two new community contribution templates for AI client usage and a multi-model chatbot debate

week1/community-contributions/api_client_template_snarky/api_client_template_snarky.ipynb

@@ -0,0 +1,250 @@
+{
+ "cells": [
+  {
+   "cell_type": "markdown",
+   "id": "d15d8294-3328-4e07-ad16-8a03e9bbfdb9",
+   "metadata": {},
+   "source": [
+    "# AI Client Template\n",
+    "This is a generic template for calling an AI of your choice, selected in .env's API_NAME\n",
+    "\n",
+    "# Connecting to AI\n",
+    "\n",
+    "The next cell is where we load in the environment variables in your `.env` file and connect to OpenAI.  \n",
+    "\n",
+    "Enter the credentials including the base URL, API Key, and model of your favorite AI APIs in your .env file\n",
+    "\n",
+    "For example,\n",
+    "\n",
+    "```\n",
+    "OPENAI_API_KEY=<your OPENAI api key>\n",
+    "OPENAI_BASE_URL=https://api.openai.com/v1/\n",
+    "OPENAI_MODEL=gpt-5-nano\n",
+    "\n",
+    "OLLAMA_API_KEY=ollama\n",
+    "OLLAMA_BASE_URL=http://localhost:11434/v1\n",
+    "OLLAMA_MODEL=llama3.2\n",
+    "\n",
+    "GEMINI_API_KEY=<your GEMINI api key>\n",
+    "GEMINI_MODEL=gpt-5-nano\n",
+    "GEMINI_BASE_URL=\n",
+    "\n",
+    "DEFAULT_API=OPENAI\n",
+    "```\n",
+    "\n",
+    "If you'd like to use free Ollama, select API_NAME=OLLAMA\n",
+    "If you'd like to use OpenAI, select API_NAME=OPENAI\n",
+    "\n",
+    "## troubleshooting\n",
+    "\n",
+    "Please see the [troubleshooting](../setup/troubleshooting.ipynb) notebook in the setup folder to diagnose and fix common problems. At the very end of it is a diagnostics script with some useful debug info.\n",
+    "\n"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 9,
+   "id": "4e2a9393-7767-488e-a8bf-27c12dca35bd",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# imports\n",
+    "\n",
+    "import os\n",
+    "from dotenv import load_dotenv\n",
+    "from IPython.display import Markdown, display\n",
+    "from openai import OpenAI\n",
+    "\n",
+    "# If you get an error running this cell, then please head over to the troubleshooting notebook!"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 10,
+   "id": "7b87cadb-d513-4303-baee-a37b6f938e4d",
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "Using OPENAI\n",
+      "API key found!\n",
+      "Model: gpt-5-nano\n",
+      "Base URL: https://api.openai.com/v1/\n"
+     ]
+    }
+   ],
+   "source": [
+    "# Load environment variables in a file called .env and initialize api_client\n",
+    "\n",
+    "load_dotenv(override=True)\n",
+    "api_name = os.getenv('DEFAULT_API')\n",
+    "api_key = os.getenv(api_name + '_API_KEY')\n",
+    "model = os.getenv(api_name + '_MODEL')\n",
+    "base_url=os.getenv(api_name + '_BASE_URL')\n",
+    "\n",
+    "if not api_name:\n",
+    "    print(\"No API name found\")\n",
+    "else:\n",
+    "    print(f\"Using {api_name}\")\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 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(f\"API key found!\")\n",
+    "\n",
+    "if not model:\n",
+    "    print(\"No model was found - please head over to the troubleshooting notebook in this folder to identify & fix!\")\n",
+    "elif api_key.strip() != api_key:\n",
+    "    print(\"An model 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(f\"Model: {model}\")\n",
+    "\n",
+    "if not base_url:\n",
+    "    print(\"No base url found\")\n",
+    "else:\n",
+    "    print(f\"Base URL: {base_url}\")\n",
+    "\n",
+    "from openai import OpenAI\n",
+    "\n",
+    "\n",
+    "api_client = OpenAI(base_url=base_url, api_key=api_key)\n"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 11,
+   "id": "80ce2d13",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# Helper functions\n",
+    "\n",
+    "def messages(system_prompt, user_prompt):\n",
+    "    return [\n",
+    "        {\"role\": \"system\", \"content\": system_prompt},\n",
+    "        {\"role\": \"user\", \"content\": user_prompt}\n",
+    "    ]\n",
+    "\n",
+    "def get_response(system_prompt, user_prompt):\n",
+    "    response = api_client.chat.completions.create(\n",
+    "        model = model,\n",
+    "        messages = messages(system_prompt, user_prompt)\n",
+    "    )\n",
+    "    assert response is not None, \"could not resolve response (should never happen)\"\n",
+    "    return response.choices[0].message.content\n",
+    "\n",
+    "\n",
+    "def display_response(system_prompt, user_prompt):\n",
+    "    display(Markdown(get_response(system_prompt, user_prompt)))"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "5fa7e13b",
+   "metadata": {},
+   "source": [
+    "# Define system and user prompts\n",
+    "\n",
+    "## Types of prompts\n",
+    "\n",
+    "You may know this already - but if not, you will get very familiar with it!\n",
+    "\n",
+    "Models like GPT have been trained to receive instructions in a particular way.\n",
+    "\n",
+    "They expect to receive:\n",
+    "\n",
+    "**A system prompt** that tells them what task they are performing and what tone they should use\n",
+    "\n",
+    "**A user prompt** -- the conversation starter that they should reply to"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 12,
+   "id": "abdb8417-c5dc-44bc-9bee-2e059d162699",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# Define our system prompt - you can experiment with this later, changing the last sentence to 'Respond in markdown in Spanish.\"\n",
+    "\n",
+    "system_prompt = \"\"\"\n",
+    "You are a snarky AI assistant that always provides short, snarky, humorous responses.\n",
+    "Respond in markdown. Do not wrap the markdown in a code block - respond just with the markdown.\n",
+    "\"\"\""
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 13,
+   "id": "f0275b1b-7cfe-4f9d-abfa-7650d378da0c",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# Define our user prompt\n",
+    "\n",
+    "user_prompt = \"\"\"\n",
+    "Please give me a fun fact about space.\n",
+    "\"\"\""
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 14,
+   "id": "3d926d59-450e-4609-92ba-2d6f244f1342",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# A function to display this nicely in the output, using markdown\n"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 15,
+   "id": "3018853a-445f-41ff-9560-d925d1774b2f",
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/markdown": [
+       "Fun fact: Space isn’t empty—it's a near-perfect vacuum full of particles and radiation. There are more stars in the observable universe than grains of sand on Earth."
+      ],
+      "text/plain": [
+       "<IPython.core.display.Markdown object>"
+      ]
+     },
+     "metadata": {},
+     "output_type": "display_data"
+    }
+   ],
+   "source": [
+    "display_response(user_prompt=user_prompt, system_prompt=system_prompt)"
+   ]
+  }
+ ],
+ "metadata": {
+  "kernelspec": {
+   "display_name": "llm-engineering",
+   "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": "3.12.3"
+  }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 5
+}

week1/community-contributions/api_client_template_snarky/api_client_template_snarky.py

@@ -0,0 +1,131 @@
+"""
+AI Client Template
+This is a generic template for calling an AI of your choice, selected in .env's DEFAULT_API
+
+# Connecting to AI
+
+The next cell is where we load in the environment variables in your `.env` file and connect to OpenAI.  
+
+Enter the credentials including the base URL, API Key, and default_model of your favorite AI APIs in your .env file
+
+For example,
+
+```
+OPENAI_API_KEY=<your OPENAI api key>
+OPENAI_MODEL=gpt-5-nano
+OPENAI_BASE_URL=
+
+GEMINI_API_KEY=<your GEMINI api key>
+GEMINI_MODEL=gpt-5-nano
+GEMINI_BASE_URL=
+
+OLLAMA_API_KEY=ollama
+OLLAMA_BASE_URL=http://localhost:11434/v1
+OLLAMA_MODEL=llama3.2
+
+DEFAULT_API=OLLAMA
+```
+
+If you'd like to use free Ollama, select DEFAULT_API=OLLAMA
+If you'd like to use OpenAI, select DEFAULT_API=OPENAI
+
+## troubleshooting
+
+Please see the [troubleshooting](../setup/troubleshooting.ipynb) notebook in the setup folder to diagnose and fix common problems. At the very end of it is a diagnostics script with some useful debug info.
+"""
+
+# imports
+
+import os
+from urllib import response
+from dotenv import load_dotenv
+from IPython.display import Markdown, display
+from openai import OpenAI
+
+# If you get an error running this cell, then please head over to the troubleshooting notebook!
+
+# Load environment variables in a file called .env and initialize api_client
+
+load_dotenv(override=True)
+default_api = os.getenv('DEFAULT_API')
+default_api_key = os.getenv(default_api + '_API_KEY')
+default_model = os.getenv(default_api + '_MODEL')
+default_base_uri=os.getenv(default_api + '_BASE_URL')
+
+if default_api:
+    print(f"Using {default_api}")
+# Check the key
+
+if not default_api_key:
+    print("No API key was found - please head over to the troubleshooting notebook in this folder to identify & fix!")
+elif default_api_key.strip() != default_api_key:
+    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")
+else:
+    print(f"API key found!")
+
+if not default_model:
+    print("No default_model was found - please head over to the troubleshooting notebook in this folder to identify & fix!")
+elif default_api_key.strip() != default_api_key:
+    print("An default_model was found, but it looks like it might have space or tab characters at the start or end - please remove them - see troubleshooting notebook")
+else:
+    print(f"Model: {default_model}")
+
+if not default_base_uri:
+    print("No base url found")
+else:
+    print(f"Base URL: {default_base_uri}")
+
+from openai import OpenAI
+
+
+api_client = OpenAI(base_url=default_base_uri, api_key=default_api_key)
+
+# Helper functions
+
+def messages(system_prompt, user_prompt):
+    return [
+        {"role": "system", "content": system_prompt},
+        {"role": "user", "content": user_prompt}
+    ]
+
+def get_response(system_prompt, user_prompt):
+    response = api_client.chat.completions.create(
+        model = default_model,
+        messages = messages(system_prompt, user_prompt)
+    )
+    assert response is not None, "could not resolve response (should never happen)"
+    return response.choices[0].message.content
+
+
+"""
+Define system and user prompts
+
+## Types of prompts
+
+You may know this already - but if not, you will get very familiar with it!
+
+Models like GPT have been trained to receive instructions in a particular way.
+
+They expect to receive:
+
+**A system prompt** that tells them what task they are performing and what tone they should use
+
+**A user prompt** -- the conversation starter that they should reply to
+"""
+
+# Define our system prompt - you can experiment with this later, changing the last sentence to 'Respond in markdown in Spanish."
+
+system_prompt = """
+You are a snarky AI assistant that always provides short, snarky, humorous responses.
+Respond in markdown. Do not wrap the markdown in a code block - respond just with the markdown.
+"""
+
+# Define our user prompt
+
+user_prompt = """
+Please give me a fun fact about space.
+"""
+
+# A function to display this nicely in the output, using markdown
+
+print(get_response(system_prompt=system_prompt, user_prompt=user_prompt))

week1/community-contributions/api_client_template_snarky/sample.env

@@ -0,0 +1,9 @@
+OPENAI_API_KEY=<your_openai_api_key_here>
+OPENAI_BASE_URL=https://api.openai.com/v1/
+OPENAI_MODEL=gpt-5-nano
+
+OLLAMA_API_KEY=ollama
+OLLAMA_BASE_URL=http://localhost:11434/v1
+OLLAMA_MODEL=llama3.2:latest
+
+DEFAULT_API=OLLAMA