brad/LLM_Engineering_OLD
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

Week 1 exercise

Browse Source
This commit is contained in:
Elijah Rwothoromo
2025-08-05 20:42:50 +03:00
parent 3a042500d7
commit 9da9692a9b
7 changed files with 649 additions and 79 deletions
Download Patch File Download Diff File Expand all files Collapse all files

135
week1/week1 EXERCISE.ipynb
View File

@@ -18,7 +18,13 @@
"metadata": {},
"outputs": [],
"source": [
"# imports"
"# imports\n",
"import os, re, requests, json, ollama\n",
"from typing import List\n",
"from dotenv import load_dotenv\n",
"from bs4 import BeautifulSoup\n",
"from IPython.display import Markdown, display, update_display\n",
"from openai import OpenAI"
]
},
{
@@ -41,7 +47,27 @@
"metadata": {},
"outputs": [],
"source": [
"# set up environment"
"# set up environment\n",
"\n",
"headers = {\n",
" \"User-Agent\": \"Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/117.0.0.0 Safari/537.36\"\n",
"}\n",
"\n",
"class Website:\n",
"\n",
" def __init__(self, url):\n",
" \"\"\"\n",
" Create this Website object from the given url using the BeautifulSoup library\n",
" \"\"\"\n",
" self.url = url\n",
" response = requests.get(url, headers=headers)\n",
" soup = BeautifulSoup(response.content, '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",
"openai = OpenAI()\n"
]
},
{
@@ -53,10 +79,68 @@
"source": [
"# here is the question; type over this to ask something new\n",
"\n",
"# question = \"\"\"\n",
"# Please explain what this code does and why:\n",
"# yield from {book.get(\"author\") for book in books if book.get(\"author\")}\n",
"# \"\"\"\n",
"\n",
"question = \"\"\"\n",
"Please explain what this code does and why:\n",
"yield from {book.get(\"author\") for book in books if book.get(\"author\")}\n",
"\"\"\""
"How good at Software Development is Elijah Rwothoromo? \\\n",
"He has a Wordpress site https://rwothoromo.wordpress.com/. \\\n",
"He also has a LinkedIn profile https://www.linkedin.com/in/rwothoromoelaijah/. \\\n",
"What can we learn from him?\n",
"\"\"\"\n"
]
},
{
"cell_type": "code",
"execution_count": null,
"id": "e14fd3a1-0aca-4794-a0e0-57458e111fc9",
"metadata": {},
"outputs": [],
"source": [
"# Process URLs in the question to improve the prompt\n",
"\n",
"# Extract all URLs from the question string using regular expressions\n",
"urls = re.findall(r'https?://[^\\s)]+', question)\n",
"\n",
"# Fetch the content for each URL using the Website class\n",
"scraped_content = []\n",
"for url in urls:\n",
" print(f\"Scraping: {url}\")\n",
" try:\n",
" site = Website(url)\n",
" content = f\"Content from {url}:\\n---\\n{site.text}\\n---\\n\" # delimiter ---\n",
" scraped_content.append(content)\n",
" except Exception as e:\n",
" print(f\"Could not scrape {url}: {e}\")\n",
" scraped_content.append(f\"Could not retrieve content from {url}.\\n\")\n",
"\n",
"# Combine all the scraped text into one string\n",
"all_scraped_text = \"\\n\".join(scraped_content)\n",
"\n",
"# Update the question with the scraped content\n",
"augmented_question = f\"\"\"\n",
"Based on the following information, please answer the user's original question.\n",
"\n",
"--- TEXT FROM WEBSITES ---\n",
"{all_scraped_text}\n",
"--- END TEXT FROM WEBSITES ---\n",
"\n",
"--- ORIGINAL QUESTION ---\n",
"{question}\n",
"\"\"\"\n",
"\n",
"# system prompt to be more accurate for AI to just analyze the provided text.\n",
"system_prompt = \"You are an expert assistant. \\\n",
"Analyze the user's question and the provided text from relevant websites to synthesize a comprehensive answer in markdown format.\\\n",
"Provides a short summary, ignoring text that might be navigation-related.\"\n",
"\n",
"# Create the messages list with the new augmented prompt\n",
"messages = [\n",
" {\"role\": \"system\", \"content\": system_prompt},\n",
" {\"role\": \"user\", \"content\": augmented_question},\n",
"]\n"
]
},
{
@@ -66,7 +150,25 @@
"metadata": {},
"outputs": [],
"source": [
"# Get gpt-4o-mini to answer, with streaming"
"# Get gpt-4o-mini to answer, with streaming\n",
"\n",
"def get_gpt_response(question):\n",
" # return response.choices[0].message.content\n",
"\n",
" stream = openai.chat.completions.create(\n",
" model=MODEL_GPT,\n",
" messages=messages,\n",
" stream=True\n",
" )\n",
" \n",
" response = \"\"\n",
" display_handle = display(Markdown(\"\"), display_id=True)\n",
" for chunk in stream:\n",
" response += chunk.choices[0].delta.content or ''\n",
" response = response.replace(\"```\",\"\").replace(\"markdown\", \"\")\n",
" update_display(Markdown(response), display_id=display_handle.display_id)\n",
"\n",
"get_gpt_response(question)"
]
},
{
@@ -76,8 +178,25 @@
"metadata": {},
"outputs": [],
"source": [
"# Get Llama 3.2 to answer"
"# Get Llama 3.2 to answer\n",
"def get_llama_response(question):\n",
" response = ollama.chat(\n",
" model=MODEL_LLAMA,\n",
" messages=messages,\n",
" stream=False # just get the results, don't stream them\n",
" )\n",
" return response['message']['content']\n",
"\n",
"display(Markdown(get_llama_response(question)))"
]
},
{
"cell_type": "code",
"execution_count": null,
"id": "fa1e9987-7b6d-49c1-9a81-b1a92aceea72",
"metadata": {},
"outputs": [],
"source": []
}
],
"metadata": {
@@ -96,7 +215,7 @@
"name": "python",
"nbconvert_exporter": "python",
"pygments_lexer": "ipython3",
"version": "3.11.11"
"version": "3.11.7"
}
},
"nbformat": 4,