Delete 2_lab2.ipynb

2_lab2.ipynb

@@ -1,474 +0,0 @@
-{
- "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": 1,
-   "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": null,
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "# Always remember to do this!\n",
-    "load_dotenv(override=True)"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": null,
-   "metadata": {},
-   "outputs": [],
-   "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)\")"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 4,
-   "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.\"\n",
-    "messages = [{\"role\": \"user\", \"content\": request}]"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": null,
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "messages"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": null,
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "openai = OpenAI()\n",
-    "response = openai.chat.completions.create(\n",
-    "    model=\"gpt-4o-mini\",\n",
-    "    messages=messages,\n",
-    ")\n",
-    "question = response.choices[0].message.content\n",
-    "print(question)\n"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 7,
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "competitors = []\n",
-    "answers = []\n",
-    "messages = [{\"role\": \"user\", \"content\": question}]"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": null,
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "# The API we know well\n",
-    "\n",
-    "model_name = \"gpt-4o-mini\"\n",
-    "\n",
-    "response = openai.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": [
-    "# Anthropic has a slightly different API, and Max Tokens is required\n",
-    "\n",
-    "model_name = \"claude-3-7-sonnet-latest\"\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-2.0-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": [
-    "groq = OpenAI(api_key=groq_api_key, base_url=\"https://api.groq.com/openai/v1\")\n",
-    "model_name = \"llama-3.3-70b-versatile\"\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": 20,
-   "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": "code",
-   "execution_count": 22,
-   "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": 29,
-   "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=\"o3-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": "3.12.9"
-  }
- },
- "nbformat": 4,
- "nbformat_minor": 2
-}