├── .github └── workflows │ ├── publish.yml │ └── test.yml ├── .gitignore ├── LICENSE ├── README.md ├── datasette_openai └── __init__.py ├── pytest.ini ├── setup.py └── tests └── test_openai.py /.github/workflows/publish.yml: -------------------------------------------------------------------------------- 1 | name: Publish Python Package 2 | 3 | on: 4 | release: 5 | types: [created] 6 | 7 | permissions: 8 | contents: read 9 | 10 | jobs: 11 | test: 12 | runs-on: ubuntu-latest 13 | strategy: 14 | matrix: 15 | python-version: ["3.7", "3.8", "3.9", "3.10", "3.11"] 16 | steps: 17 | - uses: actions/checkout@v3 18 | - name: Set up Python ${{ matrix.python-version }} 19 | uses: actions/setup-python@v4 20 | with: 21 | python-version: ${{ matrix.python-version }} 22 | cache: pip 23 | cache-dependency-path: setup.py 24 | - name: Install dependencies 25 | run: | 26 | pip install '.[test]' 27 | - name: Run tests 28 | run: | 29 | pytest 30 | deploy: 31 | runs-on: ubuntu-latest 32 | needs: [test] 33 | steps: 34 | - uses: actions/checkout@v3 35 | - name: Set up Python 36 | uses: actions/setup-python@v4 37 | with: 38 | python-version: "3.11" 39 | cache: pip 40 | cache-dependency-path: setup.py 41 | - name: Install dependencies 42 | run: | 43 | pip install setuptools wheel twine build 44 | - name: Publish 45 | env: 46 | TWINE_USERNAME: __token__ 47 | TWINE_PASSWORD: ${{ secrets.PYPI_TOKEN }} 48 | run: | 49 | python -m build 50 | twine upload dist/* 51 | 52 | -------------------------------------------------------------------------------- /.github/workflows/test.yml: -------------------------------------------------------------------------------- 1 | name: Test 2 | 3 | on: [push, pull_request] 4 | 5 | permissions: 6 | contents: read 7 | 8 | jobs: 9 | test: 10 | runs-on: ubuntu-latest 11 | strategy: 12 | matrix: 13 | python-version: ["3.7", "3.8", "3.9", "3.10", "3.11"] 14 | steps: 15 | - uses: actions/checkout@v3 16 | - name: Set up Python ${{ matrix.python-version }} 17 | uses: actions/setup-python@v4 18 | with: 19 | python-version: ${{ matrix.python-version }} 20 | cache: pip 21 | cache-dependency-path: setup.py 22 | - name: Install dependencies 23 | run: | 24 | pip install '.[test]' 25 | - name: Run tests 26 | run: | 27 | pytest 28 | 29 | -------------------------------------------------------------------------------- /.gitignore: -------------------------------------------------------------------------------- 1 | .venv 2 | __pycache__/ 3 | *.py[cod] 4 | *$py.class 5 | venv 6 | .eggs 7 | .pytest_cache 8 | *.egg-info 9 | .DS_Store 10 | .vscode 11 | dist 12 | build 13 | -------------------------------------------------------------------------------- /LICENSE: -------------------------------------------------------------------------------- 1 | Apache License 2 | Version 2.0, January 2004 3 | http://www.apache.org/licenses/ 4 | 5 | TERMS AND CONDITIONS FOR USE, REPRODUCTION, AND DISTRIBUTION 6 | 7 | 1. Definitions. 8 | 9 | "License" shall mean the terms and conditions for use, reproduction, 10 | and distribution as defined by Sections 1 through 9 of this document. 11 | 12 | "Licensor" shall mean the copyright owner or entity authorized by 13 | the copyright owner that is granting the License. 14 | 15 | "Legal Entity" shall mean the union of the acting entity and all 16 | other entities that control, are controlled by, or are under common 17 | control with that entity. For the purposes of this definition, 18 | "control" means (i) the power, direct or indirect, to cause the 19 | direction or management of such entity, whether by contract or 20 | otherwise, or (ii) ownership of fifty percent (50%) or more of the 21 | outstanding shares, or (iii) beneficial ownership of such entity. 22 | 23 | "You" (or "Your") shall mean an individual or Legal Entity 24 | exercising permissions granted by this License. 25 | 26 | "Source" form shall mean the preferred form for making modifications, 27 | including but not limited to software source code, documentation 28 | source, and configuration files. 29 | 30 | "Object" form shall mean any form resulting from mechanical 31 | transformation or translation of a Source form, including but 32 | not limited to compiled object code, generated documentation, 33 | and conversions to other media types. 34 | 35 | "Work" shall mean the work of authorship, whether in Source or 36 | Object form, made available under the License, as indicated by a 37 | copyright notice that is included in or attached to the work 38 | (an example is provided in the Appendix below). 39 | 40 | "Derivative Works" shall mean any work, whether in Source or Object 41 | form, that is based on (or derived from) the Work and for which the 42 | editorial revisions, annotations, elaborations, or other modifications 43 | represent, as a whole, an original work of authorship. For the purposes 44 | of this License, Derivative Works shall not include works that remain 45 | separable from, or merely link (or bind by name) to the interfaces of, 46 | the Work and Derivative Works thereof. 47 | 48 | "Contribution" shall mean any work of authorship, including 49 | the original version of the Work and any modifications or additions 50 | to that Work or Derivative Works thereof, that is intentionally 51 | submitted to Licensor for inclusion in the Work by the copyright owner 52 | or by an individual or Legal Entity authorized to submit on behalf of 53 | the copyright owner. For the purposes of this definition, "submitted" 54 | means any form of electronic, verbal, or written communication sent 55 | to the Licensor or its representatives, including but not limited to 56 | communication on electronic mailing lists, source code control systems, 57 | and issue tracking systems that are managed by, or on behalf of, the 58 | Licensor for the purpose of discussing and improving the Work, but 59 | excluding communication that is conspicuously marked or otherwise 60 | designated in writing by the copyright owner as "Not a Contribution." 61 | 62 | "Contributor" shall mean Licensor and any individual or Legal Entity 63 | on behalf of whom a Contribution has been received by Licensor and 64 | subsequently incorporated within the Work. 65 | 66 | 2. Grant of Copyright License. Subject to the terms and conditions of 67 | this License, each Contributor hereby grants to You a perpetual, 68 | worldwide, non-exclusive, no-charge, royalty-free, irrevocable 69 | copyright license to reproduce, prepare Derivative Works of, 70 | publicly display, publicly perform, sublicense, and distribute the 71 | Work and such Derivative Works in Source or Object form. 72 | 73 | 3. Grant of Patent License. Subject to the terms and conditions of 74 | this License, each Contributor hereby grants to You a perpetual, 75 | worldwide, non-exclusive, no-charge, royalty-free, irrevocable 76 | (except as stated in this section) patent license to make, have made, 77 | use, offer to sell, sell, import, and otherwise transfer the Work, 78 | where such license applies only to those patent claims licensable 79 | by such Contributor that are necessarily infringed by their 80 | Contribution(s) alone or by combination of their Contribution(s) 81 | with the Work to which such Contribution(s) was submitted. If You 82 | institute patent litigation against any entity (including a 83 | cross-claim or counterclaim in a lawsuit) alleging that the Work 84 | or a Contribution incorporated within the Work constitutes direct 85 | or contributory patent infringement, then any patent licenses 86 | granted to You under this License for that Work shall terminate 87 | as of the date such litigation is filed. 88 | 89 | 4. Redistribution. You may reproduce and distribute copies of the 90 | Work or Derivative Works thereof in any medium, with or without 91 | modifications, and in Source or Object form, provided that You 92 | meet the following conditions: 93 | 94 | (a) You must give any other recipients of the Work or 95 | Derivative Works a copy of this License; and 96 | 97 | (b) You must cause any modified files to carry prominent notices 98 | stating that You changed the files; and 99 | 100 | (c) You must retain, in the Source form of any Derivative Works 101 | that You distribute, all copyright, patent, trademark, and 102 | attribution notices from the Source form of the Work, 103 | excluding those notices that do not pertain to any part of 104 | the Derivative Works; and 105 | 106 | (d) If the Work includes a "NOTICE" text file as part of its 107 | distribution, then any Derivative Works that You distribute must 108 | include a readable copy of the attribution notices contained 109 | within such NOTICE file, excluding those notices that do not 110 | pertain to any part of the Derivative Works, in at least one 111 | of the following places: within a NOTICE text file distributed 112 | as part of the Derivative Works; within the Source form or 113 | documentation, if provided along with the Derivative Works; or, 114 | within a display generated by the Derivative Works, if and 115 | wherever such third-party notices normally appear. The contents 116 | of the NOTICE file are for informational purposes only and 117 | do not modify the License. You may add Your own attribution 118 | notices within Derivative Works that You distribute, alongside 119 | or as an addendum to the NOTICE text from the Work, provided 120 | that such additional attribution notices cannot be construed 121 | as modifying the License. 122 | 123 | You may add Your own copyright statement to Your modifications and 124 | may provide additional or different license terms and conditions 125 | for use, reproduction, or distribution of Your modifications, or 126 | for any such Derivative Works as a whole, provided Your use, 127 | reproduction, and distribution of the Work otherwise complies with 128 | the conditions stated in this License. 129 | 130 | 5. Submission of Contributions. Unless You explicitly state otherwise, 131 | any Contribution intentionally submitted for inclusion in the Work 132 | by You to the Licensor shall be under the terms and conditions of 133 | this License, without any additional terms or conditions. 134 | Notwithstanding the above, nothing herein shall supersede or modify 135 | the terms of any separate license agreement you may have executed 136 | with Licensor regarding such Contributions. 137 | 138 | 6. Trademarks. This License does not grant permission to use the trade 139 | names, trademarks, service marks, or product names of the Licensor, 140 | except as required for reasonable and customary use in describing the 141 | origin of the Work and reproducing the content of the NOTICE file. 142 | 143 | 7. Disclaimer of Warranty. Unless required by applicable law or 144 | agreed to in writing, Licensor provides the Work (and each 145 | Contributor provides its Contributions) on an "AS IS" BASIS, 146 | WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or 147 | implied, including, without limitation, any warranties or conditions 148 | of TITLE, NON-INFRINGEMENT, MERCHANTABILITY, or FITNESS FOR A 149 | PARTICULAR PURPOSE. You are solely responsible for determining the 150 | appropriateness of using or redistributing the Work and assume any 151 | risks associated with Your exercise of permissions under this License. 152 | 153 | 8. Limitation of Liability. In no event and under no legal theory, 154 | whether in tort (including negligence), contract, or otherwise, 155 | unless required by applicable law (such as deliberate and grossly 156 | negligent acts) or agreed to in writing, shall any Contributor be 157 | liable to You for damages, including any direct, indirect, special, 158 | incidental, or consequential damages of any character arising as a 159 | result of this License or out of the use or inability to use the 160 | Work (including but not limited to damages for loss of goodwill, 161 | work stoppage, computer failure or malfunction, or any and all 162 | other commercial damages or losses), even if such Contributor 163 | has been advised of the possibility of such damages. 164 | 165 | 9. Accepting Warranty or Additional Liability. While redistributing 166 | the Work or Derivative Works thereof, You may choose to offer, 167 | and charge a fee for, acceptance of support, warranty, indemnity, 168 | or other liability obligations and/or rights consistent with this 169 | License. However, in accepting such obligations, You may act only 170 | on Your own behalf and on Your sole responsibility, not on behalf 171 | of any other Contributor, and only if You agree to indemnify, 172 | defend, and hold each Contributor harmless for any liability 173 | incurred by, or claims asserted against, such Contributor by reason 174 | of your accepting any such warranty or additional liability. 175 | 176 | END OF TERMS AND CONDITIONS 177 | 178 | APPENDIX: How to apply the Apache License to your work. 179 | 180 | To apply the Apache License to your work, attach the following 181 | boilerplate notice, with the fields enclosed by brackets "[]" 182 | replaced with your own identifying information. (Don't include 183 | the brackets!) The text should be enclosed in the appropriate 184 | comment syntax for the file format. We also recommend that a 185 | file or class name and description of purpose be included on the 186 | same "printed page" as the copyright notice for easier 187 | identification within third-party archives. 188 | 189 | Copyright [yyyy] [name of copyright owner] 190 | 191 | Licensed under the Apache License, Version 2.0 (the "License"); 192 | you may not use this file except in compliance with the License. 193 | You may obtain a copy of the License at 194 | 195 | http://www.apache.org/licenses/LICENSE-2.0 196 | 197 | Unless required by applicable law or agreed to in writing, software 198 | distributed under the License is distributed on an "AS IS" BASIS, 199 | WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. 200 | See the License for the specific language governing permissions and 201 | limitations under the License. 202 | -------------------------------------------------------------------------------- /README.md: -------------------------------------------------------------------------------- 1 | # datasette-openai 2 | 3 | [![PyPI](https://img.shields.io/pypi/v/datasette-openai.svg)](https://pypi.org/project/datasette-openai/) 4 | [![Changelog](https://img.shields.io/github/v/release/simonw/datasette-openai?include_prereleases&label=changelog)](https://github.com/simonw/datasette-openai/releases) 5 | [![Tests](https://github.com/simonw/datasette-openai/workflows/Test/badge.svg)](https://github.com/simonw/datasette-openai/actions?query=workflow%3ATest) 6 | [![License](https://img.shields.io/badge/license-Apache%202.0-blue.svg)](https://github.com/simonw/datasette-openai/blob/main/LICENSE) 7 | 8 | SQL functions for calling OpenAI APIs 9 | 10 | See [Semantic search answers: Q&A against documentation with GPT3 + OpenAI embeddings](https://simonwillison.net/2023/Jan/13/semantic-search-answers/) for background on this project. 11 | 12 | ## Installation 13 | 14 | Install this plugin in the same environment as Datasette. 15 | 16 | datasette install datasette-openai 17 | 18 | ## ⚠️ Warning ⚠️ 19 | 20 | This plugin allows you to call a commercial, priced API using SQL queries. 21 | 22 | Use this with care! You could accidentally spend a lot of money. 23 | 24 | For example, the following query: 25 | 26 | ```sql 27 | select 28 | openai_davinci( 29 | 'Summarize this text: ' || content, 200, 1, :api_key 30 | ) as summary 31 | from documents 32 | ``` 33 | Would execute one paid API call for every item in the `documents` database. This could become very expensive. 34 | 35 | Be sure to familiarize yourself with [OpenAI pricing](https://openai.com/api/pricing/). You will need to obtain an [API key](https://beta.openai.com/account/api-keys). 36 | 37 | ## Usage 38 | 39 | This extension provides three new SQL functions: 40 | 41 | ### openai_davinci(prompt, max_tokens, temperature, api_key) 42 | 43 | This function runs a `text-davinci-003` completion against the provided prompt, with the specified values for max tokens and temperature. 44 | 45 | Da Vinci is currently 2 cents per thousand tokens. 46 | 47 | ### openai_embedding(text, api_key) 48 | 49 | This calls the OpenAI embedding endpoint and returns a binary object representing the floating point embedding for the provided text. 50 | 51 | ```sql 52 | select openai_embedding(:query, :api_key) 53 | ``` 54 | An embedding is an array of 1536 floating point values. The returned value from this is a `blob` encoding of those values. 55 | 56 | It's mainly useful for using with the `openai_embedding_similarity()` function. 57 | 58 | The embedding API is very inexpensive: at time of writing, $0.0004 cents per thousand tokens, where a token is more-or-less a single word. 59 | 60 | ### openai_embedding_similarity(a, b) 61 | 62 | This function does not make any API calls. It takes two embedding blobs and returns the cosine similarity between the two. 63 | 64 | This function is particularly useful if you have stored embeddings of documents in a database table, and you want to find the most similar documents to a query or to another document. 65 | 66 | A simple search query could look like this: 67 | ```sql 68 | with query as ( 69 | select 70 | openai_embedding(:query, :token) as q 71 | ) 72 | select 73 | id, 74 | title, 75 | openai_embedding_similarity(query.q, embedding) as score 76 | from 77 | content, query 78 | order by 79 | score desc 80 | limit 10 81 | ``` 82 | 83 | ### openai_build_prompt(text, prefix, suffix, completion_tokens, token_limit=4000) 84 | 85 | This aggregate function helps build a prompt from a number of inputs in a way that fits the GPT-3 prompt size limit. 86 | 87 | It takes the following argument: 88 | 89 | - `text` - this is the column that is being aggregated, so the function expects to have multiple values for this. All other arguments will only be read the first time they are passed, so should be consistent across all calls to the function. 90 | - `prefix` - text to use for the prefix of the prompt 91 | - `suffix` - text to use for the suffix of the prompt 92 | - `completion_tokens` - the number of tokens to reserve for the prompt response - this will be subtracted from the token limit 93 | - `token_limit` - this value is optional (there are 4-argument and 5-argument versions of the function registered). It defaults to the GPT-3 Da Vinci size limit of 4,000 tokens but can be changed if the model the prompt is being used with has a different size limit. 94 | 95 | Here's an example usage of this function, adapted from [this article](https://simonwillison.net/2023/Jan/13/semantic-search-answers/): 96 | 97 | ```sql 98 | with top_n as ( 99 | select body from blog_entry order by id desc limit 3 100 | ) 101 | select openai_build_prompt(body, 'Context: 102 | ------------ 103 | ', ' 104 | ------------ 105 | Given the above context, answer the following question: ' || :question, 106 | 500, 107 | 2000 108 | ) from top_n 109 | ``` 110 | [Try that here](https://datasette.simonwillison.net/simonwillisonblog?sql=with+top_n+as+%28%0D%0A++select+body+from+blog_entry+order+by+id+desc+limit+5%0D%0A%29%0D%0Aselect+openai_build_prompt%28body%2C+%27Context%3A%0D%0A------------%0D%0A%27%2C+%27%0D%0A------------%0D%0AGiven+the+above+context%2C+answer+the+following+question%3A+%27+%7C%7C+%3Aquestion%2C%0D%0A++500%2C%0D%0A++2000%0D%0A++%29+from+top_n&question=Examples+of+a+language+model%3F). 111 | 112 | This query first retrieves the three most recent blog entries, then constructs a prompt that with the provided prefix and suffix designed to fit 1500 tokens (2000 total, minus 500 reserved for the response). 113 | 114 | The output looks something like this (truncated for space): 115 | 116 | ``` 117 | Context: 118 | ------------ 119 | < p > If you 've spent any time with GPT - 3 or ChatGPT , you 've likely thought about how ... 120 | I release Datasette 0 . 64 this morning . This release is mainly a response to the realization that it 's not safe to run Datasette with the SpatiaLite extension loaded if that Datasette instance is configured to enable arbitrary SQL queries from untrusted users ... 121 | In lieu of my regular weeknotes ( I took two weeks off for the holidays ) here 's a look back at 2022 , mainly in terms of projects and things I 've written about ... 122 | ------------ 123 | Given the above context, answer the following question: Examples of a language model? 124 | ``` 125 | The body of each entry has been truncated to the number of tokens that will allow examples from all three entries to be included in the generated prompt. 126 | 127 | ### openai_strip_tags(text) 128 | 129 | Sometimes it can be useful to strip HTML tags from text in order to reduce the number of tokens used. This function does a very simple version of tag stripping - just removing anything that matches `<...>`. 130 | 131 | ### openai_tokenize(text) 132 | 133 | Returns a JSON array of tokens for the provided text. 134 | 135 | This uses a regular expression [extracted from OpenAI's GPT-2](https://github.com/openai/gpt-2/blob/a74da5d99abaaba920de8131d64da2862a8f213b/src/encoder.py#L53). 136 | 137 | ### openai_count_tokens(text) 138 | 139 | Returns a count of the number of tokens in the provided text. 140 | 141 | ## Development 142 | 143 | To set up this plugin locally, first checkout the code. Then create a new virtual environment: 144 | 145 | cd datasette-openai 146 | python3 -m venv venv 147 | source venv/bin/activate 148 | 149 | Now install the dependencies and test dependencies: 150 | 151 | pip install -e '.[test]' 152 | 153 | To run the tests: 154 | 155 | pytest 156 | -------------------------------------------------------------------------------- /datasette_openai/__init__.py: -------------------------------------------------------------------------------- 1 | from datasette import hookimpl 2 | import httpx 3 | import json 4 | import re 5 | import regex 6 | import struct 7 | 8 | tag_re = re.compile(r"<[^>]*>") 9 | 10 | # From https://github.com/openai/gpt-2/blob/a74da5d99abaaba920de8131d64da2862a8f213b/src/encoder.py#L53 11 | token_re = regex.compile( 12 | r"""'s|'t|'re|'ve|'m|'ll|'d| ?\p{L}+| ?\p{N}+| ?[^\s\p{L}\p{N}]+|\s+(?!\S)|\s+""" 13 | ) 14 | 15 | 16 | def tokenize(text): 17 | return [t.strip() for t in token_re.findall(text)] 18 | 19 | 20 | def count_tokens(text): 21 | return len(tokenize(text)) 22 | 23 | 24 | class BuildPrompt: 25 | def __init__(self): 26 | self.texts = [] 27 | self.first = True 28 | self.prefix = "" 29 | self.suffix = "" 30 | self.completion_tokens = 0 31 | self.token_limit = 0 32 | 33 | def step(self, text, prefix, suffix, completion_tokens, token_limit=4000): 34 | if self.first: 35 | self.first = False 36 | self.prefix = prefix 37 | self.suffix = suffix 38 | self.completion_tokens = completion_tokens 39 | self.token_limit = token_limit 40 | self.texts.append(text) 41 | 42 | def finalize(self): 43 | available_tokens = ( 44 | self.token_limit 45 | - self.completion_tokens 46 | - count_tokens(self.prefix) 47 | - count_tokens(self.suffix) 48 | ) 49 | if available_tokens < 0: 50 | return self.prefix + " " + self.suffix 51 | # Get that many tokens from each of the texts 52 | tokens_per_text = available_tokens // len(self.texts) 53 | truncated_texts = [] 54 | for text in self.texts: 55 | truncated_texts.append(" ".join(tokenize(text)[:tokens_per_text])) 56 | return self.prefix + " " + " ".join(truncated_texts) + " " + self.suffix 57 | 58 | 59 | @hookimpl 60 | def prepare_connection(conn): 61 | conn.create_function("openai_embedding", 2, openai_embedding) 62 | conn.create_function("openai_embedding_similarity", 2, openai_embedding_similarity) 63 | conn.create_function("openai_davinci", 4, openai_davinci) 64 | conn.create_function("openai_strip_tags", 1, openai_strip_tags) 65 | conn.create_function("openai_count_tokens", 1, count_tokens) 66 | conn.create_function("openai_tokenize", 1, lambda s: json.dumps(tokenize(s))) 67 | conn.create_aggregate("openai_build_prompt", 4, BuildPrompt) 68 | conn.create_aggregate("openai_build_prompt", 5, BuildPrompt) 69 | 70 | 71 | def openai_strip_tags(text): 72 | "A very naive tag stripping implementation but good enough for now" 73 | return tag_re.sub("", text) 74 | 75 | 76 | def openai_embedding(text, api_key): 77 | response = httpx.post( 78 | "https://api.openai.com/v1/embeddings", 79 | headers={"Authorization": f"Bearer {api_key}"}, 80 | json={ 81 | "input": text, 82 | "model": "text-embedding-ada-002", 83 | }, 84 | ) 85 | if response.status_code != 200: 86 | return response.text 87 | return encode(response.json()["data"][0]["embedding"]) 88 | 89 | 90 | def openai_embedding_similarity(embedding, compare_to_embedding): 91 | return cosine_similarity(decode(embedding), decode(compare_to_embedding)) 92 | 93 | 94 | def openai_davinci(prompt, max_tokens, temperature, api_key): 95 | response = httpx.post( 96 | "https://api.openai.com/v1/completions", 97 | headers={"Authorization": f"Bearer {api_key}"}, 98 | json={ 99 | "model": "text-davinci-003", 100 | "prompt": prompt, 101 | "max_tokens": max_tokens, 102 | "temperature": temperature, 103 | }, 104 | timeout=15.0, 105 | ) 106 | if response.status_code != 200: 107 | return response.text 108 | return response.json()["choices"][0]["text"] 109 | 110 | 111 | def cosine_similarity(a, b): 112 | dot_product = sum(x * y for x, y in zip(a, b)) 113 | magnitude_a = sum(x * x for x in a) ** 0.5 114 | magnitude_b = sum(x * x for x in b) ** 0.5 115 | return dot_product / (magnitude_a * magnitude_b) 116 | 117 | 118 | def decode(blob): 119 | return struct.unpack("f" * 1536, blob) 120 | 121 | 122 | def encode(values): 123 | return struct.pack("f" * 1536, *values) 124 | -------------------------------------------------------------------------------- /pytest.ini: -------------------------------------------------------------------------------- 1 | [pytest] 2 | asyncio_mode = strict 3 | -------------------------------------------------------------------------------- /setup.py: -------------------------------------------------------------------------------- 1 | from setuptools import setup 2 | import os 3 | 4 | VERSION = "0.2" 5 | 6 | 7 | def get_long_description(): 8 | with open( 9 | os.path.join(os.path.dirname(os.path.abspath(__file__)), "README.md"), 10 | encoding="utf8", 11 | ) as fp: 12 | return fp.read() 13 | 14 | 15 | setup( 16 | name="datasette-openai", 17 | description="SQL functions for calling OpenAI APIs", 18 | long_description=get_long_description(), 19 | long_description_content_type="text/markdown", 20 | author="Simon Willison", 21 | url="https://github.com/simonw/datasette-openai", 22 | project_urls={ 23 | "Issues": "https://github.com/simonw/datasette-openai/issues", 24 | "CI": "https://github.com/simonw/datasette-openai/actions", 25 | "Changelog": "https://github.com/simonw/datasette-openai/releases", 26 | }, 27 | license="Apache License, Version 2.0", 28 | classifiers=[ 29 | "Framework :: Datasette", 30 | "License :: OSI Approved :: Apache Software License", 31 | ], 32 | version=VERSION, 33 | packages=["datasette_openai"], 34 | entry_points={"datasette": ["openai = datasette_openai"]}, 35 | install_requires=["datasette", "regex"], 36 | extras_require={"test": ["pytest", "pytest-asyncio"]}, 37 | python_requires=">=3.7", 38 | ) 39 | -------------------------------------------------------------------------------- /tests/test_openai.py: -------------------------------------------------------------------------------- 1 | from datasette.app import Datasette 2 | import pytest 3 | 4 | 5 | @pytest.mark.asyncio 6 | async def test_plugin_is_installed(): 7 | datasette = Datasette(memory=True) 8 | response = await datasette.client.get("/-/plugins.json") 9 | assert response.status_code == 200 10 | installed_plugins = {p["name"] for p in response.json()} 11 | assert "datasette-openai" in installed_plugins 12 | 13 | 14 | @pytest.mark.asyncio 15 | @pytest.mark.parametrize( 16 | "function,input,expected", 17 | ( 18 | # openai_strip_tags 19 | ("openai_strip_tags", "Hello world", "Hello world"), 20 | ("openai_strip_tags", "

Hello world

", "Hello world"), 21 | # openai_count_tokens 22 | ("openai_count_tokens", "Hello world", 2), 23 | ("openai_count_tokens", "Hello world!", 3), 24 | # openai_tokenize 25 | ("openai_tokenize", "Hello world", '["Hello", "world"]'), 26 | ("openai_tokenize", "Hello world!", '["Hello", "world", "!"]'), 27 | ), 28 | ) 29 | async def test_simple_functions(function, input, expected): 30 | ds = Datasette(memory=True) 31 | response = await ds.client.get( 32 | "/_memory.json", 33 | params={ 34 | "sql": "select {}(:text)".format(function), 35 | "text": input, 36 | "_shape": "arrayfirst", 37 | }, 38 | ) 39 | assert response.status_code == 200 40 | assert response.json() == [expected] 41 | 42 | 43 | @pytest.mark.asyncio 44 | async def test_openai_build_prompt(): 45 | ds = Datasette(memory=True) 46 | await ds.invoke_startup() 47 | db = ds.add_memory_database("test") 48 | await db.execute_write_script( 49 | """ 50 | create table texts (id integer primary key, text text); 51 | insert into texts (text) values ('One'); 52 | insert into texts (text) values ('Two tokens'); 53 | insert into texts (text) values ('Now three tokens'); 54 | insert into texts (text) values ('This has four tokens'); 55 | insert into texts (text) values ('This one has five tokens'); 56 | insert into texts (text) values ('And this one has six tokens'); 57 | """ 58 | ) 59 | response = await ds.client.get( 60 | "/test.json", 61 | params={ 62 | "sql": """ 63 | select openai_build_prompt( 64 | text, 65 | "Prefix", 66 | "Suffix", 67 | 50 68 | ) 69 | from texts 70 | """, 71 | "_shape": "arrayfirst", 72 | }, 73 | ) 74 | assert response.status_code == 200 75 | assert response.json() == [ 76 | "Prefix One Two tokens Now three tokens This has four tokens This one has five tokens And this one has six tokens Suffix" 77 | ] 78 | --------------------------------------------------------------------------------