├── .gitignore ├── .vscode └── settings.json ├── LICENSE ├── README.md ├── gis.py ├── requirements.txt ├── stocks.py └── tokens.py /.gitignore: -------------------------------------------------------------------------------- 1 | *.csv 2 | 3 | # Byte-compiled / optimized / DLL files 4 | __pycache__/ 5 | *.py[cod] 6 | *$py.class 7 | 8 | # C extensions 9 | *.so 10 | 11 | # Distribution / packaging 12 | .Python 13 | build/ 14 | develop-eggs/ 15 | dist/ 16 | downloads/ 17 | eggs/ 18 | .eggs/ 19 | lib/ 20 | lib64/ 21 | parts/ 22 | sdist/ 23 | var/ 24 | wheels/ 25 | share/python-wheels/ 26 | *.egg-info/ 27 | .installed.cfg 28 | *.egg 29 | MANIFEST 30 | 31 | # PyInstaller 32 | # Usually these files are written by a python script from a template 33 | # before PyInstaller builds the exe, so as to inject date/other infos into it. 34 | *.manifest 35 | *.spec 36 | 37 | # Installer logs 38 | pip-log.txt 39 | pip-delete-this-directory.txt 40 | 41 | # Unit test / coverage reports 42 | htmlcov/ 43 | .tox/ 44 | .nox/ 45 | .coverage 46 | .coverage.* 47 | .cache 48 | nosetests.xml 49 | coverage.xml 50 | *.cover 51 | *.py,cover 52 | .hypothesis/ 53 | .pytest_cache/ 54 | cover/ 55 | 56 | # Translations 57 | *.mo 58 | *.pot 59 | 60 | # Django stuff: 61 | *.log 62 | local_settings.py 63 | db.sqlite3 64 | db.sqlite3-journal 65 | 66 | # Flask stuff: 67 | instance/ 68 | .webassets-cache 69 | 70 | # Scrapy stuff: 71 | .scrapy 72 | 73 | # Sphinx documentation 74 | docs/_build/ 75 | 76 | # PyBuilder 77 | .pybuilder/ 78 | target/ 79 | 80 | # Jupyter Notebook 81 | .ipynb_checkpoints 82 | 83 | # IPython 84 | profile_default/ 85 | ipython_config.py 86 | 87 | # pyenv 88 | # For a library or package, you might want to ignore these files since the code is 89 | # intended to run in multiple environments; otherwise, check them in: 90 | # .python-version 91 | 92 | # pipenv 93 | # According to pypa/pipenv#598, it is recommended to include Pipfile.lock in version control. 94 | # However, in case of collaboration, if having platform-specific dependencies or dependencies 95 | # having no cross-platform support, pipenv may install dependencies that don't work, or not 96 | # install all needed dependencies. 97 | #Pipfile.lock 98 | 99 | # poetry 100 | # Similar to Pipfile.lock, it is generally recommended to include poetry.lock in version control. 101 | # This is especially recommended for binary packages to ensure reproducibility, and is more 102 | # commonly ignored for libraries. 103 | # https://python-poetry.org/docs/basic-usage/#commit-your-poetrylock-file-to-version-control 104 | #poetry.lock 105 | 106 | # pdm 107 | # Similar to Pipfile.lock, it is generally recommended to include pdm.lock in version control. 108 | #pdm.lock 109 | # pdm stores project-wide configurations in .pdm.toml, but it is recommended to not include it 110 | # in version control. 111 | # https://pdm.fming.dev/#use-with-ide 112 | .pdm.toml 113 | 114 | # PEP 582; used by e.g. github.com/David-OConnor/pyflow and github.com/pdm-project/pdm 115 | __pypackages__/ 116 | 117 | # Celery stuff 118 | celerybeat-schedule 119 | celerybeat.pid 120 | 121 | # SageMath parsed files 122 | *.sage.py 123 | 124 | # Environments 125 | .env 126 | .venv 127 | env/ 128 | venv/ 129 | ENV/ 130 | env.bak/ 131 | venv.bak/ 132 | 133 | # Spyder project settings 134 | .spyderproject 135 | .spyproject 136 | 137 | # Rope project settings 138 | .ropeproject 139 | 140 | # mkdocs documentation 141 | /site 142 | 143 | # mypy 144 | .mypy_cache/ 145 | .dmypy.json 146 | dmypy.json 147 | 148 | # Pyre type checker 149 | .pyre/ 150 | 151 | # pytype static type analyzer 152 | .pytype/ 153 | 154 | # Cython debug symbols 155 | cython_debug/ 156 | 157 | # PyCharm 158 | # JetBrains specific template is maintained in a separate JetBrains.gitignore that can 159 | # be found at https://github.com/github/gitignore/blob/main/Global/JetBrains.gitignore 160 | # and can be added to the global gitignore or merged into this file. For a more nuclear 161 | # option (not recommended) you can uncomment the following to ignore the entire idea folder. 162 | #.idea/ 163 | -------------------------------------------------------------------------------- /.vscode/settings.json: -------------------------------------------------------------------------------- 1 | { 2 | "cSpell.words": [ 3 | "ndim", 4 | "pretrained" 5 | ] 6 | } -------------------------------------------------------------------------------- /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 | # Absuing Vector Search 2 | 3 | This repo contains the code for the ["Abusing Vector Search for Texts, Maps, and Chess ♟️" article](https://ashvardanian.com/posts/abusing-vector-search/). 4 | 5 | - `gis.py` - working with Geo-Spatial data using HNSW and Haversine distance. 6 | - `stocks.py` - covariance analysis for stocks using HNSW. 7 | - `tokens.py` - taking the tokenizer from BERT, but forgetting the model :) 8 | -------------------------------------------------------------------------------- /gis.py: -------------------------------------------------------------------------------- 1 | from usearch import Index 2 | 3 | import pandas as pd 4 | import numpy as np 5 | import geocoder 6 | 7 | my_coordinates = np.array(geocoder.ip('me').latlng, dtype=np.float32) 8 | 9 | df = pd.read_csv('cities.csv') 10 | coordinates = np.zeros((df.shape[0], 2), dtype=np.float32) 11 | coordinates[:, 0] = df['latitude'].to_numpy(dtype=np.float32) 12 | coordinates[:, 1] = df['longitude'].to_numpy(dtype=np.float32) 13 | labels = np.array(range(df.shape[0]), dtype=np.longlong) 14 | 15 | index = Index(metric='haversine') 16 | index.add(labels, coordinates) 17 | 18 | # Reshaping it for batch search: 19 | matches, _, _ = index.search(my_coordinates, 10) 20 | print(df.iloc[matches]) 21 | -------------------------------------------------------------------------------- /requirements.txt: -------------------------------------------------------------------------------- 1 | usearch 2 | uform 3 | 4 | pandas 5 | numpy 6 | geocoder 7 | transformers 8 | tqdm 9 | -------------------------------------------------------------------------------- /stocks.py: -------------------------------------------------------------------------------- 1 | import os 2 | from statistics import covariance 3 | import time 4 | 5 | from usearch import Index 6 | 7 | import pandas as pd 8 | import numpy as np 9 | 10 | directory: str = 'stocks' 11 | last_days: int = 30 12 | tickets: list[str] = [] 13 | ticket_to_prices: dict[str, np.array] = {} 14 | index = Index(ndim=last_days) 15 | 16 | for filename in os.listdir(directory): 17 | path = os.path.join(directory, filename) 18 | ticket = filename.split('.')[0] 19 | df = pd.read_csv(path) 20 | 21 | prices_list = df['Close'][-last_days:].to_list() 22 | prices = np.zeros(last_days, dtype=np.float32) 23 | prices[-len(prices_list):] = prices_list 24 | 25 | tickets.append(ticket) 26 | index.add(len(index), prices - np.mean(prices)) 27 | ticket_to_prices[ticket] = prices 28 | 29 | 30 | def search_and_print(selected_ticker: str = 'AAPL'): 31 | 32 | tic = time.perf_counter() 33 | selected_prices = ticket_to_prices[selected_ticker] 34 | approx_matches, _, _ = index.search( 35 | selected_prices - np.mean(selected_prices), 10) 36 | approx_tickets = [tickets[match] for match in approx_matches] 37 | toc = time.perf_counter() 38 | print('Approximate matches:', ','.join(approx_tickets)) 39 | print(f'- Measurement took {toc - tic:0.4f} seconds') 40 | 41 | tic = time.perf_counter() 42 | covariances = [ 43 | (ticket, covariance(selected_prices, prices)) 44 | for ticket, prices in ticket_to_prices.items()] 45 | covariances = sorted(covariances, key=lambda x: x[1], reverse=True) 46 | exact_tickets = [ticket for ticket, _ in covariances[:10]] 47 | toc = time.perf_counter() 48 | print('Exact matches:', ','.join(exact_tickets)) 49 | print(f'- Measurement took {toc - tic:0.4f} seconds') 50 | 51 | 52 | try: 53 | while True: 54 | selected: str = input('Type a ticker from NASDAQ, like AAPL: ') 55 | if selected not in ticket_to_prices: 56 | print(f'Missing {selected}, try again') 57 | continue 58 | 59 | print('You entered:', selected) 60 | search_and_print(selected) 61 | 62 | except KeyboardInterrupt: 63 | exit(0) 64 | -------------------------------------------------------------------------------- /tokens.py: -------------------------------------------------------------------------------- 1 | from transformers import BertTokenizer 2 | from usearch import SetsIndex, HashIndex 3 | from tqdm import tqdm 4 | import numpy as np 5 | import pandas as pd 6 | 7 | 8 | sets_index = SetsIndex() 9 | hash_index = HashIndex(bits=2048) 10 | tokenizer = BertTokenizer.from_pretrained('bert-base-uncased') 11 | 12 | df = pd.read_csv( 13 | 'posts.csv', 14 | usecols=['text', 'by', 'id'], 15 | dtype={'text': 'str', 'by': 'str', 'id': 'int'}, 16 | nrows=100000, 17 | ) 18 | print(f'Loaded {len(df)} lines') 19 | 20 | 21 | def text2set(sample: str) -> np.array: 22 | encoding = tokenizer.encode(sample, truncation=True) 23 | encoding = encoding[1:-1] 24 | encoding = sorted(set(encoding)) 25 | encoding = np.array(encoding, dtype=np.int32) 26 | return encoding 27 | 28 | 29 | def text2hashes(sample: str) -> np.array: 30 | words = sample.lower().split() 31 | return np.array([hash(word) for word in words], dtype=np.int64) 32 | 33 | 34 | for idx, sample in tqdm(enumerate(df['text'])): 35 | if not isinstance(sample, str): 36 | continue 37 | sets_index.add(idx, text2set(sample)) 38 | hash_index.add(idx, text2hashes(sample)) 39 | 40 | print(f'Added {len(sets_index)} titles to indices') 41 | 42 | 43 | def print_matches(matches: np.array): 44 | for idx, match in enumerate(matches): 45 | row = df.iloc[match] 46 | title = row['text'].replace('\n', ' ') 47 | id = row['id'] 48 | print(f'- {idx+1}. {title}') 49 | print(f' https://news.ycombinator.com/item?id={id}') 50 | 51 | 52 | try: 53 | while True: 54 | query: str = input('Please enter a search query: ') 55 | print('You entered:', query) 56 | 57 | print('For SetIndex the results are:') 58 | matches = sets_index.search(text2set(query), 3) 59 | print_matches(matches) 60 | 61 | print('For HashIndex the results are:') 62 | matches = hash_index.search(text2hashes(query), 3) 63 | print_matches(matches) 64 | 65 | except KeyboardInterrupt: 66 | exit(0) 67 | --------------------------------------------------------------------------------