43mstore\u001b[39;49m\u001b[33;43m\"\u001b[39;49m\u001b[43m:\u001b[49m\u001b[43m \u001b[49m\u001b[43mstore\u001b[49m\u001b[43m,\u001b[49m\n\u001b[32m    951\u001b[39m \u001b[43m                \u001b[49m\u001b[33;43m\"\u001b[39;49m\u001b[33;43mstream\u001b[39;49m\u001b[33;43m\"\u001b[39;49m\u001b[43m:\u001b[49m\u001b[43m \u001b[49m\u001b[43mstream\u001b[49m\u001b[43m,\u001b[49m\n\u001b[32m    952\u001b[39m \u001b[43m                \u001b[49m\u001b[33;43m\"\u001b[39;49m\u001b[33;43mstream_options\u001b[39;49m\u001b[33;43m\"\u001b[39;49m\u001b[43m:\u001b[49m\u001b[43m \u001b[49m\u001b[43mstream_options\u001b[49m\u001b[43m,\u001b[49m\n\u001b[32m    953\u001b[39m \u001b[43m                \u001b[49m\u001b[33;43m\"\u001b[39;49m\u001b[33;43mtemperature\u001b[39;49m\u001b[33;43m\"\u001b[39;49m\u001b[43m:\u001b[49m\u001b[43m \u001b[49m\u001b[43mtemperature\u001b[49m\u001b[43m,\u001b[49m\n\u001b[32m    954\u001b[39m \u001b[43m                \u001b[49m\u001b[33;43m\"\u001b[39;49m\u001b[33;43mtool_choice\u001b[39;49m\u001b[33;43m\"\u001b[39;49m\u001b[43m:\u001b[49m\u001b[43m \u001b[49m\u001b[43mtool_choice\u001b[49m\u001b[43m,\u001b[49m\n\u001b[32m    955\u001b[39m \u001b[43m                \u001b[49m\u001b[33;43m\"\u001b[39;49m\u001b[33;43mtools\u001b[39;49m\u001b[33;43m\"\u001b[39;49m\u001b[43m:\u001b[49m\u001b[43m \u001b[49m\u001b[43mtools\u001b[49m\u001b[43m,\u001b[49m\n\u001b[32m    956\u001b[39m \u001b[43m                \u001b[49m\u001b[33;43m\"\u001b[39;49m\u001b[33;43mtop_logprobs\u001b[39;49m\u001b[33;43m\"\u001b[39;49m\u001b[43m:\u001b[49m\u001b[43m \u001b[49m\u001b[43mtop_logprobs\u001b[49m\u001b[43m,\u001b[49m\n\u001b[32m    957\u001b[39m \u001b[43m                \u001b[49m\u001b[33;43m\"\u001b[39;49m\u001b[33;43mtop_p\u001b[39;49m\u001b[33;43m\"\u001b[39;49m\u001b[43m:\u001b[49m\u001b[43m \u001b[49m\u001b[43mtop_p\u001b[49m\u001b[43m,\u001b[49m\n\u001b[32m    958\u001b[39m \u001b[43m                \u001b[49m\u001b[33;43m\"\u001b[39;49m\u001b[33;43muser\u001b[39;49m\u001b[33;43m\"\u001b[39;49m\u001b[43m:\u001b[49m\u001b[43m \u001b[49m\u001b[43muser\u001b[49m\u001b[43m,\u001b[49m\n\u001b[32m    959\u001b[39m \u001b[43m                \u001b[49m\u001b[33;43m\"\u001b[39;49m\u001b[33;43mweb_search_options\u001b[39;49m\u001b[33;43m\"\u001b[39;49m\u001b[43m:\u001b[49m\u001b[43m \u001b[49m\u001b[43mweb_search_options\u001b[49m\u001b[43m,\u001b[49m\n\u001b[32m    960\u001b[39m \u001b[43m            \u001b[49m\u001b[43m}\u001b[49m\u001b[43m,\u001b[49m\n\u001b[32m    961\u001b[39m \u001b[43m            \u001b[49m\u001b[43mcompletion_create_params\u001b[49m\u001b[43m.\u001b[49m\u001b[43mCompletionCreateParamsStreaming\u001b[49m\n\u001b[32m    962\u001b[39m \u001b[43m            \u001b[49m\u001b[38;5;28;43;01mif\u001b[39;49;00m\u001b[43m \u001b[49m\u001b[43mstream\u001b[49m\n\u001b[32m    963\u001b[39m \u001b[43m            \u001b[49m\u001b[38;5;28;43;01melse\u001b[39;49;00m\u001b[43m \u001b[49m\u001b[43mcompletion_create_params\u001b[49m\u001b[43m.\u001b[49m\u001b[43mCompletionCreateParamsNonStreaming\u001b[49m\u001b[43m,\u001b[49m\n\u001b[32m    964\u001b[39m \u001b[43m        \u001b[49m\u001b[43m)\u001b[49m\u001b[43m,\u001b[49m\n\u001b[32m    965\u001b[39m \u001b[43m        \u001b[49m\u001b[43moptions\u001b[49m\u001b[43m=\u001b[49m\u001b[43mmake_request_options\u001b[49m\u001b[43m(\u001b[49m\n\u001b[32m    966\u001b[39m \u001b[43m            \u001b[49m\u001b[43mextra_headers\u001b[49m\u001b[43m=\u001b[49m\u001b[43mextra_headers\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[43mextra_query\u001b[49m\u001b[43m=\u001b[49m\u001b[43mextra_query\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[43mextra_body\u001b[49m\u001b[43m=\u001b[49m\u001b[43mextra_body\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[43mtimeout\u001b[49m\u001b[43m=\u001b[49m\u001b[43mtimeout\u001b[49m\n\u001b[32m    967\u001b[39m \u001b[43m        \u001b[49m\u001b[43m)\u001b[49m\u001b[43m,\u001b[49m\n\u001b[32m    968\u001b[39m \u001b[43m        \u001b[49m\u001b[43mcast_to\u001b[49m\u001b[43m=\u001b[49m\u001b[43mChatCompletion\u001b[49m\u001b[43m,\u001b[49m\n\u001b[32m    969\u001b[39m \u001b[43m        \u001b[49m\u001b[43mstream\u001b[49m\u001b[43m=\u001b[49m\u001b[43mstream\u001b[49m\u001b[43m \u001b[49m\u001b[38;5;129;43;01mor\u001b[39;49;00m\u001b[43m \u001b[49m\u001b[38;5;28;43;01mFalse\u001b[39;49;00m\u001b[43m,\u001b[49m\n\u001b[32m    970\u001b[39m \u001b[43m        \u001b[49m\u001b[43mstream_cls\u001b[49m\u001b[43m=\u001b[49m\u001b[43mStream\u001b[49m\u001b[43m[\u001b[49m\u001b[43mChatCompletionChunk\u001b[49m\u001b[43m]\u001b[49m\u001b[43m,\u001b[49m\n\u001b[32m    971\u001b[39m \u001b[43m    \u001b[49m\u001b[43m)\u001b[49m\n",
      "\u001b[36mFile \u001b[39m\u001b[32mc:\\Users\\haoma\\source\\repos\\ai-agent\\agents\\.venv\\Lib\\site-packages\\openai\\_base_client.py:1249\u001b[39m, in \u001b[36mSyncAPIClient.post\u001b[39m\u001b[34m(self, path, cast_to, body, options, files, stream, stream_cls)\u001b[39m\n\u001b[32m   1235\u001b[39m \u001b[38;5;28;01mdef\u001b[39;00m\u001b[38;5;250m \u001b[39m\u001b[34mpost\u001b[39m(\n\u001b[32m   1236\u001b[39m     \u001b[38;5;28mself\u001b[39m,\n\u001b[32m   1237\u001b[39m     path: \u001b[38;5;28mstr\u001b[39m,\n\u001b[32m   (...)\u001b[39m\u001b[32m   1244\u001b[39m     stream_cls: \u001b[38;5;28mtype\u001b[39m[_StreamT] | \u001b[38;5;28;01mNone\u001b[39;00m = \u001b[38;5;28;01mNone\u001b[39;00m,\n\u001b[32m   1245\u001b[39m ) -> ResponseT | _StreamT:\n\u001b[32m   1246\u001b[39m     opts = FinalRequestOptions.construct(\n\u001b[32m   1247\u001b[39m         method=\u001b[33m\"\u001b[39m\u001b[33mpost\u001b[39m\u001b[33m\"\u001b[39m, url=path, json_data=body, files=to_httpx_files(files), **options\n\u001b[32m   1248\u001b[39m     )\n\u001b[32m-> \u001b[39m\u001b[32m1249\u001b[39m     \u001b[38;5;28;01mreturn\u001b[39;00m cast(ResponseT, \u001b[38;5;28;43mself\u001b[39;49m\u001b[43m.\u001b[49m\u001b[43mrequest\u001b[49m\u001b[43m(\u001b[49m\u001b[43mcast_to\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[43mopts\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[43mstream\u001b[49m\u001b[43m=\u001b[49m\u001b[43mstream\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[43mstream_cls\u001b[49m\u001b[43m=\u001b[49m\u001b[43mstream_cls\u001b[49m\u001b[43m)\u001b[49m)\n",
      "\u001b[36mFile \u001b[39m\u001b[32mc:\\Users\\haoma\\source\\repos\\ai-agent\\agents\\.venv\\Lib\\site-packages\\openai\\_base_client.py:1037\u001b[39m, in \u001b[36mSyncAPIClient.request\u001b[39m\u001b[34m(self, cast_to, options, stream, stream_cls)\u001b[39m\n\u001b[32m   1034\u001b[39m             err.response.read()\n\u001b[32m   1036\u001b[39m         log.debug(\u001b[33m\"\u001b[39m\u001b[33mRe-raising status error\u001b[39m\u001b[33m\"\u001b[39m)\n\u001b[32m-> \u001b[39m\u001b[32m1037\u001b[39m         \u001b[38;5;28;01mraise\u001b[39;00m \u001b[38;5;28mself\u001b[39m._make_status_error_from_response(err.response) \u001b[38;5;28;01mfrom\u001b[39;00m\u001b[38;5;250m \u001b[39m\u001b[38;5;28;01mNone\u001b[39;00m\n\u001b[32m   1039\u001b[39m     \u001b[38;5;28;01mbreak\u001b[39;00m\n\u001b[32m   1041\u001b[39m \u001b[38;5;28;01massert\u001b[39;00m response \u001b[38;5;129;01mis\u001b[39;00m \u001b[38;5;129;01mnot\u001b[39;00m \u001b[38;5;28;01mNone\u001b[39;00m, \u001b[33m\"\u001b[39m\u001b[33mcould not resolve response (should never happen)\u001b[39m\u001b[33m\"\u001b[39m\n",
      "\u001b[31mPermissionDeniedError\u001b[39m: Error code: 403 - {'error': 'This authentication method does not have sufficient permissions to call Inference Providers on behalf of user haomd2'}"
     ]
    }
   ],
   "source": [
    "# The API we know well\n",
    "# I've updated this with the latest model, but it can take some time because it likes to think!\n",
    "# Replace the model with gpt-4.1-mini if you'd prefer not to wait 1-2 mins\n",
    "\n",
    "completion = client.chat.completions.create(\n",
    "    model=\"Qwen/Qwen3-8B\",\n",
    "    messages=[\n",
    "        {\n",
    "            \"role\": \"user\",\n",
    "            \"content\": \"What is the capital of France?\"\n",
    "        }\n",
    "    ],\n",
    ")\n",
    "answer = completion.choices[0].message.content\n",
    "\n",
    "display(Markdown(answer))\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "# Anthropic has a slightly different API, and Max Tokens is required\n",
    "\n",
    "model_name = \"claude-sonnet-4-5\"\n",
    "\n",
    "claude = Anthropic()\n",
    "response = claude.messages.create(model=model_name, messages=messages, max_tokens=1000)\n",
    "answer = response.content[0].text\n",
    "\n",
    "display(Markdown(answer))\n",
    "competitors.append(model_name)\n",
    "answers.append(answer)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "gemini = OpenAI(api_key=google_api_key, base_url=\"https://generativelanguage.googleapis.com/v1beta/openai/\")\n",
    "model_name = \"gemini-2.5-flash\"\n",
    "\n",
    "response = gemini.chat.completions.create(model=model_name, messages=messages)\n",
    "answer = response.choices[0].message.content\n",
    "\n",
    "display(Markdown(answer))\n",
    "competitors.append(model_name)\n",
    "answers.append(answer)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "deepseek = OpenAI(api_key=deepseek_api_key, base_url=\"https://api.deepseek.com/v1\")\n",
    "model_name = \"deepseek-chat\"\n",
    "\n",
    "response = deepseek.chat.completions.create(model=model_name, messages=messages)\n",
    "answer = response.choices[0].message.content\n",
    "\n",
    "display(Markdown(answer))\n",
    "competitors.append(model_name)\n",
    "answers.append(answer)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "# Updated with the latest Open Source model from OpenAI\n",
    "\n",
    "groq = OpenAI(api_key=groq_api_key, base_url=\"https://api.groq.com/openai/v1\")\n",
    "model_name = \"openai/gpt-oss-120b\"\n",
    "\n",
    "response = groq.chat.completions.create(model=model_name, messages=messages)\n",
    "answer = response.choices[0].message.content\n",
    "\n",
    "display(Markdown(answer))\n",
    "competitors.append(model_name)\n",
    "answers.append(answer)\n"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## For the next cell, we will use Ollama\n",
    "\n",
    "Ollama runs a local web service that gives an OpenAI compatible endpoint,  \n",
    "and runs models locally using high performance C++ code.\n",
    "\n",
    "If you don't have Ollama, install it here by visiting https://ollama.com then pressing Download and following the instructions.\n",
    "\n",
    "After it's installed, you should be able to visit here: http://localhost:11434 and see the message \"Ollama is running\"\n",
    "\n",
    "You might need to restart Cursor (and maybe reboot). Then open a Terminal (control+\\`) and run `ollama serve`\n",
    "\n",
    "Useful Ollama commands (run these in the terminal, or with an exclamation mark in this notebook):\n",
    "\n",
    "`ollama pull <model_name>` downloads a model locally  \n",
    "`ollama ls` lists all the models you've downloaded  \n",
    "`ollama rm <model_name>` deletes the specified model from your downloads"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "<table style=\"margin: 0; text-align: left; width:100%\">\n",
    "    <tr>\n",
    "        <td style=\"width: 150px; height: 150px; vertical-align: middle;\">\n",
    "            <img src=\"../assets/stop.png\" width=\"150\" height=\"150\" style=\"display: block;\" />\n",
    "        </td>\n",
    "        <td>\n",
    "            <h2 style=\"color:#ff7800;\">Super important - ignore me at your peril!</h2>\n",
    "            <span style=\"color:#ff7800;\">The model called <b>llama3.3</b> is FAR too large for home computers - it's not intended for personal computing and will consume all your resources! Stick with the nicely sized <b>llama3.2</b> or <b>llama3.2:1b</b> and if you want larger, try llama3.1 or smaller variants of Qwen, Gemma, Phi or DeepSeek. See the <A href=\"https://ollama.com/models\">the Ollama models page</a> for a full list of models and sizes.\n",
    "            </span>\n",
    "        </td>\n",
    "    </tr>\n",
    "</table>"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "!ollama pull llama3.2"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "ollama = OpenAI(base_url='http://localhost:11434/v1', api_key='ollama')\n",
    "model_name = \"llama3.2\"\n",
    "\n",
    "response = ollama.chat.completions.create(model=model_name, messages=messages)\n",
    "answer = response.choices[0].message.content\n",
    "\n",
    "display(Markdown(answer))\n",
    "competitors.append(model_name)\n",
    "answers.append(answer)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "# So where are we?\n",
    "\n",
    "print(competitors)\n",
    "print(answers)\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "# It's nice to know how to use \"zip\"\n",
    "for competitor, answer in zip(competitors, answers):\n",
    "    print(f\"Competitor: {competitor}\\n\\n{answer}\")\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "# Let's bring this together - note the use of \"enumerate\"\n",
    "\n",
    "together = \"\"\n",
    "for index, answer in enumerate(answers):\n",
    "    together += f\"# Response from competitor {index+1}\\n\\n\"\n",
    "    together += answer + \"\\n\\n\""
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "print(together)"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": []
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "judge = f\"\"\"You are judging a competition between {len(competitors)} competitors.\n",
    "Each model has been given this question:\n",
    "\n",
    "{question}\n",
    "\n",
    "Your job is to evaluate each response for clarity and strength of argument, and rank them in order of best to worst.\n",
    "Respond with JSON, and only JSON, with the following format:\n",
    "{{\"results\": [\"best competitor number\", \"second best competitor number\", \"third best competitor number\", ...]}}\n",
    "\n",
    "Here are the responses from each competitor:\n",
    "\n",
    "{together}\n",
    "\n",
    "Now respond with the JSON with the ranked order of the competitors, nothing else. Do not include markdown formatting or code blocks.\"\"\"\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "print(judge)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "judge_messages = [{\"role\": \"user\", \"content\": judge}]"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "# Judgement time!\n",
    "\n",
    "openai = OpenAI()\n",
    "response = openai.chat.completions.create(\n",
    "    model=\"gpt-5-mini\",\n",
    "    messages=judge_messages,\n",
    ")\n",
    "results = response.choices[0].message.content\n",
    "print(results)\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "# OK let's turn this into results!\n",
    "\n",
    "results_dict = json.loads(results)\n",
    "ranks = results_dict[\"results\"]\n",
    "for index, result in enumerate(ranks):\n",
    "    competitor = competitors[int(result)-1]\n",
    "    print(f\"Rank {index+1}: {competitor}\")"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "<table style=\"margin: 0; text-align: left; width:100%\">\n",
    "    <tr>\n",
    "        <td style=\"width: 150px; height: 150px; vertical-align: middle;\">\n",
    "            <img src=\"../assets/exercise.png\" width=\"150\" height=\"150\" style=\"display: block;\" />\n",
    "        </td>\n",
    "        <td>\n",
    "            <h2 style=\"color:#ff7800;\">Exercise</h2>\n",
    "            <span style=\"color:#ff7800;\">Which pattern(s) did this use? Try updating this to add another Agentic design pattern.\n",
    "            </span>\n",
    "        </td>\n",
    "    </tr>\n",
    "</table>"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "<table style=\"margin: 0; text-align: left; width:100%\">\n",
    "    <tr>\n",
    "        <td style=\"width: 150px; height: 150px; vertical-align: middle;\">\n",
    "            <img src=\"../assets/business.png\" width=\"150\" height=\"150\" style=\"display: block;\" />\n",
    "        </td>\n",
    "        <td>\n",
    "            <h2 style=\"color:#00bfff;\">Commercial implications</h2>\n",
    "            <span style=\"color:#00bfff;\">These kinds of patterns - to send a task to multiple models, and evaluate results,\n",
    "            are common where you need to improve the quality of your LLM response. This approach can be universally applied\n",
    "            to business projects where accuracy is critical.\n",
    "            </span>\n",
    "        </td>\n",
    "    </tr>\n",
    "</table>"
   ]
  }
 ],
 "metadata": {
  "kernelspec": {
   "display_name": ".venv",
   "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": "3.12.12"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 2
}