File size: 3,405 Bytes
7b856a8 4e3dc76 872b692 4e3dc76 f5ec828 4e3dc76 f5ec828 872b692 f5ec828 4e3dc76 f5ec828 872b692 4e3dc76 f5ec828 4e3dc76 f5ec828 4e3dc76 7b856a8 f5ec828 872b692 7b856a8 4e3dc76 7b856a8 872b692 7b856a8 f5ec828 872b692 f5ec828 7b856a8 4e3dc76 7b856a8 4e3dc76 7b856a8 f5ec828 872b692 f5ec828 7b856a8 4e3dc76 f5ec828 7b856a8 f5ec828 872b692 7b856a8 4e3dc76 7b856a8 f5ec828 4e3dc76 872b692 4e3dc76 7b856a8 872b692 7b856a8 4e3dc76 7b856a8 4e3dc76 872b692 4e3dc76 7b856a8 f5ec828 7b856a8 |
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 |
{
"cells": [
{
"cell_type": "code",
"execution_count": null,
"id": "247c85dd",
"metadata": {
"lines_to_next_cell": 2
},
"outputs": [],
"source": [
"!pip install -q git+https://github.com/srush/MiniChain\n",
"!git clone https://github.com/srush/MiniChain; cp -fr MiniChain/examples/* . "
]
},
{
"cell_type": "code",
"execution_count": null,
"id": "d36498d1",
"metadata": {
"lines_to_next_cell": 2
},
"outputs": [],
"source": [
"desc = \"\"\"\n",
"### Typed Extraction\n",
"\n",
"Information extraction that is automatically generated from a typed specification. [](https://colab.research.google.com/github/srush/MiniChain/blob/master/examples/pal.ipynb)\n",
"\n",
"(Novel to MiniChain)\n",
"\"\"\""
]
},
{
"cell_type": "code",
"execution_count": null,
"id": "e894e4fb",
"metadata": {
"lines_to_next_cell": 1
},
"outputs": [],
"source": [
"from minichain import prompt, show, type_to_prompt, OpenAI\n",
"from dataclasses import dataclass\n",
"from typing import List\n",
"from enum import Enum"
]
},
{
"cell_type": "markdown",
"id": "6ac1ff70",
"metadata": {},
"source": [
"Data specification"
]
},
{
"cell_type": "code",
"execution_count": null,
"id": "64a00e69",
"metadata": {},
"outputs": [],
"source": [
"class StatType(Enum):\n",
" POINTS = 1\n",
" REBOUNDS = 2\n",
" ASSISTS = 3\n",
"\n",
"@dataclass\n",
"class Stat:\n",
" value: int\n",
" stat: StatType\n",
"\n",
"@dataclass\n",
"class Player:\n",
" player: str\n",
" stats: List[Stat]"
]
},
{
"cell_type": "code",
"execution_count": null,
"id": "35e0ed85",
"metadata": {},
"outputs": [],
"source": [
"@prompt(OpenAI(), template_file=\"stats.pmpt.tpl\", parser=\"json\")\n",
"def stats(model, passage):\n",
" out = model(dict(passage=passage, typ=type_to_prompt(Player)))\n",
" return [Player(**j) for j in out]"
]
},
{
"cell_type": "code",
"execution_count": null,
"id": "7241bdc6",
"metadata": {
"lines_to_next_cell": 2
},
"outputs": [],
"source": [
"article = open(\"sixers.txt\").read()\n",
"gradio = show(lambda passage: stats(passage),\n",
" examples=[article],\n",
" subprompts=[stats],\n",
" out_type=\"json\",\n",
" description=desc,\n",
")\n",
"if __name__ == \"__main__\":\n",
" gradio.launch()"
]
},
{
"cell_type": "markdown",
"id": "18ed1b96",
"metadata": {},
"source": [
"ExtractionPrompt().show({\"passage\": \"Harden had 10 rebounds.\"},\n",
" '[{\"player\": \"Harden\", \"stats\": {\"value\": 10, \"stat\": 2}}]')"
]
},
{
"cell_type": "markdown",
"id": "02c96e7d",
"metadata": {},
"source": [
"# View the run log."
]
},
{
"cell_type": "markdown",
"id": "0ea427dd",
"metadata": {},
"source": [
"minichain.show_log(\"bash.log\")"
]
}
],
"metadata": {
"jupytext": {
"cell_metadata_filter": "-all",
"main_language": "python",
"notebook_metadata_filter": "-all"
}
},
"nbformat": 4,
"nbformat_minor": 5
}
|