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

remove redundant changes

Browse Source
This commit is contained in:
Elijah Rwothoromo
2025-08-05 21:47:40 +03:00
parent ae7d307063
commit c577b86757
4 changed files with 257 additions and 290 deletions
Download Patch File Download Diff File Expand all files Collapse all files

235
week1/community-contributions/rwothoromo/week1/week1 EXERCISE.ipynb Normal file
View File

@@ -0,0 +1,235 @@
{
"cells": [
{
"cell_type": "markdown",
"id": "fe12c203-e6a6-452c-a655-afb8a03a4ff5",
"metadata": {},
"source": [
"# End of week 1 exercise\n",
"\n",
"To demonstrate your familiarity with OpenAI API, and also Ollama, build a tool that takes a technical question, \n",
"and responds with an explanation. This is a tool that you will be able to use yourself during the course!"
]
},
{
"cell_type": "code",
"execution_count": null,
"id": "c1070317-3ed9-4659-abe3-828943230e03",
"metadata": {},
"outputs": [],
"source": [
"# imports\n",
"# Important Pull request ref: https://chatgpt.com/share/677a9cb5-c64c-8012-99e0-e06e88afd293\n",
"\n",
"import re, requests, ollama\n",
"from bs4 import BeautifulSoup\n",
"from IPython.display import Markdown, display, update_display\n",
"from openai import OpenAI"
]
},
{
"cell_type": "code",
"execution_count": null,
"id": "4a456906-915a-4bfd-bb9d-57e505c5093f",
"metadata": {},
"outputs": [],
"source": [
"# constants\n",
"\n",
"MODEL_GPT = 'gpt-4o-mini'\n",
"MODEL_LLAMA = 'llama3.2'"
]
},
{
"cell_type": "code",
"execution_count": null,
"id": "a8d7923c-5f28-4c30-8556-342d7c8497c1",
"metadata": {},
"outputs": [],
"source": [
"# 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"
]
},
{
"cell_type": "code",
"execution_count": null,
"id": "3f0d0137-52b0-47a8-81a8-11a90a010798",
"metadata": {},
"outputs": [],
"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",
"# Popular dev site https://projecteuler.net/\n",
"# \"\"\"\n",
"\n",
"question = \"\"\"\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",
"# print(urls)\n",
"\n",
"if len(urls) > 0:\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",
" updated_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",
"else:\n",
" updated_question = question\n",
"\n",
"# print(updated_question)\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",
"Provide a short summary, ignoring text that might be navigation-related.\"\n",
"\n",
"# Create the messages list with the newly updated prompt\n",
"messages = [\n",
" {\"role\": \"system\", \"content\": system_prompt},\n",
" {\"role\": \"user\", \"content\": updated_question},\n",
"]\n"
]
},
{
"cell_type": "code",
"execution_count": null,
"id": "60ce7000-a4a5-4cce-a261-e75ef45063b4",
"metadata": {},
"outputs": [],
"source": [
"# Get gpt-4o-mini to answer, with streaming\n",
"\n",
"def get_gpt_response(question):\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)"
]
},
{
"cell_type": "code",
"execution_count": null,
"id": "8f7c8ea8-4082-4ad0-8751-3301adcf6538",
"metadata": {},
"outputs": [],
"source": [
"# Get Llama 3.2 to answer\n",
"\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": {
"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": "3.11.7"
}
},
"nbformat": 4,
"nbformat_minor": 5
}

94
week1/day1.ipynb
View File

@@ -497,26 +497,6 @@
"display_summary(\"https://anthropic.com\")"
]
},
{
"cell_type": "code",
"execution_count": null,
"id": "5a904323-acd9-4c8e-9a17-70df76184590",
"metadata": {},
"outputs": [],
"source": [
"display_summary(\"https://rwothoromo.wordpress.com/\")"
]
},
{
"cell_type": "code",
"execution_count": null,
"id": "a66c9fe8-c26a-49dd-9bc4-9efffc638f95",
"metadata": {},
"outputs": [],
"source": [
"display_summary(\"https://openai.com\")"
]
},
{
"cell_type": "markdown",
"id": "c951be1a-7f1b-448f-af1f-845978e47e2c",
@@ -558,55 +538,23 @@
"source": [
"# Step 1: Create your prompts\n",
"\n",
"system_prompt = \"You are a professional assistant\"\n",
"system_prompt = \"something here\"\n",
"user_prompt = \"\"\"\n",
"Review this conversation and provide a comprehensive summary. Also, suggest how much better the converation could have gone:\n",
"\n",
"Dear Dev Contact,\n",
"\n",
"I hope this message finds you well.\n",
"I would like to share that I have proficiency in front-end design tools, particularly Figma, react and Angular. At this stage, I am keenly interested in finding opportunities to apply these skills professionally.\n",
"\n",
"If you are aware of any companies, projects, or platforms seeking enterprise in front-end design, I would be grateful for any advice or recommendations you might kindly provide.\n",
"\n",
"Thank you very much for your time and consideration.\n",
"\n",
"Hello Job Seeker,\n",
"\n",
"I hope you are doing well.\n",
"\n",
"Dev Contact: The last role (3 months gig) I saw was looking for a junior PHP Developer. Does your CV include that?\n",
"\n",
"Hello Dev Contact \n",
"Thank you for your feedback.\n",
"Yes my CV has PHP as one of my skill set. Can I share it with you?\n",
"\n",
"Dev Contact: They said \"It's late. Interviews were on Monday\"\n",
"\n",
"Hello Dev Contact\n",
"\n",
"Thanks for the update. When you hear of any opportunity please let me know.\n",
"\n",
"Dev Contact: For now, check out https://refactory.academy/courses/refactory-apprenticeship/\n",
" Lots of text\n",
" Can be pasted here\n",
"\"\"\"\n",
"\n",
"# Step 2: Make the messages list\n",
"\n",
"messages = [\n",
" {\"role\": \"system\", \"content\": system_prompt},\n",
" {\"role\": \"user\", \"content\": user_prompt},\n",
"] # fill this in\n",
"messages = [] # fill this in\n",
"\n",
"# Step 3: Call OpenAI\n",
"\n",
"response = openai.chat.completions.create(\n",
" model = \"gpt-4o-mini\",\n",
" messages = messages\n",
")\n",
"response =\n",
"\n",
"# Step 4: print the result\n",
"\n",
"print(response.choices[0].message.content)"
"print("
]
},
{
@@ -640,34 +588,6 @@
"id": "f4484fcf-8b39-4c3f-9674-37970ed71988",
"metadata": {},
"outputs": [],
"source": [
"# To perform summaries using a model running locally\n",
"import ollama\n",
"\n",
"# OLLAMA_API = \"http://localhost:11434/api/chat\"\n",
"# HEADERS = {\"Content-Type\": \"application/json\"}\n",
"MODEL = \"llama3.2\"\n",
"\n",
"\n",
"def summarize_with_local_model(url):\n",
" website = Website(url)\n",
" messages = messages_for(website)\n",
" response = ollama.chat(\n",
" model=MODEL,\n",
" messages=messages,\n",
" stream=False # just get the results, don't stream them\n",
" )\n",
" return response['message']['content']\n",
"\n",
"display(Markdown(summarize_with_local_model(\"https://rwothoromo.wordpress.com/\")))"
]
},
{
"cell_type": "code",
"execution_count": null,
"id": "e76cbf31-2a82-40b8-b2e7-e2ceae7483ed",
"metadata": {},
"outputs": [],
"source": []
}
],
@@ -687,7 +607,7 @@
"name": "python",
"nbconvert_exporter": "python",
"pygments_lexer": "ipython3",
"version": "3.11.7"
"version": "3.11.12"
}
},
"nbformat": 4,

71
week1/day5.ipynb
View File

@@ -144,15 +144,6 @@
" {\"type\": \"careers page\", \"url\": \"https://another.full.url/careers\"}\n",
" ]\n",
"}\n",
"\"\"\"\n",
"link_system_prompt += \"And this example:\"\n",
"link_system_prompt += \"\"\"\n",
"{\n",
" \"links\": [\n",
" {\"type\": \"for-you page\", \"url\": \"https://full.url/goes/here/services\"},\n",
" {\"type\": \"speak-to-a-human page\", \"url\": \"https://another.full.url/contact-us\"}\n",
" ]\n",
"}\n",
"\"\"\""
]
},
@@ -222,9 +213,6 @@
"source": [
"# Anthropic has made their site harder to scrape, so I'm using HuggingFace..\n",
"\n",
"# anthropic = Website(\"https://anthropic.com\")\n",
"# anthropic.links\n",
"# get_links(\"https://anthropic.com\")\n",
"huggingface = Website(\"https://huggingface.co\")\n",
"huggingface.links"
]
@@ -284,15 +272,15 @@
"metadata": {},
"outputs": [],
"source": [
"# system_prompt = \"You are an assistant that analyzes the contents of several relevant pages from a company website \\\n",
"# and creates a short brochure about the company for prospective customers, investors and recruits. Respond in markdown.\\\n",
"# Include details of company culture, customers and careers/jobs if you have the information.\"\n",
"system_prompt = \"You are an assistant that analyzes the contents of several relevant pages from a company website \\\n",
"and creates a short brochure about the company for prospective customers, investors and recruits. Respond in markdown.\\\n",
"Include details of company culture, customers and careers/jobs if you have the information.\"\n",
"\n",
"# Or uncomment the lines below for a more humorous brochure - this demonstrates how easy it is to incorporate 'tone':\n",
"\n",
"system_prompt = \"You are an assistant that analyzes the contents of several relevant pages from a company website \\\n",
"and creates a short humorous, entertaining, jokey brochure about the company for prospective customers, investors and recruits. Respond in markdown.\\\n",
"Include details of company culture, customers and careers/jobs if you have the information.\"\n"
"# system_prompt = \"You are an assistant that analyzes the contents of several relevant pages from a company website \\\n",
"# and creates a short humorous, entertaining, jokey brochure about the company for prospective customers, investors and recruits. Respond in markdown.\\\n",
"# Include details of company culture, customers and careers/jobs if you have the information.\"\n"
]
},
{
@@ -305,7 +293,6 @@
"def get_brochure_user_prompt(company_name, url):\n",
" user_prompt = f\"You are looking at a company called: {company_name}\\n\"\n",
" user_prompt += f\"Here are the contents of its landing page and other relevant pages; use this information to build a short brochure of the company in markdown.\\n\"\n",
" user_prompt += f\"Keep the details brief or concise, factoring in that they would be printed on a simple hand-out flyer.\\n\"\n",
" user_prompt += get_all_details(url)\n",
" user_prompt = user_prompt[:5_000] # Truncate if more than 5,000 characters\n",
" return user_prompt"
@@ -337,28 +324,6 @@
" ],\n",
" )\n",
" result = response.choices[0].message.content\n",
" # display(Markdown(result))\n",
" # print(result)\n",
" return result"
]
},
{
"cell_type": "code",
"execution_count": null,
"id": "0029e063-0c07-4712-82d9-536ec3579e80",
"metadata": {},
"outputs": [],
"source": [
"def translate_brochure(brochure, language):\n",
" system_prompt_for_language = \"You're an expert in \" + language + \". Translate the brochure!\"\n",
" response = openai.chat.completions.create(\n",
" model=MODEL,\n",
" messages=[\n",
" {\"role\": \"system\", \"content\": system_prompt_for_language},\n",
" {\"role\": \"user\", \"content\": brochure}\n",
" ],\n",
" )\n",
" result = response.choices[0].message.content\n",
" display(Markdown(result))"
]
},
@@ -372,28 +337,6 @@
"create_brochure(\"HuggingFace\", \"https://huggingface.co\")"
]
},
{
"cell_type": "code",
"execution_count": null,
"id": "f8371bf5-c4c0-4e52-9a2a-066d994b0510",
"metadata": {},
"outputs": [],
"source": [
"brochure = create_brochure(\"Paint and Sip Uganda\", \"https://paintandsipuganda.com/\")\n",
"# translate_brochure(brochure, \"Spanish\")\n",
"translate_brochure(brochure, \"Swahili\")"
]
},
{
"cell_type": "code",
"execution_count": null,
"id": "34e03db6-61d0-4fc5-bf66-4f679b9befde",
"metadata": {},
"outputs": [],
"source": [
"create_brochure(\"Wabeh\", \"https://wabeh.com/\")"
]
},
{
"cell_type": "markdown",
"id": "61eaaab7-0b47-4b29-82d4-75d474ad8d18",
@@ -558,7 +501,7 @@
"name": "python",
"nbconvert_exporter": "python",
"pygments_lexer": "ipython3",
"version": "3.11.7"
"version": "3.11.13"
}
},
"nbformat": 4,

147
week1/week1 EXERCISE.ipynb
View File

@@ -18,13 +18,7 @@
"metadata": {},
"outputs": [],
"source": [
"# imports\n",
"# Important Pull request ref: https://chatgpt.com/share/677a9cb5-c64c-8012-99e0-e06e88afd293\n",
"\n",
"import re, requests, ollama\n",
"from bs4 import BeautifulSoup\n",
"from IPython.display import Markdown, display, update_display\n",
"from openai import OpenAI"
"# imports"
]
},
{
@@ -47,27 +41,7 @@
"metadata": {},
"outputs": [],
"source": [
"# 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"
"# set up environment"
]
},
{
@@ -79,81 +53,10 @@
"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",
"# Popular dev site https://projecteuler.net/\n",
"# \"\"\"\n",
"\n",
"question = \"\"\"\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",
"# print(urls)\n",
"\n",
"if len(urls) > 0:\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",
" updated_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",
"else:\n",
" updated_question = question\n",
"\n",
"# print(updated_question)\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",
"Provide a short summary, ignoring text that might be navigation-related.\"\n",
"\n",
"# Create the messages list with the newly updated prompt\n",
"messages = [\n",
" {\"role\": \"system\", \"content\": system_prompt},\n",
" {\"role\": \"user\", \"content\": updated_question},\n",
"]\n"
"Please explain what this code does and why:\n",
"yield from {book.get(\"author\") for book in books if book.get(\"author\")}\n",
"\"\"\""
]
},
{
@@ -163,23 +66,7 @@
"metadata": {},
"outputs": [],
"source": [
"# Get gpt-4o-mini to answer, with streaming\n",
"\n",
"def get_gpt_response(question):\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)"
"# Get gpt-4o-mini to answer, with streaming"
]
},
{
@@ -189,26 +76,8 @@
"metadata": {},
"outputs": [],
"source": [
"# Get Llama 3.2 to answer\n",
"\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)))"
"# Get Llama 3.2 to answer"
]
},
{
"cell_type": "code",
"execution_count": null,
"id": "fa1e9987-7b6d-49c1-9a81-b1a92aceea72",
"metadata": {},
"outputs": [],
"source": []
}
],
"metadata": {
@@ -227,7 +96,7 @@
"name": "python",
"nbconvert_exporter": "python",
"pygments_lexer": "ipython3",
"version": "3.11.7"
"version": "3.11.11"
}
},
"nbformat": 4,