From 431fe0d75f1aa4c98a3feecac814fbaf6c793e42 Mon Sep 17 00:00:00 2001 From: Dorotea Poljak Date: Wed, 23 Oct 2024 16:52:14 +0200 Subject: [PATCH] Add files via upload --- week2/day2-with-tasks.ipynb | 952 ++++++++++++++++++++++++++++++++++++ 1 file changed, 952 insertions(+) create mode 100644 week2/day2-with-tasks.ipynb diff --git a/week2/day2-with-tasks.ipynb b/week2/day2-with-tasks.ipynb new file mode 100644 index 0000000..01abde9 --- /dev/null +++ b/week2/day2-with-tasks.ipynb @@ -0,0 +1,952 @@ +{ + "cells": [ + { + "cell_type": "markdown", + "id": "8b0e11f2-9ea4-48c2-b8d2-d0a4ba967827", + "metadata": {}, + "source": [ + "# Gradio Day!\n", + "\n", + "Today we will build User Interfaces using the outrageously simple Gradio framework.\n", + "\n", + "Prepare for joy!" + ] + }, + { + "cell_type": "code", + "execution_count": 2, + "id": "c44c5494-950d-4d2f-8d4f-b87b57c5b330", + "metadata": {}, + "outputs": [], + "source": [ + "# imports\n", + "\n", + "import os\n", + "import requests\n", + "from bs4 import BeautifulSoup\n", + "from typing import List\n", + "from dotenv import load_dotenv\n", + "from openai import OpenAI\n", + "import google.generativeai\n", + "import anthropic" + ] + }, + { + "cell_type": "code", + "execution_count": 3, + "id": "d1715421-cead-400b-99af-986388a97aff", + "metadata": {}, + "outputs": [], + "source": [ + "import gradio as gr # oh yeah!" + ] + }, + { + "cell_type": "code", + "execution_count": 4, + "id": "337d5dfc-0181-4e3b-8ab9-e78e0c3f657b", + "metadata": {}, + "outputs": [], + "source": [ + "# Load environment variables in a file called .env\n", + "\n", + "load_dotenv()\n", + "os.environ['OPENAI_API_KEY'] = os.getenv('OPENAI_API_KEY', 'your-key-if-not-using-env')\n", + "os.environ['ANTHROPIC_API_KEY'] = os.getenv('ANTHROPIC_API_KEY', 'your-key-if-not-using-env')\n", + "os.environ['GOOGLE_API_KEY'] = os.getenv('GOOGLE_API_KEY', 'your-key-if-not-using-env')" + ] + }, + { + "cell_type": "code", + "execution_count": 5, + "id": "22586021-1795-4929-8079-63f5bb4edd4c", + "metadata": {}, + "outputs": [], + "source": [ + "# Connect to OpenAI, Anthropic and Google\n", + "\n", + "openai = OpenAI()\n", + "\n", + "claude = anthropic.Anthropic()\n", + "\n", + "google.generativeai.configure()" + ] + }, + { + "cell_type": "code", + "execution_count": 7, + "id": "b16e6021-6dc4-4397-985a-6679d6c8ffd5", + "metadata": {}, + "outputs": [], + "source": [ + "# A generic system message - no more snarky adversarial AIs!\n", + "\n", + "system_message = \"You are a helpful assistant that responds in markdown\"" + ] + }, + { + "cell_type": "code", + "execution_count": 7, + "id": "02ef9b69-ef31-427d-86d0-b8c799e1c1b1", + "metadata": {}, + "outputs": [], + "source": [ + "# Let's wrap a call to GPT-4o-mini in a simple function\n", + "\n", + "def message_gpt(prompt):\n", + " messages = [\n", + " {\"role\": \"system\", \"content\": system_message},\n", + " {\"role\": \"user\", \"content\": prompt}\n", + " ]\n", + " completion = openai.chat.completions.create(\n", + " model='gpt-4o-mini',\n", + " messages=messages,\n", + " )\n", + " return completion.choices[0].message.content" + ] + }, + { + "cell_type": "code", + "execution_count": 8, + "id": "aef7d314-2b13-436b-b02d-8de3b72b193f", + "metadata": {}, + "outputs": [ + { + "data": { + "text/plain": [ + "\"Today's date is October 3, 2023.\"" + ] + }, + "execution_count": 8, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "message_gpt(\"What is today's date?\")" + ] + }, + { + "cell_type": "markdown", + "id": "f94013d1-4f27-4329-97e8-8c58db93636a", + "metadata": {}, + "source": [ + "## User Interface time!" + ] + }, + { + "cell_type": "code", + "execution_count": 9, + "id": "bc664b7a-c01d-4fea-a1de-ae22cdd5141a", + "metadata": {}, + "outputs": [], + "source": [ + "# here's a simple function\n", + "\n", + "def shout(text):\n", + " print(f\"Shout has been called with input {text}\")\n", + " return text.upper()" + ] + }, + { + "cell_type": "code", + "execution_count": 10, + "id": "083ea451-d3a0-4d13-b599-93ed49b975e4", + "metadata": {}, + "outputs": [ + { + "name": "stdout", + "output_type": "stream", + "text": [ + "Shout has been called with input hello\n" + ] + }, + { + "data": { + "text/plain": [ + "'HELLO'" + ] + }, + "execution_count": 10, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "shout(\"hello\")" + ] + }, + { + "cell_type": "code", + "execution_count": 11, + "id": "08f1f15a-122e-4502-b112-6ee2817dda32", + "metadata": { + "scrolled": true + }, + "outputs": [ + { + "name": "stdout", + "output_type": "stream", + "text": [ + "* Running on local URL: http://127.0.0.1:7860\n", + "\n", + "To create a public link, set `share=True` in `launch()`.\n" + ] + }, + { + "data": { + "text/html": [ + "
" + ], + "text/plain": [ + "" + ] + }, + "metadata": {}, + "output_type": "display_data" + }, + { + "data": { + "text/plain": [] + }, + "execution_count": 11, + "metadata": {}, + "output_type": "execute_result" + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "Shout has been called with input hello\n", + "Created dataset file at: .gradio\\flagged\\dataset1.csv\n" + ] + } + ], + "source": [ + "gr.Interface(fn=shout, inputs=\"textbox\", outputs=\"textbox\").launch()" + ] + }, + { + "cell_type": "code", + "execution_count": 14, + "id": "c9a359a4-685c-4c99-891c-bb4d1cb7f426", + "metadata": {}, + "outputs": [ + { + "name": "stdout", + "output_type": "stream", + "text": [ + "* Running on local URL: http://127.0.0.1:7863\n", + "* Running on public URL: https://1b149f8be167f11821.gradio.live\n", + "\n", + "This share link expires in 72 hours. For free permanent hosting and GPU upgrades, run `gradio deploy` from the terminal in the working directory to deploy to Hugging Face Spaces (https://huggingface.co/spaces)\n" + ] + }, + { + "data": { + "text/html": [ + "
" + ], + "text/plain": [ + "" + ] + }, + "metadata": {}, + "output_type": "display_data" + }, + { + "data": { + "text/plain": [] + }, + "execution_count": 14, + "metadata": {}, + "output_type": "execute_result" + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "Shout has been called with input wow, this is cool! \n" + ] + } + ], + "source": [ + "gr.Interface(fn=shout, inputs=\"textbox\", outputs=\"textbox\", flagging_mode=\"never\").launch(share=True)" + ] + }, + { + "cell_type": "code", + "execution_count": 16, + "id": "3cc67b26-dd5f-406d-88f6-2306ee2950c0", + "metadata": {}, + "outputs": [ + { + "name": "stdout", + "output_type": "stream", + "text": [ + "* Running on local URL: http://127.0.0.1:7865\n", + "\n", + "To create a public link, set `share=True` in `launch()`.\n" + ] + }, + { + "data": { + "text/html": [ + "
" + ], + "text/plain": [ + "" + ] + }, + "metadata": {}, + "output_type": "display_data" + }, + { + "data": { + "text/plain": [] + }, + "execution_count": 16, + "metadata": {}, + "output_type": "execute_result" + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "Shout has been called with input hello again :)\n" + ] + } + ], + "source": [ + "view = gr.Interface(\n", + " fn=shout,\n", + " inputs=[gr.Textbox(label=\"Your message:\", lines=6)],\n", + " outputs=[gr.Textbox(label=\"Response:\", lines=8)],\n", + " flagging_mode=\"never\"\n", + ")\n", + "view.launch()" + ] + }, + { + "cell_type": "code", + "execution_count": 17, + "id": "f235288e-63a2-4341-935b-1441f9be969b", + "metadata": {}, + "outputs": [ + { + "name": "stdout", + "output_type": "stream", + "text": [ + "* Running on local URL: http://127.0.0.1:7866\n", + "\n", + "To create a public link, set `share=True` in `launch()`.\n" + ] + }, + { + "data": { + "text/html": [ + "
" + ], + "text/plain": [ + "" + ] + }, + "metadata": {}, + "output_type": "display_data" + }, + { + "data": { + "text/plain": [] + }, + "execution_count": 17, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "view = gr.Interface(\n", + " fn=message_gpt,\n", + " inputs=[gr.Textbox(label=\"Your message:\", lines=6)],\n", + " outputs=[gr.Textbox(label=\"Response:\", lines=8)],\n", + " flagging_mode=\"never\"\n", + ")\n", + "view.launch()" + ] + }, + { + "cell_type": "code", + "execution_count": 18, + "id": "af9a3262-e626-4e4b-80b0-aca152405e63", + "metadata": {}, + "outputs": [ + { + "name": "stdout", + "output_type": "stream", + "text": [ + "* Running on local URL: http://127.0.0.1:7867\n", + "\n", + "To create a public link, set `share=True` in `launch()`.\n" + ] + }, + { + "data": { + "text/html": [ + "
" + ], + "text/plain": [ + "" + ] + }, + "metadata": {}, + "output_type": "display_data" + }, + { + "data": { + "text/plain": [] + }, + "execution_count": 18, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "system_message = \"You are a helpful assistant that responds in markdown\"\n", + "\n", + "view = gr.Interface(\n", + " fn=message_gpt,\n", + " inputs=[gr.Textbox(label=\"Your message:\")],\n", + " outputs=[gr.Markdown(label=\"Response:\")],\n", + " flagging_mode=\"never\"\n", + ")\n", + "view.launch()" + ] + }, + { + "cell_type": "code", + "execution_count": 8, + "id": "88c04ebf-0671-4fea-95c9-bc1565d4bb4f", + "metadata": {}, + "outputs": [], + "source": [ + "# Let's create a call that streams back results\n", + "\n", + "def stream_gpt(prompt):\n", + " messages = [\n", + " {\"role\": \"system\", \"content\": system_message},\n", + " {\"role\": \"user\", \"content\": prompt}\n", + " ]\n", + " stream = openai.chat.completions.create(\n", + " model='gpt-4o-mini',\n", + " messages=messages,\n", + " stream=True\n", + " )\n", + " result = \"\"\n", + " for chunk in stream:\n", + " result += chunk.choices[0].delta.content or \"\"\n", + " yield result" + ] + }, + { + "cell_type": "code", + "execution_count": 20, + "id": "0bb1f789-ff11-4cba-ac67-11b815e29d09", + "metadata": {}, + "outputs": [ + { + "name": "stdout", + "output_type": "stream", + "text": [ + "* Running on local URL: http://127.0.0.1:7868\n", + "\n", + "To create a public link, set `share=True` in `launch()`.\n" + ] + }, + { + "data": { + "text/html": [ + "
" + ], + "text/plain": [ + "" + ] + }, + "metadata": {}, + "output_type": "display_data" + }, + { + "data": { + "text/plain": [] + }, + "execution_count": 20, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "view = gr.Interface(\n", + " fn=stream_gpt,\n", + " inputs=[gr.Textbox(label=\"Your message:\")],\n", + " outputs=[gr.Markdown(label=\"Response:\")],\n", + " flagging_mode=\"never\"\n", + ")\n", + "view.launch()" + ] + }, + { + "cell_type": "code", + "execution_count": 9, + "id": "bbc8e930-ba2a-4194-8f7c-044659150626", + "metadata": {}, + "outputs": [], + "source": [ + "def stream_claude(prompt):\n", + " result = claude.messages.stream(\n", + " model=\"claude-3-haiku-20240307\",\n", + " max_tokens=1000,\n", + " temperature=0.7,\n", + " system=system_message,\n", + " messages=[\n", + " {\"role\": \"user\", \"content\": prompt},\n", + " ],\n", + " )\n", + " response = \"\"\n", + " with result as stream:\n", + " for text in stream.text_stream:\n", + " response += text or \"\"\n", + " yield response" + ] + }, + { + "cell_type": "code", + "execution_count": 22, + "id": "a0066ffd-196e-4eaf-ad1e-d492958b62af", + "metadata": {}, + "outputs": [ + { + "name": "stdout", + "output_type": "stream", + "text": [ + "* Running on local URL: http://127.0.0.1:7869\n", + "\n", + "To create a public link, set `share=True` in `launch()`.\n" + ] + }, + { + "data": { + "text/html": [ + "
" + ], + "text/plain": [ + "" + ] + }, + "metadata": {}, + "output_type": "display_data" + }, + { + "data": { + "text/plain": [] + }, + "execution_count": 22, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "view = gr.Interface(\n", + " fn=stream_claude,\n", + " inputs=[gr.Textbox(label=\"Your message:\")],\n", + " outputs=[gr.Markdown(label=\"Response:\")],\n", + " flagging_mode=\"never\"\n", + ")\n", + "view.launch()" + ] + }, + { + "cell_type": "code", + "execution_count": 186, + "id": "1f3906c9-2bb2-40ca-acc9-c3e8a7c4c61c", + "metadata": {}, + "outputs": [], + "source": [ + "def chat_gemini(prompt):\n", + " gemini = google.generativeai.GenerativeModel(\n", + " model_name='gemini-1.5-flash',\n", + " system_instruction=system_message\n", + " )\n", + " response = gemini.generate_content(prompt)\n", + " return(response.text)" + ] + }, + { + "cell_type": "code", + "execution_count": 187, + "id": "a14cddc3-7a1e-4c09-98f4-ee6b33486922", + "metadata": {}, + "outputs": [ + { + "data": { + "text/plain": [ + "'Hello! 👋 How can I help you today? 😊 \\n'" + ] + }, + "execution_count": 187, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "chat_gemini(\"Hello\")" + ] + }, + { + "cell_type": "code", + "execution_count": 87, + "id": "6d74e2de-1fcd-49d4-9991-bffa7f5099ec", + "metadata": {}, + "outputs": [ + { + "name": "stdout", + "output_type": "stream", + "text": [ + "* Running on local URL: http://127.0.0.1:7879\n", + "\n", + "To create a public link, set `share=True` in `launch()`.\n" + ] + }, + { + "data": { + "text/html": [ + "
" + ], + "text/plain": [ + "" + ] + }, + "metadata": {}, + "output_type": "display_data" + }, + { + "data": { + "text/plain": [] + }, + "execution_count": 87, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "gr.Interface(fn=chat_gemini, inputs=\"textbox\", outputs=\"textbox\").launch()" + ] + }, + { + "cell_type": "code", + "execution_count": 10, + "id": "223465b1-6699-4d34-b1a9-38306edc4ca7", + "metadata": {}, + "outputs": [], + "source": [ + "def stream_gemini(prompt):\n", + " gemini = google.generativeai.GenerativeModel(\n", + " model_name='gemini-1.5-flash',\n", + " system_instruction=system_message\n", + " )\n", + " stream = gemini.generate_content(prompt, stream=True)\n", + " result = \"\"\n", + " for chunk in stream:\n", + " result += chunk.text or \"\"\n", + " yield result" + ] + }, + { + "cell_type": "code", + "execution_count": 223, + "id": "28dc9075-013b-43eb-a1ae-59097c781b86", + "metadata": {}, + "outputs": [ + { + "name": "stdout", + "output_type": "stream", + "text": [ + "* Running on local URL: http://127.0.0.1:7897\n", + "\n", + "To create a public link, set `share=True` in `launch()`.\n" + ] + }, + { + "data": { + "text/html": [ + "
" + ], + "text/plain": [ + "" + ] + }, + "metadata": {}, + "output_type": "display_data" + }, + { + "data": { + "text/plain": [] + }, + "execution_count": 223, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "view = gr.Interface(\n", + " fn=stream_gemini,\n", + " inputs=[gr.Textbox(label=\"Your message:\")],\n", + " outputs=[gr.Markdown(label=\"Response:\")],\n", + " flagging_mode=\"never\"\n", + ")\n", + "view.launch()" + ] + }, + { + "cell_type": "code", + "execution_count": 11, + "id": "0087623a-4e31-470b-b2e6-d8d16fc7bcf5", + "metadata": {}, + "outputs": [], + "source": [ + "def stream_model(prompt, model):\n", + " if model==\"GPT\":\n", + " result = stream_gpt(prompt)\n", + " elif model==\"Gemini\":\n", + " result = stream_gemini(prompt)\n", + " elif model==\"Claude\":\n", + " result = stream_claude(prompt)\n", + " else:\n", + " raise ValueError(\"Unknown model\")\n", + " for reply in result:\n", + " yield reply" + ] + }, + { + "cell_type": "code", + "execution_count": 12, + "id": "8d8ce810-997c-4b6a-bc4f-1fc847ac8855", + "metadata": { + "scrolled": true + }, + "outputs": [ + { + "name": "stdout", + "output_type": "stream", + "text": [ + "* Running on local URL: http://127.0.0.1:7860\n", + "\n", + "To create a public link, set `share=True` in `launch()`.\n" + ] + }, + { + "data": { + "text/html": [ + "
" + ], + "text/plain": [ + "" + ] + }, + "metadata": {}, + "output_type": "display_data" + }, + { + "data": { + "text/plain": [] + }, + "execution_count": 12, + "metadata": {}, + "output_type": "execute_result" + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "Using existing dataset file at: .gradio\\flagged\\dataset2.csv\n" + ] + } + ], + "source": [ + "view = gr.Interface(\n", + " fn=stream_model,\n", + " inputs=[gr.Textbox(label=\"Your message:\"), gr.Dropdown([\"GPT\", \"Claude\", \"Gemini\"], label=\"Select model\")],\n", + " outputs=[gr.Markdown(label=\"Response:\")],\n", + " flagging_mode=\"auto\"\n", + ")\n", + "view.launch()" + ] + }, + { + "cell_type": "markdown", + "id": "d933865b-654c-4b92-aa45-cf389f1eda3d", + "metadata": {}, + "source": [ + "# Building a company brochure generator\n", + "\n", + "Now you know how - it's simple!" + ] + }, + { + "cell_type": "code", + "execution_count": 18, + "id": "1626eb2e-eee8-4183-bda5-1591b58ae3cf", + "metadata": {}, + "outputs": [], + "source": [ + "# A class to represent a Webpage\n", + "\n", + "class Website:\n", + " url: str\n", + " title: str\n", + " text: str\n", + "\n", + " def __init__(self, url):\n", + " self.url = url\n", + " response = requests.get(url)\n", + " self.body = response.content\n", + " soup = BeautifulSoup(self.body, 'html.parser')\n", + " self.title = soup.title.string if soup.title else \"No title found\"\n", + " for irrelevant in soup.body([\"script\", \"style\", \"img\", \"input\"]):\n", + " irrelevant.decompose()\n", + " self.text = soup.body.get_text(separator=\"\\n\", strip=True)\n", + "\n", + " def get_contents(self):\n", + " return f\"Webpage Title:\\n{self.title}\\nWebpage Contents:\\n{self.text}\\n\\n\"" + ] + }, + { + "cell_type": "code", + "execution_count": 25, + "id": "c701ec17-ecd5-4000-9f68-34634c8ed49d", + "metadata": {}, + "outputs": [], + "source": [ + "serious_system_prompt = \"You are an assistant that analyzes the contents of a company website landing page \\\n", + "and creates a short brochure about the company for prospective customers, investors and recruits. Use a serious tone in your respose. \\\n", + "Respond in markdown.\"" + ] + }, + { + "cell_type": "code", + "execution_count": 26, + "id": "67969d54-2ab5-4133-8d3d-83f08e63755d", + "metadata": {}, + "outputs": [], + "source": [ + "funny_system_prompt = \"You are an assistant that analyzes the contents of a company website landing page \\\n", + "and creates a short brochure about the company for prospective customers, investors and recruits. Use a funny tone in your response. \\\n", + "Respond in markdown.\"" + ] + }, + { + "cell_type": "code", + "execution_count": 27, + "id": "5def90e0-4343-4f58-9d4a-0e36e445efa4", + "metadata": {}, + "outputs": [], + "source": [ + "def stream_brochure(company_name, url, model, mode):\n", + " prompt = f\"Please generate a company brochure for {company_name}. Here is their landing page:\\n\"\n", + " prompt += Website(url).get_contents()\n", + " if model==\"GPT\":\n", + " result = stream_gpt(prompt)\n", + " elif model==\"Claude\":\n", + " result = stream_claude(prompt)\n", + " elif model==\"Gemini\":\n", + " result = stream_gemini(prompt)\n", + " else:\n", + " raise ValueError(\"Unknown model\")\n", + " if mode==\"Funny\":\n", + " system_prompt = funny_system_prompt\n", + " elif mode==\"Serious\":\n", + " system_prompt = serious_system_prompt\n", + " else:\n", + " raise ValueError(\"Unknown model\")\n", + " for reply in result:\n", + " yield reply" + ] + }, + { + "cell_type": "code", + "execution_count": 28, + "id": "66399365-5d67-4984-9d47-93ed26c0bd3d", + "metadata": {}, + "outputs": [ + { + "name": "stdout", + "output_type": "stream", + "text": [ + "* Running on local URL: http://127.0.0.1:7864\n", + "\n", + "To create a public link, set `share=True` in `launch()`.\n" + ] + }, + { + "data": { + "text/html": [ + "
" + ], + "text/plain": [ + "" + ] + }, + "metadata": {}, + "output_type": "display_data" + }, + { + "data": { + "text/plain": [] + }, + "execution_count": 28, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "view = gr.Interface(\n", + " fn=stream_brochure,\n", + " inputs=[\n", + " gr.Textbox(label=\"Company name:\"),\n", + " gr.Textbox(label=\"Landing page URL:\"),\n", + " gr.Dropdown([\"GPT\", \"Claude\", \"Gemini\"], label=\"Select model\"),\n", + " gr.Dropdown([\"Funny\", \"Serious\"], label=\"Select mode\")],\n", + " outputs=[gr.Markdown(label=\"Brochure:\")],\n", + " flagging_mode=\"never\"\n", + ")\n", + "view.launch()" + ] + }, + { + "cell_type": "code", + "execution_count": null, + "id": "d0fc580a-dc98-48c3-9dd4-b19cd3be5a18", + "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": "3.12.0" + } + }, + "nbformat": 4, + "nbformat_minor": 5 +}