481 lines
16 KiB
Plaintext
481 lines
16 KiB
Plaintext
{
|
|
"cells": [
|
|
{
|
|
"cell_type": "markdown",
|
|
"id": "ddfa9ae6-69fe-444a-b994-8c4c5970a7ec",
|
|
"metadata": {},
|
|
"source": [
|
|
"# Project - Airline AI Assistant\n",
|
|
"\n",
|
|
"We'll now bring together what we've learned to make an AI Customer Support assistant for an Airline"
|
|
]
|
|
},
|
|
{
|
|
"cell_type": "code",
|
|
"execution_count": null,
|
|
"id": "8b50bbe2-c0b1-49c3-9a5c-1ba7efa2bcb4",
|
|
"metadata": {},
|
|
"outputs": [],
|
|
"source": [
|
|
"# imports\n",
|
|
"\n",
|
|
"import os\n",
|
|
"import json\n",
|
|
"from dotenv import load_dotenv\n",
|
|
"from openai import OpenAI\n",
|
|
"import gradio as gr"
|
|
]
|
|
},
|
|
{
|
|
"cell_type": "code",
|
|
"execution_count": null,
|
|
"id": "747e8786-9da8-4342-b6c9-f5f69c2e22ae",
|
|
"metadata": {},
|
|
"outputs": [],
|
|
"source": [
|
|
"# Initialization\n",
|
|
"\n",
|
|
"load_dotenv()\n",
|
|
"os.environ['OPENAI_API_KEY'] = os.getenv('OPENAI_API_KEY', 'your-key-if-not-using-env')\n",
|
|
"MODEL = \"gpt-4o-mini\"\n",
|
|
"openai = OpenAI()"
|
|
]
|
|
},
|
|
{
|
|
"cell_type": "code",
|
|
"execution_count": null,
|
|
"id": "0a521d84-d07c-49ab-a0df-d6451499ed97",
|
|
"metadata": {},
|
|
"outputs": [],
|
|
"source": [
|
|
"system_message = \"You are a helpful assistant for an Airline called FlightAI. \"\n",
|
|
"system_message += \"Give short, courteous answers, no more than 1 sentence. \"\n",
|
|
"system_message += \"Always be accurate. If you don't know the answer, say so.\""
|
|
]
|
|
},
|
|
{
|
|
"cell_type": "code",
|
|
"execution_count": null,
|
|
"id": "61a2a15d-b559-4844-b377-6bd5cb4949f6",
|
|
"metadata": {},
|
|
"outputs": [],
|
|
"source": [
|
|
"def chat(message, history):\n",
|
|
" messages = [{\"role\": \"system\", \"content\": system_message}]\n",
|
|
" for human, assistant in history:\n",
|
|
" messages.append({\"role\": \"user\", \"content\": human})\n",
|
|
" messages.append({\"role\": \"assistant\", \"content\": assistant})\n",
|
|
" messages.append({\"role\": \"user\", \"content\": message})\n",
|
|
" response = openai.chat.completions.create(model=MODEL, messages=messages)\n",
|
|
" return response.choices[0].message.content\n",
|
|
"\n",
|
|
"gr.ChatInterface(fn=chat).launch()"
|
|
]
|
|
},
|
|
{
|
|
"cell_type": "markdown",
|
|
"id": "36bedabf-a0a7-4985-ad8e-07ed6a55a3a4",
|
|
"metadata": {},
|
|
"source": [
|
|
"## Tools\n",
|
|
"\n",
|
|
"Tools are an incredibly powerful feature provided by the frontier LLMs.\n",
|
|
"\n",
|
|
"With tools, you can write a function, and have the LLM call that function as part of its response.\n",
|
|
"\n",
|
|
"Sounds almost spooky.. we're giving it the power to run code on our machine?\n",
|
|
"\n",
|
|
"Well, kinda."
|
|
]
|
|
},
|
|
{
|
|
"cell_type": "code",
|
|
"execution_count": null,
|
|
"id": "0696acb1-0b05-4dc2-80d5-771be04f1fb2",
|
|
"metadata": {},
|
|
"outputs": [],
|
|
"source": [
|
|
"# Let's start by making a useful function\n",
|
|
"\n",
|
|
"ticket_prices = {\"london\": \"$799\", \"paris\": \"$899\", \"tokyo\": \"$1400\", \"berlin\": \"$499\"}\n",
|
|
"\n",
|
|
"def get_ticket_price(destination_city):\n",
|
|
" print(f\"Tool get_ticket_price called for {destination_city}\")\n",
|
|
" city = destination_city.lower()\n",
|
|
" return ticket_prices.get(city, \"Unknown\")"
|
|
]
|
|
},
|
|
{
|
|
"cell_type": "code",
|
|
"execution_count": null,
|
|
"id": "80ca4e09-6287-4d3f-997d-fa6afbcf6c85",
|
|
"metadata": {},
|
|
"outputs": [],
|
|
"source": [
|
|
"get_ticket_price(\"London\")"
|
|
]
|
|
},
|
|
{
|
|
"cell_type": "code",
|
|
"execution_count": null,
|
|
"id": "4afceded-7178-4c05-8fa6-9f2085e6a344",
|
|
"metadata": {},
|
|
"outputs": [],
|
|
"source": [
|
|
"# There's a particular dictionary structure that's required to describe our function:\n",
|
|
"\n",
|
|
"price_function = {\n",
|
|
" \"name\": \"get_ticket_price\",\n",
|
|
" \"description\": \"Get the price of a return ticket to the destination city. Call this whenever you need to know the ticket price, for example when a customer asks 'How much is a ticket to this city'\",\n",
|
|
" \"parameters\": {\n",
|
|
" \"type\": \"object\",\n",
|
|
" \"properties\": {\n",
|
|
" \"destination_city\": {\n",
|
|
" \"type\": \"string\",\n",
|
|
" \"description\": \"The city that the customer wants to travel to\",\n",
|
|
" },\n",
|
|
" },\n",
|
|
" \"required\": [\"destination_city\"],\n",
|
|
" \"additionalProperties\": False\n",
|
|
" }\n",
|
|
"}"
|
|
]
|
|
},
|
|
{
|
|
"cell_type": "code",
|
|
"execution_count": null,
|
|
"id": "bdca8679-935f-4e7f-97e6-e71a4d4f228c",
|
|
"metadata": {},
|
|
"outputs": [],
|
|
"source": [
|
|
"# And this is included in a list of tools:\n",
|
|
"\n",
|
|
"tools = [{\"type\": \"function\", \"function\": price_function}]"
|
|
]
|
|
},
|
|
{
|
|
"cell_type": "markdown",
|
|
"id": "c3d3554f-b4e3-4ce7-af6f-68faa6dd2340",
|
|
"metadata": {},
|
|
"source": [
|
|
"## Getting OpenAI to use our Tool\n",
|
|
"\n",
|
|
"There's some fiddly stuff to allow OpenAI \"to call our tool\"\n",
|
|
"\n",
|
|
"What we actually do is give the LLM the opportunity to inform us that it wants us to run the tool.\n",
|
|
"\n",
|
|
"Here's how the new chat function looks:"
|
|
]
|
|
},
|
|
{
|
|
"cell_type": "code",
|
|
"execution_count": null,
|
|
"id": "ce9b0744-9c78-408d-b9df-9f6fd9ed78cf",
|
|
"metadata": {},
|
|
"outputs": [],
|
|
"source": [
|
|
"def chat(message, history):\n",
|
|
" messages = [{\"role\": \"system\", \"content\": system_message}]\n",
|
|
" for human, assistant in history:\n",
|
|
" messages.append({\"role\": \"user\", \"content\": human})\n",
|
|
" messages.append({\"role\": \"assistant\", \"content\": assistant})\n",
|
|
" messages.append({\"role\": \"user\", \"content\": message})\n",
|
|
" response = openai.chat.completions.create(model=MODEL, messages=messages, tools=tools)\n",
|
|
"\n",
|
|
" if response.choices[0].finish_reason==\"tool_calls\":\n",
|
|
" message = response.choices[0].message\n",
|
|
" response, city = handle_tool_call(message)\n",
|
|
" messages.append(message)\n",
|
|
" messages.append(response)\n",
|
|
" response = openai.chat.completions.create(model=MODEL, messages=messages)\n",
|
|
" \n",
|
|
" return response.choices[0].message.content"
|
|
]
|
|
},
|
|
{
|
|
"cell_type": "code",
|
|
"execution_count": null,
|
|
"id": "b0992986-ea09-4912-a076-8e5603ee631f",
|
|
"metadata": {},
|
|
"outputs": [],
|
|
"source": [
|
|
"# We have to write that function handle_tool_call:\n",
|
|
"\n",
|
|
"def handle_tool_call(message):\n",
|
|
" tool_call = message.tool_calls[0]\n",
|
|
" arguments = json.loads(tool_call.function.arguments)\n",
|
|
" city = arguments.get('destination_city')\n",
|
|
" price = get_ticket_price(city)\n",
|
|
" response = {\n",
|
|
" \"role\": \"tool\",\n",
|
|
" \"content\": json.dumps({\"destination_city\": city,\"price\": price}),\n",
|
|
" \"tool_call_id\": message.tool_calls[0].id\n",
|
|
" }\n",
|
|
" return response, city"
|
|
]
|
|
},
|
|
{
|
|
"cell_type": "code",
|
|
"execution_count": null,
|
|
"id": "f4be8a71-b19e-4c2f-80df-f59ff2661f14",
|
|
"metadata": {},
|
|
"outputs": [],
|
|
"source": [
|
|
"gr.ChatInterface(fn=chat).launch()"
|
|
]
|
|
},
|
|
{
|
|
"cell_type": "markdown",
|
|
"id": "473e5b39-da8f-4db1-83ae-dbaca2e9531e",
|
|
"metadata": {},
|
|
"source": [
|
|
"# Let's go multi-modal!!\n",
|
|
"\n",
|
|
"We can use DALL-E-3, the image generation model behind GPT-4o, to make us some images\n",
|
|
"\n",
|
|
"Let's put this in a function called artist.\n",
|
|
"\n",
|
|
"### Price alert: each time I generate an image it costs about 4c - don't go crazy with images!"
|
|
]
|
|
},
|
|
{
|
|
"cell_type": "code",
|
|
"execution_count": null,
|
|
"id": "2c27c4ba-8ed5-492f-add1-02ce9c81d34c",
|
|
"metadata": {},
|
|
"outputs": [],
|
|
"source": [
|
|
"# Some imports for handling images\n",
|
|
"\n",
|
|
"import base64\n",
|
|
"from io import BytesIO\n",
|
|
"from PIL import Image"
|
|
]
|
|
},
|
|
{
|
|
"cell_type": "code",
|
|
"execution_count": null,
|
|
"id": "773a9f11-557e-43c9-ad50-56cbec3a0f8f",
|
|
"metadata": {},
|
|
"outputs": [],
|
|
"source": [
|
|
"def artist(city):\n",
|
|
" image_response = openai.images.generate(\n",
|
|
" model=\"dall-e-3\",\n",
|
|
" prompt=f\"An image representing a vacation in {city}, showing tourist spots and everything unique about {city}, in a vibrant pop-art style\",\n",
|
|
" size=\"1024x1024\",\n",
|
|
" n=1,\n",
|
|
" response_format=\"b64_json\",\n",
|
|
" )\n",
|
|
" image_base64 = image_response.data[0].b64_json\n",
|
|
" image_data = base64.b64decode(image_base64)\n",
|
|
" return Image.open(BytesIO(image_data))"
|
|
]
|
|
},
|
|
{
|
|
"cell_type": "code",
|
|
"execution_count": null,
|
|
"id": "d877c453-e7fb-482a-88aa-1a03f976b9e9",
|
|
"metadata": {},
|
|
"outputs": [],
|
|
"source": [
|
|
"image = artist(\"New York City\")\n",
|
|
"display(image)"
|
|
]
|
|
},
|
|
{
|
|
"cell_type": "code",
|
|
"execution_count": null,
|
|
"id": "728a12c5-adc3-415d-bb05-82beb73b079b",
|
|
"metadata": {},
|
|
"outputs": [],
|
|
"source": []
|
|
},
|
|
{
|
|
"cell_type": "markdown",
|
|
"id": "f4975b87-19e9-4ade-a232-9b809ec75c9a",
|
|
"metadata": {},
|
|
"source": [
|
|
"## Audio\n",
|
|
"\n",
|
|
"And let's make a function talker that uses OpenAI's speech model to generate Audio\n",
|
|
"\n",
|
|
"### Troubleshooting Audio issues\n",
|
|
"\n",
|
|
"If you have any problems running this code below (like a FileNotFound error, or a warning of a missing package), you may need to install FFmpeg, a very popular audio utility.\n",
|
|
"\n",
|
|
"**For PC Users**\n",
|
|
"\n",
|
|
"1. Download FFmpeg from the official website: https://ffmpeg.org/download.html\n",
|
|
"\n",
|
|
"2. Extract the downloaded files to a location on your computer (e.g., `C:\\ffmpeg`)\n",
|
|
"\n",
|
|
"3. Add the FFmpeg bin folder to your system PATH:\n",
|
|
"- Right-click on 'This PC' or 'My Computer' and select 'Properties'\n",
|
|
"- Click on 'Advanced system settings'\n",
|
|
"- Click on 'Environment Variables'\n",
|
|
"- Under 'System variables', find and edit 'Path'\n",
|
|
"- Add a new entry with the path to your FFmpeg bin folder (e.g., `C:\\ffmpeg\\bin`)\n",
|
|
"- Restart your command prompt, and within Jupyter Lab do Kernel -> Restart kernel, to pick up the changes\n",
|
|
"\n",
|
|
"4. Open a new command prompt and run this to make sure it's installed OK\n",
|
|
"`ffmpeg -version`\n",
|
|
"\n",
|
|
"**For Mac Users**\n",
|
|
"\n",
|
|
"1. Install homebrew if you don't have it already by running this in a Terminal window and following any instructions: \n",
|
|
"`/bin/bash -c \"$(curl -fsSL https://raw.githubusercontent.com/Homebrew/install/HEAD/install.sh)\"`\n",
|
|
"\n",
|
|
"2. Then install FFmpeg with `brew install ffmpeg`\n",
|
|
"\n",
|
|
"3. Verify your installation with `ffmpeg -version` and if everything is good, within Jupyter Lab do Kernel -> Restart kernel to pick up the changes\n",
|
|
"\n",
|
|
"Message me or email me at ed@edwarddonner.com with any problems!"
|
|
]
|
|
},
|
|
{
|
|
"cell_type": "code",
|
|
"execution_count": null,
|
|
"id": "ffbfe93b-5e86-4e68-ba71-b301cd5230db",
|
|
"metadata": {},
|
|
"outputs": [],
|
|
"source": [
|
|
"from pydub import AudioSegment\n",
|
|
"from pydub.playback import play\n",
|
|
"\n",
|
|
"def talker(message):\n",
|
|
" response = openai.audio.speech.create(\n",
|
|
" model=\"tts-1\",\n",
|
|
" voice=\"onyx\", # Also, try replacing onyx with alloy\n",
|
|
" input=message\n",
|
|
" )\n",
|
|
" \n",
|
|
" audio_stream = BytesIO(response.content)\n",
|
|
" audio = AudioSegment.from_file(audio_stream, format=\"mp3\")\n",
|
|
" play(audio)"
|
|
]
|
|
},
|
|
{
|
|
"cell_type": "code",
|
|
"execution_count": null,
|
|
"id": "b88d775d-d357-4292-a1ad-5dc5ed567281",
|
|
"metadata": {},
|
|
"outputs": [],
|
|
"source": [
|
|
"talker(\"Well, hi there\")"
|
|
]
|
|
},
|
|
{
|
|
"cell_type": "markdown",
|
|
"id": "1d48876d-c4fa-46a8-a04f-f9fadf61fb0d",
|
|
"metadata": {},
|
|
"source": [
|
|
"# Our Agent Framework\n",
|
|
"\n",
|
|
"The term 'Agentic AI' and Agentization is an umbrella term that refers to a number of techniques, such as:\n",
|
|
"\n",
|
|
"1. Breaking a complex problem into smaller steps, with multiple LLMs carrying out specialized tasks\n",
|
|
"2. The ability for LLMs to use Tools to give them additional capabilities\n",
|
|
"3. The 'Agent Environment' which allows Agents to collaborate\n",
|
|
"4. An LLM can act as the Planner, dividing bigger tasks into smaller ones for the specialists\n",
|
|
"5. The concept of an Agent having autonomy / agency, beyond just responding to a prompt - such as Memory\n",
|
|
"\n",
|
|
"We're showing 1 and 2 here, and to a lesser extent 3 and 5. In week 8 we will do the lot!"
|
|
]
|
|
},
|
|
{
|
|
"cell_type": "code",
|
|
"execution_count": null,
|
|
"id": "ba820c95-02f5-499e-8f3c-8727ee0a6c0c",
|
|
"metadata": {},
|
|
"outputs": [],
|
|
"source": [
|
|
"def chat(message, history):\n",
|
|
" image = None\n",
|
|
" conversation = [{\"role\": \"system\", \"content\": system_message}]\n",
|
|
" for human, assistant in history:\n",
|
|
" conversation.append({\"role\": \"user\", \"content\": human})\n",
|
|
" conversation.append({\"role\": \"assistant\", \"content\": assistant})\n",
|
|
" conversation.append({\"role\": \"user\", \"content\": message})\n",
|
|
" response = openai.chat.completions.create(model=MODEL, messages=conversation, tools=tools)\n",
|
|
"\n",
|
|
" if response.choices[0].finish_reason==\"tool_calls\":\n",
|
|
" message = tool_call = response.choices[0].message\n",
|
|
" response, city = handle_tool_call(message)\n",
|
|
" conversation.append(message)\n",
|
|
" conversation.append(response)\n",
|
|
" image = artist(city)\n",
|
|
" response = openai.chat.completions.create(model=MODEL, messages=conversation)\n",
|
|
"\n",
|
|
" reply = response.choices[0].message.content\n",
|
|
" talker(reply)\n",
|
|
" return reply, image"
|
|
]
|
|
},
|
|
{
|
|
"cell_type": "code",
|
|
"execution_count": null,
|
|
"id": "f38d0d27-33bf-4992-a2e5-5dbed973cde7",
|
|
"metadata": {},
|
|
"outputs": [],
|
|
"source": [
|
|
"# More involved Gradio code as we're not using the preset Chat interface\n",
|
|
"\n",
|
|
"with gr.Blocks() as ui:\n",
|
|
" with gr.Row():\n",
|
|
" chatbot = gr.Chatbot(height=500)\n",
|
|
" image_output = gr.Image(height=500)\n",
|
|
" with gr.Row():\n",
|
|
" msg = gr.Textbox(label=\"Chat with our AI Assistant:\")\n",
|
|
" with gr.Row():\n",
|
|
" clear = gr.Button(\"Clear\")\n",
|
|
"\n",
|
|
" def user(user_message, history):\n",
|
|
" return \"\", history + [[user_message, None]]\n",
|
|
"\n",
|
|
" def bot(history):\n",
|
|
" user_message = history[-1][0]\n",
|
|
" bot_message, image = chat(user_message, history[:-1])\n",
|
|
" history[-1][1] = bot_message\n",
|
|
" return history, image\n",
|
|
"\n",
|
|
" msg.submit(user, [msg, chatbot], [msg, chatbot], queue=False).then(\n",
|
|
" bot, chatbot, [chatbot, image_output]\n",
|
|
" )\n",
|
|
" clear.click(lambda: None, None, chatbot, queue=False)\n",
|
|
"\n",
|
|
"ui.launch()"
|
|
]
|
|
},
|
|
{
|
|
"cell_type": "code",
|
|
"execution_count": null,
|
|
"id": "b0b12548-951d-4e7c-8e77-803a92271855",
|
|
"metadata": {},
|
|
"outputs": [],
|
|
"source": []
|
|
}
|
|
],
|
|
"metadata": {
|
|
"kernelspec": {
|
|
"display_name": "Python 3 (ipykernel)",
|
|
"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": "3.11.10"
|
|
}
|
|
},
|
|
"nbformat": 4,
|
|
"nbformat_minor": 5
|
|
}
|