Merge pull request #808 from muthash/stephen/week3-exercise-2
[Bootcamp] Week 3 Synthetic Data Generator (Stephen)
This commit is contained in:
Ed Donner
GitHub
@@ -0,0 +1,216 @@
|
|||||||
|
{
|
||||||
|
"cells": [
|
||||||
|
{
|
||||||
|
"cell_type": "markdown",
|
||||||
|
"id": "c58e628f",
|
||||||
|
"metadata": {},
|
||||||
|
"source": [
|
||||||
|
"\n",
|
||||||
|
"## **Week 3 task.**\n",
|
||||||
|
"Create your own tool that generates synthetic data/test data. Input the type of dataset or products or job postings, etc. and let the tool dream up various data samples.\n",
|
||||||
|
"\n",
|
||||||
|
"https://colab.research.google.com/drive/13wR4Blz3Ot_x0GOpflmvvFffm5XU3Kct?usp=sharing"
|
||||||
|
]
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"cell_type": "code",
|
||||||
|
"execution_count": 2,
|
||||||
|
"id": "0ddde9ed",
|
||||||
|
"metadata": {},
|
||||||
|
"outputs": [],
|
||||||
|
"source": [
|
||||||
|
"# imports\n",
|
||||||
|
"\n",
|
||||||
|
"import os\n",
|
||||||
|
"import requests\n",
|
||||||
|
"import torch\n",
|
||||||
|
"from IPython.display import Markdown, display, update_display\n",
|
||||||
|
"from openai import OpenAI\n",
|
||||||
|
"from huggingface_hub import login\n",
|
||||||
|
"from huggingface_hub import login\n",
|
||||||
|
"from transformers import AutoTokenizer, AutoModelForCausalLM, TextStreamer, BitsAndBytesConfig\n",
|
||||||
|
"from dotenv import load_dotenv\n",
|
||||||
|
"import gradio as gr"
|
||||||
|
]
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"cell_type": "code",
|
||||||
|
"execution_count": null,
|
||||||
|
"id": "cbbc6cc8",
|
||||||
|
"metadata": {},
|
||||||
|
"outputs": [],
|
||||||
|
"source": [
|
||||||
|
"\n",
|
||||||
|
"load_dotenv(override=True)\n",
|
||||||
|
"\n",
|
||||||
|
"openai_api_key = os.getenv('OPENAI_API_KEY')\n",
|
||||||
|
"llama_api_key = \"ollama\"\n",
|
||||||
|
"\n",
|
||||||
|
"# hf_token = userdata.get('HF_TOKEN')\n",
|
||||||
|
"# login(hf_token, add_to_git_credential=True)\n",
|
||||||
|
"\n",
|
||||||
|
"\n",
|
||||||
|
"if openai_api_key:\n",
|
||||||
|
" print(f\"OpenAI API Key exists and begins {openai_api_key[:8]}\")\n",
|
||||||
|
"else:\n",
|
||||||
|
" print(\"OpenAI API Key not set\")\n",
|
||||||
|
"\n",
|
||||||
|
"if llama_api_key:\n",
|
||||||
|
" print(f\"LLama API Key exists\")\n",
|
||||||
|
"else:\n",
|
||||||
|
" print(\"LLama API Key not set\")\n",
|
||||||
|
" \n",
|
||||||
|
"GPT_MODEL = \"gpt-4.1-mini\"\n",
|
||||||
|
"LLAMA_MODEL = \"llama3.1\"\n",
|
||||||
|
"\n",
|
||||||
|
"\n",
|
||||||
|
"openai = OpenAI()\n",
|
||||||
|
"\n",
|
||||||
|
"llama_url = \"http://localhost:11434/v1\"\n",
|
||||||
|
"llama = OpenAI(api_key=llama_api_key, base_url=llama_url)"
|
||||||
|
]
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"cell_type": "code",
|
||||||
|
"execution_count": 12,
|
||||||
|
"id": "ef083ec6",
|
||||||
|
"metadata": {},
|
||||||
|
"outputs": [],
|
||||||
|
"source": [
|
||||||
|
"def generate_with_gpt(user_prompt: str, num_samples: int = 5):\n",
|
||||||
|
" \"\"\"\n",
|
||||||
|
" Generates synthetic data using OpenAI's GPT.\n",
|
||||||
|
" Return a JSON string.\n",
|
||||||
|
" \"\"\"\n",
|
||||||
|
" if not openai:\n",
|
||||||
|
" return json.dumps({\"error\": \"OpenAI client not initialized. Please check your API key.\"}, indent=2)\n",
|
||||||
|
"\n",
|
||||||
|
" try:\n",
|
||||||
|
" response = openai.chat.completions.create(\n",
|
||||||
|
" model=GPT_MODEL,\n",
|
||||||
|
" messages=[\n",
|
||||||
|
" {\"role\": \"system\", \"content\": f\"You are a data generation assistant. Generate a JSON array of exactly {num_samples} objects based on the user's request. The output must be valid JSON only, without any other text or formatting.\"},\n",
|
||||||
|
" {\"role\": \"user\", \"content\": user_prompt}\n",
|
||||||
|
" ],\n",
|
||||||
|
" response_format={\"type\": \"json_object\"}\n",
|
||||||
|
" )\n",
|
||||||
|
" \n",
|
||||||
|
" json_text = response.choices[0].message.content\n",
|
||||||
|
" return json_text\n",
|
||||||
|
" except APIError as e:\n",
|
||||||
|
" return json.dumps({\"error\": f\"Error from OpenAI API: {e.body}\"}, indent=2)\n",
|
||||||
|
" except Exception as e:\n",
|
||||||
|
" return json.dumps({\"error\": f\"An unexpected error occurred: {e}\"}, indent=2)\n",
|
||||||
|
"\n",
|
||||||
|
"def generate_with_gpt(user_prompt: str, num_samples: int = 5):\n",
|
||||||
|
" \"\"\"\n",
|
||||||
|
" Generates synthetic data using OpenAI's GPT.\n",
|
||||||
|
" Return a JSON string.\n",
|
||||||
|
" \"\"\"\n",
|
||||||
|
" if not openai:\n",
|
||||||
|
" return json.dumps({\"error\": \"OpenAI client not initialized. Please check your API key.\"}, indent=2)\n",
|
||||||
|
"\n",
|
||||||
|
" try:\n",
|
||||||
|
" response = openai.chat.completions.create(\n",
|
||||||
|
" model=GPT_MODEL,\n",
|
||||||
|
" messages=[\n",
|
||||||
|
" {\"role\": \"system\", \"content\": f\"You are a data generation assistant. Generate a JSON array of exactly {num_samples} objects based on the user's request. The output must be valid JSON only, without any other text or formatting.\"},\n",
|
||||||
|
" {\"role\": \"user\", \"content\": user_prompt}\n",
|
||||||
|
" ],\n",
|
||||||
|
" response_format={\"type\": \"json_object\"}\n",
|
||||||
|
" )\n",
|
||||||
|
" \n",
|
||||||
|
" json_text = response.choices[0].message.content\n",
|
||||||
|
" return json_text\n",
|
||||||
|
" except APIError as e:\n",
|
||||||
|
" return json.dumps({\"error\": f\"Error from OpenAI API: {e.body}\"}, indent=2)\n",
|
||||||
|
" except Exception as e:\n",
|
||||||
|
" return json.dumps({\"error\": f\"An unexpected error occurred: {e}\"}, indent=2)"
|
||||||
|
]
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"cell_type": "code",
|
||||||
|
"execution_count": 13,
|
||||||
|
"id": "b98f84d8",
|
||||||
|
"metadata": {},
|
||||||
|
"outputs": [],
|
||||||
|
"source": [
|
||||||
|
"def generate_data(user_prompt, model_choice):\n",
|
||||||
|
" \"\"\"\n",
|
||||||
|
" Wrapper function that calls the appropriate generation function based on model choice.\n",
|
||||||
|
" \"\"\"\n",
|
||||||
|
" if not user_prompt:\n",
|
||||||
|
" return json.dumps({\"error\": \"Please provide a description for the data.\"}, indent=2)\n",
|
||||||
|
"\n",
|
||||||
|
" if model_choice == f\"Hugging Face ({LLAMA_MODEL})\":\n",
|
||||||
|
" return generate_with_llama(user_prompt)\n",
|
||||||
|
" elif model_choice == f\"OpenAI ({GPT_MODEL})\":\n",
|
||||||
|
" return generate_with_gpt(user_prompt)\n",
|
||||||
|
" else:\n",
|
||||||
|
" return json.dumps({\"error\": \"Invalid model choice.\"}, indent=2)"
|
||||||
|
]
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"cell_type": "code",
|
||||||
|
"execution_count": null,
|
||||||
|
"id": "adbc19a8",
|
||||||
|
"metadata": {},
|
||||||
|
"outputs": [],
|
||||||
|
"source": [
|
||||||
|
"# Gradio UI\n",
|
||||||
|
"with gr.Blocks(theme=gr.themes.Glass(), title=\"Synthetic Data Generator\") as ui:\n",
|
||||||
|
" gr.Markdown(\"# Synthetic Data Generator\")\n",
|
||||||
|
" gr.Markdown(\"Describe the type of data you need, select a model, and click 'Generate'.\")\n",
|
||||||
|
"\n",
|
||||||
|
" with gr.Row():\n",
|
||||||
|
" with gr.Column(scale=3):\n",
|
||||||
|
" data_prompt = gr.Textbox(\n",
|
||||||
|
" lines=5,\n",
|
||||||
|
" label=\"Data Prompt\",\n",
|
||||||
|
" placeholder=\"e.g., a list of customer profiles with name, email, and a favorite product\"\n",
|
||||||
|
" )\n",
|
||||||
|
" \n",
|
||||||
|
" with gr.Column(scale=1):\n",
|
||||||
|
" model_choice = gr.Radio(\n",
|
||||||
|
" [f\"Hugging Face ({LLAMA_MODEL})\", f\"OpenAI ({GPT_MODEL})\"],\n",
|
||||||
|
" label=\"Choose a Model\",\n",
|
||||||
|
" value=f\"Hugging Face ({LLAMA_MODEL})\"\n",
|
||||||
|
" )\n",
|
||||||
|
" \n",
|
||||||
|
" generate_btn = gr.Button(\"Generate Data\")\n",
|
||||||
|
" \n",
|
||||||
|
" with gr.Row():\n",
|
||||||
|
" output_json = gr.JSON(label=\"Generated Data\")\n",
|
||||||
|
" \n",
|
||||||
|
" generate_btn.click(\n",
|
||||||
|
" fn=generate_data,\n",
|
||||||
|
" inputs=[data_prompt, model_choice],\n",
|
||||||
|
" outputs=output_json\n",
|
||||||
|
" )\n",
|
||||||
|
"\n",
|
||||||
|
"ui.launch(inbrowser=True, debug=True)"
|
||||||
|
]
|
||||||
|
}
|
||||||
|
],
|
||||||
|
"metadata": {
|
||||||
|
"kernelspec": {
|
||||||
|
"display_name": ".venv",
|
||||||
|
"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": "3.12.12"
|
||||||
|
}
|
||||||
|
},
|
||||||
|
"nbformat": 4,
|
||||||
|
"nbformat_minor": 5
|
||||||
|
}
|
||||||
Reference in New Issue
Block a user