From b7f3701a7cdbb93275cb6e8921432f8e1f4a0aba Mon Sep 17 00:00:00 2001 From: Batikan Iscan Date: Sat, 30 Nov 2024 17:38:21 -0500 Subject: [PATCH] adding my contribution --- .../day1-article-pdf-reader.ipynb | 189 ++++++++++++++++++ 1 file changed, 189 insertions(+) create mode 100644 week1/community-contributions/day1-article-pdf-reader.ipynb diff --git a/week1/community-contributions/day1-article-pdf-reader.ipynb b/week1/community-contributions/day1-article-pdf-reader.ipynb new file mode 100644 index 0000000..28af4e3 --- /dev/null +++ b/week1/community-contributions/day1-article-pdf-reader.ipynb @@ -0,0 +1,189 @@ +{ + "cells": [ + { + "cell_type": "markdown", + "id": "c7d95a7f-205a-4262-a1af-4579489025ff", + "metadata": {}, + "source": [ + "# Hello everyone." + ] + }, + { + "cell_type": "markdown", + "id": "bc815dbc-acf7-45f9-a043-5767184c44c6", + "metadata": {}, + "source": [ + "I completed the day 1, first LLM Experiment moments ago and found it really awesome. After the challenge was done, I wanted to chip in my two cents by making a PDF summarizer, basing myself on the code for the Website Summarizer. I want to share it in this contribution!\n", + "### To consider:\n", + "* To extract the contents of PDF files, I used the PyPDF2 library, which doesn't come with the default configuration of the virtual environment. To remedy the situation, you need to follow the steps:\n", + " 1. Shut down Anaconda. Running `CTRL-C` in the Anaconda terminal should achieve this.\n", + " 2. Run the following command, `pip install PyPDF2 --user`\n", + " 3. Restart Jupyter lab with `jupyter lab`\n", + "* To find PDF files online, you can add `filetype:url` on your browser query, i.e. searching the following can give you PDF files to add as input: `AI Engineering prompts filetype:pdf`!\n", + "\n", + "Without further ado, here's the PDF Summarizer!" + ] + }, + { + "cell_type": "code", + "execution_count": null, + "id": "06b63787-c6c8-4868-8a71-eb56b7618626", + "metadata": {}, + "outputs": [], + "source": [ + "# Import statements\n", + "import os\n", + "import requests\n", + "from dotenv import load_dotenv\n", + "from IPython.display import Markdown, display\n", + "from openai import OpenAI\n", + "from io import BytesIO\n", + "from PyPDF2 import PdfReader" + ] + }, + { + "cell_type": "code", + "execution_count": null, + "id": "284ca770-5da4-495c-b1cf-637727a8609f", + "metadata": {}, + "outputs": [], + "source": [ + "# Load environment variables in a file called .env\n", + "\n", + "load_dotenv()\n", + "api_key = os.getenv('OPENAI_API_KEY')\n", + "\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 not api_key.startswith(\"sk-proj-\"):\n", + " print(\"An API key was found, but it doesn't start sk-proj-; please check you're using the right key - see troubleshooting notebook\")\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(\"API key found and looks good so far!\")" + ] + }, + { + "cell_type": "code", + "execution_count": null, + "id": "d4c316d7-d9c9-4400-b03e-1dd629c6b2ad", + "metadata": {}, + "outputs": [], + "source": [ + "openai = OpenAI()\n", + "\n", + "# If this doesn't work, try Kernel menu >> Restart Kernel and Clear Outputs Of All Cells, then run the cells from the top of this notebook down.\n", + "# If it STILL doesn't work (horrors!) then please see the troubleshooting notebook, or try the below line instead:\n", + "# openai = OpenAI(api_key=\"your-key-here-starting-sk-proj-\")" + ] + }, + { + "cell_type": "code", + "execution_count": null, + "id": "3a053092-f4f6-4156-8721-39353c8a9367", + "metadata": {}, + "outputs": [], + "source": [ + "# Step 0: Create article class\n", + "class Article:\n", + " def __init__(self, url):\n", + " \"\"\"\n", + " Create this Article object from the given url using the PyPDF2 library\n", + " \"\"\"\n", + " self.url = url \n", + " response = requests.get(self.url)\n", + " if response.status_code == 200:\n", + " pdf_bytes = BytesIO(response.content)\n", + " reader = PdfReader(pdf_bytes)\n", + " \n", + " text = \"\"\n", + " for page in reader.pages:\n", + " text += page.extract_text()\n", + " \n", + " self.text = text\n", + " self.title = reader.metadata.get(\"/Title\", \"No title found\")\n", + " else:\n", + " print(f\"Failed to fetch PDF. Status code: {response.status_code}\")\n", + " self.text = \"No text found\"\n", + " self.title = \"No title found\"" + ] + }, + { + "cell_type": "code", + "execution_count": null, + "id": "adc528f2-25ca-47b5-896e-9d417ba0195f", + "metadata": {}, + "outputs": [], + "source": [ + "# Step 1: Create your prompts\n", + "\n", + "def craft_user_prompt(article):\n", + " user_prompt = f\"You are looking at a research article titled {article.title}\\n Based on the body of the article, how are micro RNAs produced in the cell? State the function of the proteins \\\n", + " involved. The body of the article is as follows.\"\n", + " user_prompt += article.text\n", + " return user_prompt\n", + "\n", + "# Step 2: Make the messages list\n", + "def craft_messages(article):\n", + " system_prompt = \"You are an assistant that analyses the contents of a research article and provide answers to the question asked by the user in 250 words or less. \\\n", + " Ignore text that doesn't belong to the article, like headers or navigation related text. Respond in markdown. Structure your text in the form of question/answer.\"\n", + " return [\n", + " {\"role\": \"system\", \"content\": system_prompt},\n", + " {\"role\": \"user\", \"content\": craft_user_prompt(article)}\n", + " ]" + ] + }, + { + "cell_type": "code", + "execution_count": null, + "id": "81ab896e-1ba9-4964-a477-2a0608b7036c", + "metadata": {}, + "outputs": [], + "source": [ + "# Step 3: Call OpenAI\n", + "def summarize(url):\n", + " article = Article(url)\n", + " response = openai.chat.completions.create(\n", + " model = \"gpt-4o-mini\",\n", + " messages = craft_messages(article)\n", + " )\n", + " return response.choices[0].message.content" + ] + }, + { + "cell_type": "code", + "execution_count": null, + "id": "a7a98cdf-0d3b-477d-8e39-a6a4264b9feb", + "metadata": {}, + "outputs": [], + "source": [ + "# Step 4: Print the result of an example pdf\n", + "summary = summarize(\"https://www.nature.com/articles/s12276-023-01050-9.pdf\")\n", + "display(Markdown(summary))" + ] + } + ], + "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 +}