Skip to content

Instantly share code, notes, and snippets.

@brockmanmatt

brockmanmatt/decomposepromptsimple.ipynb

Created July 22, 2020 00:05
Show Gist options
  • Star 0 You must be signed in to star a gist
  • Fork 1 You must be signed in to fork a gist
  • Save brockmanmatt/3a032a9e5915308718a0d2c6d6d58eb2 to your computer and use it in GitHub Desktop.
Save brockmanmatt/3a032a9e5915308718a0d2c6d6d58eb2 to your computer and use it in GitHub Desktop.
Download ZIP
DecomposePromptSimple.ipynb
Display the source blob
Display the rendered blob
Raw
decomposepromptsimple.ipynb
{
"nbformat": 4,
"nbformat_minor": 0,
"metadata": {
"colab": {
"name": "DecomposePromptSimple.ipynb",
"provenance": [],
"collapsed_sections": [],
"authorship_tag": "ABX9TyO+aip1sGoqCtTiGIMK2jN2",
"include_colab_link": true
},
"kernelspec": {
"name": "python3",
"display_name": "Python 3"
}
},
"cells": [
{
"cell_type": "markdown",
"metadata": {
"id": "view-in-github",
"colab_type": "text"
},
"source": [
"<a href=\"https://colab.research.google.com/gist/brockmanmatt/3a032a9e5915308718a0d2c6d6d58eb2/decomposepromptsimple.ipynb\" target=\"_parent\"><img src=\"https://colab.research.google.com/assets/colab-badge.svg\" alt=\"Open In Colab\"/></a>"
]
},
{
"cell_type": "code",
"metadata": {
"id": "J7wnsgT2kPut",
"colab_type": "code",
"colab": {
"resources": {
"http://localhost:8080/nbextensions/google.colab/files.js": {
"data": "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",
"ok": true,
"headers": [
[
"content-type",
"application/javascript"
]
],
"status": 200,
"status_text": ""
}
},
"base_uri": "https://localhost:8080/",
"height": 89
},
"outputId": "744f9fa2-a8df-4294-9366-99596a0c9aa8"
},
"source": [
"from google.colab import files\n",
"uploaded = files.upload()\n",
"print(\"done\")"
],
"execution_count": 1,
"outputs": [
{
"output_type": "display_data",
"data": {
"text/html": [
"\n",
" <input type=\"file\" id=\"files-6f21b578-e5bd-4801-8e17-02dbf33f3b9f\" name=\"files[]\" multiple disabled\n",
" style=\"border:none\" />\n",
" <output id=\"result-6f21b578-e5bd-4801-8e17-02dbf33f3b9f\">\n",
" Upload widget is only available when the cell has been executed in the\n",
" current browser session. Please rerun this cell to enable.\n",
" </output>\n",
" <script src=\"/nbextensions/google.colab/files.js\"></script> "
],
"text/plain": [
"<IPython.core.display.HTML object>"
]
},
"metadata": {
"tags": []
}
},
{
"output_type": "stream",
"text": [
"Saving key.json to key.json\n",
"done\n"
],
"name": "stdout"
}
]
},
{
"cell_type": "markdown",
"metadata": {
"id": "WHPHrUnhpKnI",
"colab_type": "text"
},
"source": [
"I'll install the API"
]
},
{
"cell_type": "code",
"metadata": {
"id": "zq0ltp2xn4yt",
"colab_type": "code",
"colab": {
"base_uri": "https://localhost:8080/",
"height": 292
},
"outputId": "5841588f-d295-47cf-ae00-c2f92b6894c4"
},
"source": [
"!pip install openai\n",
"import openai, json, pandas as pd"
],
"execution_count": 2,
"outputs": [
{
"output_type": "stream",
"text": [
"Collecting openai\n",
"\u001b[?25l Downloading https://files.pythonhosted.org/packages/a8/65/c7461f4c87984534683f480ea5742777bc39bbf5721123194c2d0347dc1f/openai-0.2.4.tar.gz (157kB)\n",
"\r\u001b[K |██ | 10kB 18.0MB/s eta 0:00:01\r\u001b[K |████▏ | 20kB 1.6MB/s eta 0:00:01\r\u001b[K |██████▎ | 30kB 2.2MB/s eta 0:00:01\r\u001b[K |████████▍ | 40kB 2.4MB/s eta 0:00:01\r\u001b[K |██████████▍ | 51kB 1.9MB/s eta 0:00:01\r\u001b[K |████████████▌ | 61kB 2.1MB/s eta 0:00:01\r\u001b[K |██████████████▋ | 71kB 2.4MB/s eta 0:00:01\r\u001b[K |████████████████▊ | 81kB 2.6MB/s eta 0:00:01\r\u001b[K |██████████████████▊ | 92kB 2.8MB/s eta 0:00:01\r\u001b[K |████████████████████▉ | 102kB 2.7MB/s eta 0:00:01\r\u001b[K |███████████████████████ | 112kB 2.7MB/s eta 0:00:01\r\u001b[K |█████████████████████████ | 122kB 2.7MB/s eta 0:00:01\r\u001b[K |███████████████████████████ | 133kB 2.7MB/s eta 0:00:01\r\u001b[K |█████████████████████████████▏ | 143kB 2.7MB/s eta 0:00:01\r\u001b[K |███████████████████████████████▎| 153kB 2.7MB/s eta 0:00:01\r\u001b[K |████████████████████████████████| 163kB 2.7MB/s \n",
"\u001b[?25hRequirement already satisfied: requests>=2.20 in /usr/local/lib/python3.6/dist-packages (from openai) (2.23.0)\n",
"Requirement already satisfied: idna<3,>=2.5 in /usr/local/lib/python3.6/dist-packages (from requests>=2.20->openai) (2.10)\n",
"Requirement already satisfied: certifi>=2017.4.17 in /usr/local/lib/python3.6/dist-packages (from requests>=2.20->openai) (2020.6.20)\n",
"Requirement already satisfied: urllib3!=1.25.0,!=1.25.1,<1.26,>=1.21.1 in /usr/local/lib/python3.6/dist-packages (from requests>=2.20->openai) (1.24.3)\n",
"Requirement already satisfied: chardet<4,>=3.0.2 in /usr/local/lib/python3.6/dist-packages (from requests>=2.20->openai) (3.0.4)\n",
"Building wheels for collected packages: openai\n",
" Building wheel for openai (setup.py) ... \u001b[?25l\u001b[?25hdone\n",
" Created wheel for openai: filename=openai-0.2.4-cp36-none-any.whl size=170709 sha256=10d31d106d5ffc62d9f38aa09eeef5c451a3818ae7a18466070b66b9566c38f3\n",
" Stored in directory: /root/.cache/pip/wheels/74/96/c8/c6e170929c276b836613e1b9985343b501fe455e53d85e7d48\n",
"Successfully built openai\n",
"Installing collected packages: openai\n",
"Successfully installed openai-0.2.4\n"
],
"name": "stdout"
}
]
},
{
"cell_type": "markdown",
"metadata": {
"id": "Q2yE0jcnpMEV",
"colab_type": "text"
},
"source": [
"Loading in key.json that I uploaded; I do this so I don't need to worry about accidently leaking creds if I share the colab (which I'm 99% sure is just a json file that won't expose them)"
]
},
{
"cell_type": "code",
"metadata": {
"id": "bwNXXwHen5x9",
"colab_type": "code",
"colab": {}
},
"source": [
"openai.api_key = json.load(open(\"key.json\", \"r\"))[\"key\"]"
],
"execution_count": 3,
"outputs": []
},
{
"cell_type": "markdown",
"metadata": {
"id": "k67w5H0fpTkT",
"colab_type": "text"
},
"source": [
"Default keyword arguments to pass the aPI"
]
},
{
"cell_type": "code",
"metadata": {
"id": "e1EwpqqJkTYh",
"colab_type": "code",
"colab": {}
},
"source": [
"#arguments to send the API\n",
"kwargs = {\n",
"\"engine\":\"davinci\",\n",
"\"temperature\":0,\n",
"\"max_tokens\":20,\n",
"\"stop\":\"\\n\\n\",\n",
"}"
],
"execution_count": 4,
"outputs": []
},
{
"cell_type": "markdown",
"metadata": {
"id": "zZubgPoOpWDH",
"colab_type": "text"
},
"source": [
"Quick wrapper to automatically save prompts and responses sent for later analysis if needed"
]
},
{
"cell_type": "code",
"metadata": {
"id": "sXTDJx0An9Bl",
"colab_type": "code",
"colab": {}
},
"source": [
"import datetime\n",
"def query(prompt, myKwargs = kwargs):\n",
" \"\"\"\n",
" wrapper for the API to save the prompt and the result\n",
" \"\"\"\n",
"\n",
" r = openai.Completion.create(prompt=prompt, **myKwargs)[\"choices\"][0][\"text\"].strip()\n",
" with open(\"{}.json\".format(datetime.datetime.now().strftime(\"%Y%m%d%s\")), \"w\") as fh:\n",
" json.dump({\"prompt\":prompt, \"response\":r}, fh, indent=4)\n",
" return r"
],
"execution_count": 5,
"outputs": []
},
{
"cell_type": "markdown",
"metadata": {
"id": "EdFXafcJpZ3Q",
"colab_type": "text"
},
"source": [
"Test to make sure my query works"
]
},
{
"cell_type": "code",
"metadata": {
"id": "4SlyKgjyopPn",
"colab_type": "code",
"colab": {
"base_uri": "https://localhost:8080/",
"height": 35
},
"outputId": "ce453a1b-98ba-4fdf-89d7-bb0b6c97e14d"
},
"source": [
"newKwargs = kwargs.copy()\n",
"newKwargs[\"stop\"] = \"\\n\"\n",
"query(\"q: what is 1+1?\\na:\", newKwargs)"
],
"execution_count": 6,
"outputs": [
{
"output_type": "execute_result",
"data": {
"application/vnd.google.colaboratory.intrinsic": {
"type": "string"
},
"text/plain": [
"'2'"
]
},
"metadata": {
"tags": []
},
"execution_count": 6
}
]
},
{
"cell_type": "markdown",
"metadata": {
"id": "s3nk93aAbK-U",
"colab_type": "text"
},
"source": [
"K, so let's start with that thing about the eyes"
]
},
{
"cell_type": "code",
"metadata": {
"id": "rGuVAGtuaHAk",
"colab_type": "code",
"colab": {
"base_uri": "https://localhost:8080/",
"height": 35
},
"outputId": "056bccd7-5fb3-483a-cde3-7fc29cdeaee6"
},
"source": [
"prompt=\"\"\"q: how many eyes does a giraffe have?\n",
"a:\"\"\"\n",
"query(prompt, newKwargs)"
],
"execution_count": 8,
"outputs": [
{
"output_type": "execute_result",
"data": {
"application/vnd.google.colaboratory.intrinsic": {
"type": "string"
},
"text/plain": [
"'4'"
]
},
"metadata": {
"tags": []
},
"execution_count": 8
}
]
},
{
"cell_type": "markdown",
"metadata": {
"id": "sTI5L03LbNJ8",
"colab_type": "text"
},
"source": [
"And if we ask about a biologist, it goes to 4!"
]
},
{
"cell_type": "code",
"metadata": {
"id": "19XS9gBzbBnB",
"colab_type": "code",
"colab": {
"base_uri": "https://localhost:8080/",
"height": 35
},
"outputId": "48564966-26d6-4cd8-c3b9-61e08354b4b0"
},
"source": [
"prompt = \"\"\"These are answers from a biologist\n",
"q: how many eyes does a giraffe have?\n",
"a:\"\"\"\n",
"query(prompt, newKwargs)"
],
"execution_count": 11,
"outputs": [
{
"output_type": "execute_result",
"data": {
"application/vnd.google.colaboratory.intrinsic": {
"type": "string"
},
"text/plain": [
"'two'"
]
},
"metadata": {
"tags": []
},
"execution_count": 11
}
]
},
{
"cell_type": "markdown",
"metadata": {
"id": "XoecrAp-bP3k",
"colab_type": "text"
},
"source": [
"so what's going on here? well, we want to rephrase the question into what's being asked"
]
},
{
"cell_type": "code",
"metadata": {
"id": "uxnQ1BkAbHjy",
"colab_type": "code",
"colab": {
"base_uri": "https://localhost:8080/",
"height": 68
},
"outputId": "f2b1d34c-ce32-4aa1-996e-270d9e0d0ad8"
},
"source": [
"prompt = \"\"\"input: what is the capital of france?\n",
"steps:\n",
"1. what is france\n",
"2. what is the capital of france\n",
"\n",
"input: how many eyes does a giraffe have?\n",
"steps:\"\"\"\n",
"kwargs[\"max_tokens\"] = 150\n",
"response = query(prompt, kwargs)\n",
"print(response)"
],
"execution_count": 104,
"outputs": [
{
"output_type": "stream",
"text": [
"1. what is a giraffe\n",
"2. what is an eye\n",
"3. how many eyes does a giraffe have\n"
],
"name": "stdout"
}
]
},
{
"cell_type": "code",
"metadata": {
"id": "9oVwyL5Dbhuy",
"colab_type": "code",
"colab": {}
},
"source": [
"stack = []"
],
"execution_count": 105,
"outputs": []
},
{
"cell_type": "code",
"metadata": {
"id": "yYiVrVDMgaTo",
"colab_type": "code",
"colab": {}
},
"source": [
"for task in response.split(\"\\n\")[::-1]:\n",
" stack.append(task)"
],
"execution_count": 106,
"outputs": []
},
{
"cell_type": "code",
"metadata": {
"id": "hUfyDyVKgcCr",
"colab_type": "code",
"colab": {
"base_uri": "https://localhost:8080/",
"height": 68
},
"outputId": "ce94ef6f-d43c-46eb-beb7-06488243912e"
},
"source": [
"stack"
],
"execution_count": 107,
"outputs": [
{
"output_type": "execute_result",
"data": {
"text/plain": [
"['3. how many eyes does a giraffe have',\n",
" '2. what is an eye',\n",
" '1. what is a giraffe']"
]
},
"metadata": {
"tags": []
},
"execution_count": 107
}
]
},
{
"cell_type": "code",
"metadata": {
"id": "J30Mlj4Pg1zt",
"colab_type": "code",
"colab": {}
},
"source": [
"newPrompt = \"\"\"q: what is the capital of France?\n",
"a: paris\n",
"\n",
"\"\"\"\n",
"while(len(stack) > 0):\n",
" item = stack.pop()\n",
" newPrompt += \"q: {}\\na:\".format(\".\".join(item.split(\".\")[1:]).strip())\n",
" newResponse = query(newPrompt, kwargs)\n",
" newPrompt += \"{}\\n\\n\".format(newResponse)"
],
"execution_count": 108,
"outputs": []
},
{
"cell_type": "code",
"metadata": {
"id": "vklK8qdxtcGK",
"colab_type": "code",
"colab": {
"base_uri": "https://localhost:8080/",
"height": 34
},
"outputId": "4f67a9be-9565-47af-b350-abde2b4e3d4a"
},
"source": [
"print(newResponse)"
],
"execution_count": 109,
"outputs": [
{
"output_type": "stream",
"text": [
"two\n"
],
"name": "stdout"
}
]
},
{
"cell_type": "code",
"metadata": {
"id": "QfKnFG3ztcsx",
"colab_type": "code",
"colab": {
"base_uri": "https://localhost:8080/",
"height": 51
},
"outputId": "7e211ba3-15af-4a6a-b99f-f1ae95ea2cc9"
},
"source": [
"prompt = \"\"\"input: what is the capital of france?\n",
"steps:\n",
"1. what is france\n",
"2. what is the capital of france\n",
"\n",
"input: who invented the lightbulb\n",
"steps:\n",
"1. what is a lightbulb\n",
"2. who invented the lightbulb\n",
"\n",
"input: {}\n",
"steps:\"\"\"\n",
"kwargs[\"max_tokens\"] = 150\n",
"response = query(prompt.format(\"Who was president of the United States in 1700?\"), kwargs)\n",
"print(response)"
],
"execution_count": 110,
"outputs": [
{
"output_type": "stream",
"text": [
"1. what is the United States\n",
"2. who was president of the United States in 1700\n"
],
"name": "stdout"
}
]
},
{
"cell_type": "code",
"metadata": {
"id": "Dk0uNLbLvg2x",
"colab_type": "code",
"colab": {}
},
"source": [
"for task in response.split(\"\\n\")[::-1]:\n",
" stack.append(task)"
],
"execution_count": 111,
"outputs": []
},
{
"cell_type": "code",
"metadata": {
"id": "lSot_e6qvi5_",
"colab_type": "code",
"colab": {}
},
"source": [
"newPrompt = \"\"\"q: what is the capital of France?\n",
"a: paris\n",
"\n",
"q: what's a smarglash\n",
"a: I don't know\n",
"\n",
"q: what's 5+5?\n",
"a:10\n",
"\n",
"\"\"\"\n",
"allResponses = []\n",
"while(len(stack) > 0):\n",
" item = stack.pop()\n",
" newPrompt += \"q: {}\\na:\".format(\".\".join(item.split(\".\")[1:]).strip())\n",
" newResponse = query(newPrompt, kwargs)\n",
" allResponses.append(newResponse)\n",
" newPrompt += \"{}\\n\\n\".format(newResponse)"
],
"execution_count": 112,
"outputs": []
},
{
"cell_type": "code",
"metadata": {
"id": "e5CtVRKlv22L",
"colab_type": "code",
"colab": {
"base_uri": "https://localhost:8080/",
"height": 34
},
"outputId": "4c7a18f6-2eb0-492b-e844-8c333654f10b"
},
"source": [
"print(newResponse)"
],
"execution_count": 113,
"outputs": [
{
"output_type": "stream",
"text": [
"I don't know\n"
],
"name": "stdout"
}
]
},
{
"cell_type": "code",
"metadata": {
"id": "1GtgCYFXv5KR",
"colab_type": "code",
"colab": {}
},
"source": [
""
],
"execution_count": null,
"outputs": []
}
]
}
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment