|
|
|
@ -40,10 +40,10 @@
|
|
|
|
|
"import openai\n",
|
|
|
|
|
"import pandas as pd\n",
|
|
|
|
|
"import numpy as np\n",
|
|
|
|
|
"import json\n",
|
|
|
|
|
"import os\n",
|
|
|
|
|
"\n",
|
|
|
|
|
"from helpers import OPENAI_API_KEY\n",
|
|
|
|
|
"\n",
|
|
|
|
|
"openai.api_key = OPENAI_API_KEY\n",
|
|
|
|
|
"openai.api_key = os.getenv(\"OPENAI_API_KEY\")\n",
|
|
|
|
|
"COMPLETIONS_MODEL = \"text-davinci-002\""
|
|
|
|
|
]
|
|
|
|
|
},
|
|
|
|
@ -183,19 +183,9 @@
|
|
|
|
|
},
|
|
|
|
|
{
|
|
|
|
|
"cell_type": "code",
|
|
|
|
|
"execution_count": 316,
|
|
|
|
|
"execution_count": 335,
|
|
|
|
|
"metadata": {},
|
|
|
|
|
"outputs": [
|
|
|
|
|
{
|
|
|
|
|
"name": "stdout",
|
|
|
|
|
"output_type": "stream",
|
|
|
|
|
"text": [
|
|
|
|
|
"31\n",
|
|
|
|
|
"8\n",
|
|
|
|
|
"All good\n"
|
|
|
|
|
]
|
|
|
|
|
}
|
|
|
|
|
],
|
|
|
|
|
"outputs": [],
|
|
|
|
|
"source": [
|
|
|
|
|
"def request_completion(prompt):\n",
|
|
|
|
|
" \n",
|
|
|
|
@ -221,7 +211,9 @@
|
|
|
|
|
" \n",
|
|
|
|
|
" return classification\n",
|
|
|
|
|
"\n",
|
|
|
|
|
"import json\n",
|
|
|
|
|
"# This function takes your training and validation outputs from the prepare_data function of the Finetuning API, and\n",
|
|
|
|
|
"# confirms that each have the same number of classes.\n",
|
|
|
|
|
"# If they do not have the same number of classes the fine-tune will fail and return an error\n",
|
|
|
|
|
"\n",
|
|
|
|
|
"def check_finetune_classes(train_file,valid_file):\n",
|
|
|
|
|
"\n",
|
|
|
|
@ -270,18 +262,17 @@
|
|
|
|
|
"outputs": [],
|
|
|
|
|
"source": [
|
|
|
|
|
"zero_shot_prompt = '''You are a data expert working for the National Library of Scotland. \n",
|
|
|
|
|
" You are analysing all transactions over £25,000 in value and classifying them into one of five categories.\n",
|
|
|
|
|
" The five categories are Building Improvement, Literature & Archive, Utility Bills, Professional Services and Software/IT.\n",
|
|
|
|
|
" If you can't tell what it is, say Could not classify\n",
|
|
|
|
|
" \n",
|
|
|
|
|
" Transaction:\n",
|
|
|
|
|
"You are analysing all transactions over £25,000 in value and classifying them into one of five categories.\n",
|
|
|
|
|
"The five categories are Building Improvement, Literature & Archive, Utility Bills, Professional Services and Software/IT.\n",
|
|
|
|
|
"If you can't tell what it is, say Could not classify\n",
|
|
|
|
|
" \n",
|
|
|
|
|
" Supplier: SUPPLIER_NAME\n",
|
|
|
|
|
" Description: DESCRIPTION_TEXT\n",
|
|
|
|
|
" Value: TRANSACTION_VALUE\n",
|
|
|
|
|
"Transaction:\n",
|
|
|
|
|
" \n",
|
|
|
|
|
"Supplier: SUPPLIER_NAME\n",
|
|
|
|
|
"Description: DESCRIPTION_TEXT\n",
|
|
|
|
|
"Value: TRANSACTION_VALUE\n",
|
|
|
|
|
" \n",
|
|
|
|
|
" The classification is:'''"
|
|
|
|
|
"The classification is:'''"
|
|
|
|
|
]
|
|
|
|
|
},
|
|
|
|
|
{
|
|
|
|
|