From the uDemy course on LLM engineering.
https://www.udemy.com/course/llm-engineering-master-ai-and-large-language-models
You can not select more than 25 topics
Topics must start with a letter or number, can include dashes ('-') and can be up to 35 characters long.
332 lines
11 KiB
332 lines
11 KiB
{ |
|
"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": "markdown", |
|
"id": "c70e5ab1", |
|
"metadata": {}, |
|
"source": [ |
|
"## **1. Get a response from your favorite AI Tutor** " |
|
] |
|
}, |
|
{ |
|
"cell_type": "code", |
|
"execution_count": 1, |
|
"id": "c1070317-3ed9-4659-abe3-828943230e03", |
|
"metadata": {}, |
|
"outputs": [], |
|
"source": [ |
|
"import os\n", |
|
"from openai import OpenAI\n", |
|
"import json\n", |
|
"from dotenv import load_dotenv\n", |
|
"from IPython.display import Markdown, display, update_display" |
|
] |
|
}, |
|
{ |
|
"cell_type": "code", |
|
"execution_count": null, |
|
"id": "65dace69", |
|
"metadata": {}, |
|
"outputs": [], |
|
"source": [ |
|
"load_dotenv()\n", |
|
"api_key = os.getenv('OPENAI_API_KEY')\n", |
|
"\n", |
|
"if api_key and api_key.startswith('sk-proj-') and len(api_key) > 10:\n", |
|
" print(\"API key looks good so far\")\n", |
|
"else:\n", |
|
" print(\"There might be a problem with your API key? Please visit the troubleshooting notebook!\")" |
|
] |
|
}, |
|
{ |
|
"cell_type": "code", |
|
"execution_count": 3, |
|
"id": "4a456906-915a-4bfd-bb9d-57e505c5093f", |
|
"metadata": {}, |
|
"outputs": [], |
|
"source": [ |
|
"# constants\n", |
|
"\n", |
|
"MODEL_GPT = 'gpt-4o-mini'\n", |
|
"MODEL_LLAMA = 'llama3.2'\n", |
|
"\n", |
|
"openai = OpenAI()\n", |
|
"\n", |
|
"ollama_via_openai = OpenAI(base_url='http://localhost:11434/v1', api_key='ollama')" |
|
] |
|
}, |
|
{ |
|
"cell_type": "code", |
|
"execution_count": 38, |
|
"id": "3673d863", |
|
"metadata": {}, |
|
"outputs": [], |
|
"source": [ |
|
"system_prompt = \"\"\"You are the software engnieer, phd in mathematics, machine learning engnieer, and other topics\"\"\"\n", |
|
"system_prompt += \"\"\"\n", |
|
"When responding, always use Markdown for formatting. For any code, use well-structured code blocks with syntax highlighting,\n", |
|
"For instance:\n", |
|
"```python\n", |
|
"\n", |
|
"sample_list = [for i in range(10)]\n", |
|
"```\n", |
|
"Another example\n", |
|
"```javascript\n", |
|
" function displayMessage() {\n", |
|
" alert(\"Hello, welcome to JavaScript!\");\n", |
|
" }\n", |
|
"\n", |
|
"```\n", |
|
"\n", |
|
"Break down explanations into clear, numbered steps for better understanding. \n", |
|
"Highlight important terms using inline code formatting (e.g., `function_name`, `variable`).\n", |
|
"Provide examples for any concepts and ensure all examples are concise, clear, and relevant.\n", |
|
"Your goal is to create visually appealing, easy-to-read, and informative responses.\n", |
|
"\n", |
|
"\"\"\"\n" |
|
] |
|
}, |
|
{ |
|
"cell_type": "code", |
|
"execution_count": 39, |
|
"id": "1df78d41", |
|
"metadata": {}, |
|
"outputs": [], |
|
"source": [ |
|
"def tutor_user_prompt(question):\n", |
|
" # Ensure the question is properly appended to the user prompt.\n", |
|
" user_prompt = (\n", |
|
" \"Please carefully explain the following question in a step-by-step manner for clarity:\\n\\n\"\n", |
|
" )\n", |
|
" user_prompt += question\n", |
|
" return user_prompt" |
|
] |
|
}, |
|
{ |
|
"cell_type": "code", |
|
"execution_count": 43, |
|
"id": "6dccbccb", |
|
"metadata": {}, |
|
"outputs": [], |
|
"source": [ |
|
"\n", |
|
"\n", |
|
"def askTutor(question, MODEL):\n", |
|
" # Generate the user prompt dynamically.\n", |
|
" user_prompt = tutor_user_prompt(question)\n", |
|
" \n", |
|
" # OpenAI API call to generate response.\n", |
|
" if MODEL == 'gpt-4o-mini':\n", |
|
" print(f'You are getting response from {MODEL}')\n", |
|
" stream = openai.chat.completions.create(\n", |
|
" model=MODEL,\n", |
|
" messages=[\n", |
|
" {\"role\": \"system\", \"content\": system_prompt},\n", |
|
" {\"role\": \"user\", \"content\": user_prompt}\n", |
|
" ],\n", |
|
" stream=True\n", |
|
" )\n", |
|
" else:\n", |
|
" MODEL == 'llama3.2'\n", |
|
" print(f'You are getting response from {MODEL}')\n", |
|
" stream = ollama_via_openai.chat.completions.create(\n", |
|
" model=MODEL,\n", |
|
" messages=[\n", |
|
" {\"role\": \"system\", \"content\": system_prompt},\n", |
|
" {\"role\": \"user\", \"content\": user_prompt}\n", |
|
" ],\n", |
|
" stream=True\n", |
|
" )\n", |
|
"\n", |
|
" # Initialize variables for response processing.\n", |
|
" response = \"\"\n", |
|
" display_handle = display(Markdown(\"\"), display_id=True)\n", |
|
" \n", |
|
" # Process the response stream and update display dynamically.\n", |
|
" for chunk in stream:\n", |
|
" # Safely access the content attribute.\n", |
|
" response_chunk = getattr(chunk.choices[0].delta, \"content\", \"\")\n", |
|
" if response_chunk: # Check if response_chunk is not None or empty\n", |
|
" response += response_chunk\n", |
|
" # No replacement of Markdown formatting here!\n", |
|
" update_display(Markdown(response), display_id=display_handle.display_id)\n" |
|
] |
|
}, |
|
{ |
|
"cell_type": "code", |
|
"execution_count": 44, |
|
"id": "a8d7923c-5f28-4c30-8556-342d7c8497c1", |
|
"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", |
|
"\"\"\"" |
|
] |
|
}, |
|
{ |
|
"cell_type": "code", |
|
"execution_count": null, |
|
"id": "3f0d0137-52b0-47a8-81a8-11a90a010798", |
|
"metadata": {}, |
|
"outputs": [], |
|
"source": [ |
|
"askTutor(question=question, MODEL=MODEL_GPT)" |
|
] |
|
}, |
|
{ |
|
"cell_type": "markdown", |
|
"id": "b79f9479", |
|
"metadata": {}, |
|
"source": [ |
|
"## **2. Using both LLMs collaboratively approach**" |
|
] |
|
}, |
|
{ |
|
"cell_type": "markdown", |
|
"id": "80e3c8f5", |
|
"metadata": {}, |
|
"source": [ |
|
"- I thought about like similar the idea of a RAG (Retrieval-Augmented Generation) approach, is an excellent idea to improve responses by refining the user query and producing a polished, detailed final answer. Two LLM talking each other its cool!!! Here's how we can implement this:\n", |
|
"\n", |
|
"**Updated Concept:**\n", |
|
"1. Refine Query with Ollama:\n", |
|
" - Use Ollama to refine the raw user query into a well-structured prompt.\n", |
|
" - This is especially helpful when users input vague or poorly structured queries.\n", |
|
"2. Generate Final Response with GPT:\n", |
|
" - Pass the refined prompt from Ollama to GPT to generate the final, detailed, and polished response.\n", |
|
"3. Return the Combined Output:\n", |
|
" - Combine the input, refined query, and the final response into a single display to ensure clarity." |
|
] |
|
}, |
|
{ |
|
"cell_type": "code", |
|
"execution_count": 59, |
|
"id": "60f5ac2d", |
|
"metadata": {}, |
|
"outputs": [], |
|
"source": [ |
|
"def refine_with_ollama(raw_question):\n", |
|
" \"\"\"\n", |
|
" Use Ollama to refine the user's raw question into a well-structured prompt.\n", |
|
" \"\"\"\n", |
|
" print(\"Refining the query using Ollama...\")\n", |
|
" messages = [\n", |
|
" {\"role\": \"system\", \"content\": \"You are a helpful assistant. Refine and structure the following user input.\"},\n", |
|
"\n", |
|
" {\"role\": \"user\", \"content\": raw_question},\n", |
|
" ]\n", |
|
" response = ollama_via_openai.chat.completions.create(\n", |
|
" model=MODEL_LLAMA,\n", |
|
" messages=messages,\n", |
|
" stream=False # Non-streamed refinement\n", |
|
" )\n", |
|
" refined_query = response.choices[0].message.content\n", |
|
" return refined_query" |
|
] |
|
}, |
|
{ |
|
"cell_type": "code", |
|
"execution_count": 60, |
|
"id": "2aa4c9f6", |
|
"metadata": {}, |
|
"outputs": [], |
|
"source": [ |
|
"def ask_with_ollama_and_gpt(raw_question):\n", |
|
" \"\"\"\n", |
|
" Use Ollama to refine the user query and GPT to generate the final response.\n", |
|
" \"\"\"\n", |
|
" # Step 1: Refine the query using Ollama\n", |
|
" refined_query = refine_with_ollama(raw_question)\n", |
|
" \n", |
|
" # Step 2: Generate final response with GPT\n", |
|
" print(\"Generating the final response using GPT...\")\n", |
|
" messages = [\n", |
|
" {\"role\": \"system\", \"content\": system_prompt},\n", |
|
" {\"role\": \"user\", \"content\": refined_query},\n", |
|
" ]\n", |
|
" stream = openai.chat.completions.create(\n", |
|
" model=MODEL_GPT,\n", |
|
" messages=messages,\n", |
|
" stream=True # Stream response for dynamic display\n", |
|
" )\n", |
|
"\n", |
|
" # Step 3: Combine responses\n", |
|
" response = \"\"\n", |
|
" display_handle = display(Markdown(f\"### Refined Query:\\n\\n{refined_query}\\n\\n---\\n\\n### Final Response:\"), display_id=True)\n", |
|
" for chunk in stream:\n", |
|
" response_chunk = getattr(chunk.choices[0].delta, \"content\", \"\")\n", |
|
" if response_chunk:\n", |
|
" response += response_chunk\n", |
|
" update_display(Markdown(f\"### Refined Query:\\n\\n{refined_query}\\n\\n---\\n\\n### Final Response:\\n\\n{response}\"), display_id=display_handle.display_id)" |
|
] |
|
}, |
|
{ |
|
"cell_type": "code", |
|
"execution_count": 61, |
|
"id": "4150e857", |
|
"metadata": {}, |
|
"outputs": [], |
|
"source": [ |
|
"# Example Usage\n", |
|
"question = \"\"\"\n", |
|
"Please explain what this code does:\n", |
|
"yield from {book.get(\"author\") for book in books if book.get(\"author\")}\n", |
|
"\"\"\"" |
|
] |
|
}, |
|
{ |
|
"cell_type": "code", |
|
"execution_count": null, |
|
"id": "f2b8935f", |
|
"metadata": {}, |
|
"outputs": [], |
|
"source": [ |
|
"ask_with_ollama_and_gpt(raw_question=question)" |
|
] |
|
}, |
|
{ |
|
"cell_type": "code", |
|
"execution_count": null, |
|
"id": "086a5294", |
|
"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 |
|
}
|
|
|