openai/openai-python
Publicmirrored fromhttps://github.com/openai/openai-pythonAvailable
examples/embeddings/Get_embeddings.ipynb
107lines · modecode
| 1 | { |
| 2 | "cells": [ |
| 3 | { |
| 4 | "cell_type": "markdown", |
| 5 | "metadata": {}, |
| 6 | "source": [ |
| 7 | "## Get embeddings\n", |
| 8 | "\n", |
| 9 | "The function `get_embedding` will give us an embedding for an input text." |
| 10 | ] |
| 11 | }, |
| 12 | { |
| 13 | "cell_type": "code", |
| 14 | "execution_count": 1, |
| 15 | "metadata": {}, |
| 16 | "outputs": [ |
| 17 | { |
| 18 | "data": { |
| 19 | "text/plain": [ |
| 20 | "12288" |
| 21 | ] |
| 22 | }, |
| 23 | "execution_count": 1, |
| 24 | "metadata": {}, |
| 25 | "output_type": "execute_result" |
| 26 | } |
| 27 | ], |
| 28 | "source": [ |
| 29 | "import openai\n", |
| 30 | "\n", |
| 31 | "embedding = openai.Embedding.create(input=\"Sample document text goes here\", engine=\"text-similarity-davinci-001\")['data'][0]['embedding']\n", |
| 32 | "len(embedding)" |
| 33 | ] |
| 34 | }, |
| 35 | { |
| 36 | "cell_type": "code", |
| 37 | "execution_count": 2, |
| 38 | "metadata": {}, |
| 39 | "outputs": [ |
| 40 | { |
| 41 | "name": "stdout", |
| 42 | "output_type": "stream", |
| 43 | "text": [ |
| 44 | "1024\n" |
| 45 | ] |
| 46 | } |
| 47 | ], |
| 48 | "source": [ |
| 49 | "import openai\n", |
| 50 | "from tenacity import retry, wait_random_exponential, stop_after_attempt\n", |
| 51 | "\n", |
| 52 | "@retry(wait=wait_random_exponential(min=1, max=20), stop=stop_after_attempt(6))\n", |
| 53 | "def get_embedding(text: str, engine=\"text-similarity-davinci-001\") -> List[float]:\n", |
| 54 | "\n", |
| 55 | " # replace newlines, which can negatively affect performance.\n", |
| 56 | " text = text.replace(\"\\n\", \" \")\n", |
| 57 | "\n", |
| 58 | " return openai.Embedding.create(input=[text], engine=engine)[\"data\"][0][\"embedding\"]\n", |
| 59 | "\n", |
| 60 | "embedding = get_embedding(\"Sample query text goes here\", engine=\"text-search-ada-query-001\")\n", |
| 61 | "print(len(embedding))" |
| 62 | ] |
| 63 | }, |
| 64 | { |
| 65 | "cell_type": "code", |
| 66 | "execution_count": 53, |
| 67 | "metadata": {}, |
| 68 | "outputs": [ |
| 69 | { |
| 70 | "name": "stdout", |
| 71 | "output_type": "stream", |
| 72 | "text": [ |
| 73 | "1024\n" |
| 74 | ] |
| 75 | } |
| 76 | ], |
| 77 | "source": [ |
| 78 | "embedding = get_embedding(\"Sample document text goes here\", engine=\"text-search-ada-doc-001\")\n", |
| 79 | "print(len(embedding))" |
| 80 | ] |
| 81 | } |
| 82 | ], |
| 83 | "metadata": { |
| 84 | "interpreter": { |
| 85 | "hash": "be4b5d5b73a21c599de40d6deb1129796d12dc1cc33a738f7bac13269cfcafe8" |
| 86 | }, |
| 87 | "kernelspec": { |
| 88 | "display_name": "Python 3.7.3 64-bit ('base': conda)", |
| 89 | "name": "python3" |
| 90 | }, |
| 91 | "language_info": { |
| 92 | "codemirror_mode": { |
| 93 | "name": "ipython", |
| 94 | "version": 3 |
| 95 | }, |
| 96 | "file_extension": ".py", |
| 97 | "mimetype": "text/x-python", |
| 98 | "name": "python", |
| 99 | "nbconvert_exporter": "python", |
| 100 | "pygments_lexer": "ipython3", |
| 101 | "version": "3.7.3" |
| 102 | }, |
| 103 | "orig_nbformat": 4 |
| 104 | }, |
| 105 | "nbformat": 4, |
| 106 | "nbformat_minor": 2 |
| 107 | } |
| 108 | |