diff --git a/week2/community-contributions/Airlines_Chatbot_with_Audio_Input.ipynb b/week2/community-contributions/Airlines_Chatbot_with_Audio_Input.ipynb new file mode 100644 index 0000000..4b18a89 --- /dev/null +++ b/week2/community-contributions/Airlines_Chatbot_with_Audio_Input.ipynb @@ -0,0 +1,326 @@ +{ + "cells": [ + { + "cell_type": "markdown", + "id": "d006b2ea-9dfe-49c7-88a9-a5a0775185fd", + "metadata": {}, + "source": [ + "# Project to take Audio Input to the Airlines ChatBot" + ] + }, + { + "cell_type": "code", + "execution_count": null, + "id": "a07e7793-b8f5-44f4-aded-5562f633271a", + "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\n", + "import base64\n", + "from io import BytesIO\n", + "from PIL import Image\n", + "from IPython.display import Audio, display" + ] + }, + { + "cell_type": "code", + "execution_count": null, + "id": "9e2315a3-f80c-4d3f-8073-f5b61d709564", + "metadata": {}, + "outputs": [], + "source": [ + "# Initialization\n", + "\n", + "load_dotenv(override=True)\n", + "\n", + "openai_api_key = os.getenv('OPENAI_API_KEY')\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", + "MODEL = \"gpt-4o-mini\"\n", + "openai = OpenAI()" + ] + }, + { + "cell_type": "code", + "execution_count": null, + "id": "40da9de1-b350-49de-8acd-052f40ce5611", + "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": "5537635c-a60d-4983-8018-375c6a912e19", + "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": "c7132dd0-8788-4885-a415-d59664f68fd8", + "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": "7703ca0c-5da4-4641-bcb1-7727d1b2f2bf", + "metadata": {}, + "outputs": [], + "source": [ + "# And this is included in a list of tools:\n", + "\n", + "tools = [{\"type\": \"function\", \"function\": price_function}]" + ] + }, + { + "cell_type": "code", + "execution_count": null, + "id": "29ce724b-d998-4c3f-bc40-6b8576c0fd34", + "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\": tool_call.id\n", + " }\n", + " return response, city" + ] + }, + { + "cell_type": "code", + "execution_count": null, + "id": "931d0565-b01d-4aa8-bd18-72bafff8fb3b", + "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": "fa165f7f-9796-4513-b923-2fa0b0b9ddd8", + "metadata": {}, + "outputs": [], + "source": [ + "import base64\n", + "from io import BytesIO\n", + "from PIL import Image\n", + "from IPython.display import Audio, display\n", + "\n", + "def talker(message):\n", + " response = openai.audio.speech.create(\n", + " model=\"tts-1\",\n", + " voice=\"onyx\",\n", + " input=message)\n", + "\n", + " audio_stream = BytesIO(response.content)\n", + " output_filename = \"output_audio.mp3\"\n", + " with open(output_filename, \"wb\") as f:\n", + " f.write(audio_stream.read())\n", + "\n", + " # Play the generated audio\n", + " display(Audio(output_filename, autoplay=True))\n", + "\n", + "talker(\"Well, hi there\")" + ] + }, + { + "cell_type": "code", + "execution_count": null, + "id": "b512d4ff-0f7b-4148-b161-4ee0ebf14776", + "metadata": {}, + "outputs": [], + "source": [ + "def transcribe_audio(audio_file):\n", + " with open(audio_file, \"rb\") as f:\n", + " transcript = openai.audio.transcriptions.create(\n", + " model=\"whisper-1\",\n", + " file=f\n", + " )\n", + " return transcript.text" + ] + }, + { + "cell_type": "code", + "execution_count": null, + "id": "c3852570-fb26-4507-a001-f50fd94b7655", + "metadata": {}, + "outputs": [], + "source": [ + "# Translate between languages using GPT\n", + "def translate(text, source_lang, target_lang):\n", + " translation_prompt = (\n", + " f\"Translate the following text from {source_lang} to {target_lang}:\\n\\n{text}\"\n", + " )\n", + " response = openai.chat.completions.create(\n", + " model=\"gpt-3.5-turbo\",\n", + " messages=[{\"role\": \"user\", \"content\": translation_prompt}]\n", + " )\n", + " return response.choices[0].message.content.strip()" + ] + }, + { + "cell_type": "code", + "execution_count": null, + "id": "3d75abc2-870e-48af-a8fe-8dd463418b3d", + "metadata": {}, + "outputs": [], + "source": [ + "# Chatbot logic: handle both text and audio input\n", + "def chatbot_dual(history):\n", + " messages = [{\"role\": \"system\", \"content\": system_message}] + history\n", + " response = openai.chat.completions.create(model=MODEL, messages=messages, tools=tools)\n", + " image = None\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", + " image = artist(city)\n", + " response = openai.chat.completions.create(model=MODEL, messages=messages)\n", + " \n", + " reply = response.choices[0].message.content\n", + " history += [{\"role\":\"assistant\", \"content\":reply}]\n", + "\n", + " # Comment out or delete the next line if you'd rather skip Audio for now..\n", + " # audio_response = talker(reply)\n", + " talker(reply)\n", + " return history, image# Chatbot logic here — replace with real logic" + ] + }, + { + "cell_type": "code", + "execution_count": null, + "id": "512fec09-c2f7-4847-817b-bc20f8b30319", + "metadata": {}, + "outputs": [], + "source": [ + "# More involved Gradio code as we're not using the preset Chat interface!\n", + "# Passing in inbrowser=True in the last line will cause a Gradio window to pop up immediately.\n", + "\n", + "with gr.Blocks() as ui:\n", + " with gr.Row():\n", + " chatbot = gr.Chatbot(height=500, type=\"messages\")\n", + " image_output = gr.Image(height=500)\n", + "\n", + " with gr.Row():\n", + " text_input = gr.Textbox(label=\"Chat with our AI Assistant:\")\n", + " audio_input = gr.Audio(sources=\"microphone\", type=\"filepath\", label=\"Or speak to the assistant\")\n", + "\n", + " with gr.Row():\n", + " # voice_output = gr.Audio(label=\"Bot Voice Reply\", autoplay=True)\n", + " clear = gr.Button(\"Clear\")\n", + "\n", + " def do_entry(message, audio, history):\n", + " if message:\n", + " history += [{\"role\":\"user\", \"content\":message}]\n", + " if audio:\n", + " history += [{\"role\":\"user\", \"content\":transcribe_audio(audio)}]\n", + " return \"\", None, history\n", + "\n", + " text_input.submit(do_entry, inputs=[text_input, audio_input, chatbot], outputs=[text_input, audio_input, chatbot]).then(chatbot_dual, inputs=chatbot, outputs=[chatbot, image_output]\n", + " )\n", + "\n", + " audio_input.change(do_entry, inputs=[text_input, audio_input, chatbot], outputs=[text_input, audio_input, chatbot]).then(chatbot_dual, inputs=chatbot, outputs=[chatbot, image_output]\n", + " )\n", + "\n", + " clear.click(lambda: None, inputs=None, outputs=chatbot, queue=False)\n", + "\n", + "ui.launch(inbrowser=True)" + ] + }, + { + "cell_type": "code", + "execution_count": null, + "id": "3e1294e2-caf0-4f0f-b09e-b0d52c8ca6ec", + "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": "3.11.11" + } + }, + "nbformat": 4, + "nbformat_minor": 5 +}