diff --git a/Madhul-Solutions/MS-PDF-Analyser.ipynb b/Madhul-Solutions/MS-PDF-Analyser.ipynb new file mode 100644 index 0000000..d1b5e3f --- /dev/null +++ b/Madhul-Solutions/MS-PDF-Analyser.ipynb @@ -0,0 +1,419 @@ +{ + "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": "14e98361-f302-423d-87a5-f2f5d570f4ac", + "metadata": {}, + "outputs": [], + "source": [ + "### Prerequisite - Install below package\n", + "#--> !pip install PyPDF2 --user" + ] + }, + { + "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\n", + "import logging" + ] + }, + { + "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": 60, + "id": "b6f2967e-4779-458f-aea8-c47147528f77", + "metadata": {}, + "outputs": [], + "source": [ + "# Step 1: Defince calss for article pdf document\n", + "\n", + "class Article:\n", + " def __init__(self, url):\n", + " # Configure logging\n", + " logging.basicConfig(level=logging.ERROR)\n", + "\n", + " # Comprehensive headers to mimic browser\n", + " headers = {\n", + " 'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/91.0.4472.124 Safari/537.36',\n", + " 'Accept': 'application/pdf,text/html,application/xhtml+xml,application/xml',\n", + " 'Accept-Language': 'en-US,en;q=0.5',\n", + " 'Referer': self._extract_base_url(url)\n", + " }\n", + "\n", + " try:\n", + " # Enhanced download attempt with multiple strategies\n", + " response = self._download_pdf(url, headers)\n", + " \n", + " # Process PDF\n", + " pdf_bytes = BytesIO(response.content)\n", + " reader = PdfReader(pdf_bytes)\n", + " \n", + " # Efficient text extraction\n", + " self.text = \" \".join(page.extract_text() for page in reader.pages)\n", + " \n", + " # Safe metadata extraction\n", + " self.title = (reader.metadata or {}).get(\"/Title\", \"No title found\") or \"No title found\"\n", + "\n", + " except Exception as error:\n", + " logging.error(f\"PDF Processing Error: {error}\")\n", + " self.text = \"No text found\"\n", + " self.title = \"No title found\"\n", + "\n", + " def _download_pdf(self, url, headers):\n", + " \"\"\"\n", + " Multiple download strategies to handle different access scenarios\n", + " \"\"\"\n", + " try:\n", + " # Primary download attempt\n", + " response = requests.get(url, headers=headers, timeout=10)\n", + " response.raise_for_status()\n", + " return response\n", + "\n", + " except requests.RequestException as primary_error:\n", + " logging.warning(f\"Primary download failed: {primary_error}\")\n", + " \n", + " try:\n", + " # Fallback strategy: Disable SSL verification\n", + " response = requests.get(url, headers=headers, verify=False, timeout=10)\n", + " response.raise_for_status()\n", + " return response\n", + " \n", + " except requests.RequestException as fallback_error:\n", + " logging.error(f\"All download attempts failed: {fallback_error}\")\n", + " raise\n", + "\n", + " def _extract_base_url(self, url):\n", + " \"\"\"\n", + " Extract base URL for Referer header\n", + " \"\"\"\n", + " from urllib.parse import urlparse\n", + " parsed_url = urlparse(url)\n", + " return f\"{parsed_url.scheme}://{parsed_url.netloc}\"" + ] + }, + { + "cell_type": "markdown", + "id": "95933aab-54df-4afc-a19c-46033f51378f", + "metadata": {}, + "source": [ + "#####user_prompt_input = input(\"Explain how you would like me to summarise the document? \\n\")" + ] + }, + { + "cell_type": "code", + "execution_count": 61, + "id": "821acbfa-ad06-4afd-9ac1-b9f68b7a418e", + "metadata": {}, + "outputs": [], + "source": [ + "# General Research Analyst\n", + "#### Step 1: Create your prompts\n", + "\n", + "def craft_user_prompt(article):\n", + " user_prompt = f\"You are looking at a document titled {article.title}\\n Based on the body of the document, provide an impactful summary. 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 a research assistant specialising in processing documents. You have been tasked with analysing the contents of the articel and call out the important points as bullets and highlights. \\\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": 62, + "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": "markdown", + "id": "ccdfdd33-652f-4ecf-9a0d-355197aba9d5", + "metadata": {}, + "source": [ + "# Results below:" + ] + }, + { + "cell_type": "code", + "execution_count": 63, + "id": "008c03fd-9cc5-4449-a054-7bbef1863b01", + "metadata": {}, + "outputs": [ + { + "name": "stdin", + "output_type": "stream", + "text": [ + "Please input the pdf URL: \n", + " https://www.binasss.sa.cr/bibliotecas/bhm/ago22/32.pdf\n" + ] + }, + { + "data": { + "text/markdown": [ + "## Summary of **Bronchiectasis — A Clinical Review**\n", + "\n", + "### What is bronchiectasis?\n", + "- Bronchiectasis is a clinical syndrome characterized by:\n", + " - Chronic cough \n", + " - Sputum production\n", + " - Abnormal thickening and dilation of bronchial walls, visible on lung imaging.\n", + "\n", + "### Historical Background\n", + "- First reported by René Laënnec in 1819.\n", + "- Radiographic characteristics understood more clearly since the 1950s.\n", + "\n", + "### Current Trends\n", + "- Significantly increasing incidence and prevalence over the last 20 years.\n", + "- Diagnosed across a wide age range, with geographic variability in prevalence (as high as 1.5% in some populations).\n", + "- Improved recognition, partly due to advanced imaging technologies like CT scans.\n", + " \n", + "### Clinical Presentation\n", + "- Symptoms include chronic productive cough, chest pain, and shortness of breath.\n", + "- Often misdiagnosed as chronic bronchitis or asthma, leading to delayed diagnosis.\n", + "- Intermittent exacerbations are common, defined by a worsening of cough and sputum characteristics for 48 hours or more.\n", + "\n", + "### Diagnostic Approaches\n", + "- High-resolution CT scans are essential for diagnosis, seeking specific airway abnormalities.\n", + "- A systematic evaluation to identify underlying causes (such as congenital disorders or autoimmune diseases) is critical.\n", + "\n", + "### Pathobiology\n", + "- Multiple factors lead to airway dysfunction, inflammatory responses, and cyclical deterioration.\n", + "- Neutrophils and neutrophil elastase play significant roles in disease progression and exacerbations.\n", + "\n", + "### Microbiological Features\n", + "- **Common pathogens**:\n", + " - Pseudomonas aeruginosa (notably linked to exacerbations and worse prognosis)\n", + " - Staphylococcus aureus and other bacteria.\n", + "- Non-tuberculous mycobacterial infections are reported increasingly.\n", + "\n", + "### Treatment Strategies\n", + "- Emphasizes education about the disease and its management.\n", + "- Goals include symptom management, quality of life improvement, and reduction of exacerbation frequency.\n", + "- Options include:\n", + " - Airway-clearance therapies\n", + " - Antibiotics (macrolides or inhaled antibiotics)\n", + " - Addressing any treatable underlying conditions.\n", + "\n", + "### Prognostic Indicators\n", + "- Disease severity scores like the Bronchiectasis Severity Index and FACED scale are used for predicting outcomes.\n", + "\n", + "### Future Directions\n", + "- Emphasis on research into novel therapies targeting inflamatory pathways and innovative diagnostic tools.\n", + "\n", + "### Conclusion\n", + "- Bronchiectasis represents a complex clinical challenge that requires a multidisciplinary approach for effective management and treatment improvements. Further understanding of the disease mechanisms, enhancing diagnostic processes, and tailored therapies are vital for future advancements in the care of patients." + ], + "text/plain": [ + "" + ] + }, + "metadata": {}, + "output_type": "display_data" + } + ], + "source": [ + "# Step 4: Print the result of an example pdf\n", + "article_url=input('Please input the pdf URL: \\n')\n", + "summary = summarize(article_url)\n", + "display(Markdown(summary))" + ] + }, + { + "cell_type": "markdown", + "id": "fd2cb395-9e29-438e-9388-5555673b4689", + "metadata": {}, + "source": [ + "# Financial Report Analyst\n", + "#### Step 1: Create your prompts\n", + "\n", + "def craft_user_prompt(article):\n", + " user_prompt = f\"You are looking at a document titled {article.title}\\n Based on the body of the document, provide an impactful summary. Call out important points as bullets and highlughts . 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 a financial report research assistant that specialises in analysing the contents of a financial report and provide summary for investors to \\ \n", + " help adjust investment strategies. Call out important points as bullets and highlights. \\\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": "markdown", + "id": "70cbbffd-bf70-47d1-b5d6-5f929bdd89eb", + "metadata": {}, + "source": [ + "# Medical Report Analyst\n", + "#### 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, Summarise the research article while highliting, Introduction, the problem, possible solution and conclusion. 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 a medical research assistant that analyses the contents of a research article and provides a summary while calling out important points as bullets and quotes. \\\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": "markdown", + "id": "c0bb9579-686a-4277-a139-7dff2c64cc9f", + "metadata": {}, + "source": [ + "# QA Format\n", + "#### 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": "680b45ae-6f3d-43b5-b69a-4e7f4fcca268", + "metadata": {}, + "outputs": [], + "source": [] + }, + { + "cell_type": "code", + "execution_count": null, + "id": "988864cc-08a2-4cfb-a09b-524504ee3803", + "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 +}