├── requirements.txt ├── Dockerfile ├── README.md ├── main.py ├── .gitignore └── LICENSE /requirements.txt: -------------------------------------------------------------------------------- 1 | fastapi==0.104.1 2 | uvicorn==0.24.0 3 | sentence-transformers==2.2.2 4 | numpy==1.26.2 5 | scipy==1.10.1 6 | scikit-learn==1.3.0 7 | torchvision 8 | torchaudio -------------------------------------------------------------------------------- /Dockerfile: -------------------------------------------------------------------------------- 1 | FROM python:3.11-slim-buster 2 | WORKDIR /app 3 | ADD ./requirements.txt /app/requirements.txt 4 | 5 | RUN pip install --upgrade pip -i https://pypi.tuna.tsinghua.edu.cn/simple 6 | RUN pip install --no-cache-dir -r requirements.txt -i https://pypi.tuna.tsinghua.edu.cn/simple 7 | 8 | ADD . /app 9 | 10 | EXPOSE 6008 11 | CMD ["uvicorn", "main:app", "--host", "0.0.0.0", "--port", "6008"] -------------------------------------------------------------------------------- /README.md: -------------------------------------------------------------------------------- 1 | # bge-api 2 | 3 | BGE-large Embeddings api by FastAPI 4 | 5 | > Refer to **m3e-large-api** 6 | 7 | ## Quick Start 8 | 9 | ### CPU 10 | 11 | ```sh 12 | docker run -d --name bge-large-api -p 6008:6008 jokerwho/bge-large-api:latest 13 | ``` 14 | 15 | ### GPU 16 | 17 | > required nvidia-docker2 18 | 19 | ```sh 20 | docker run -d --name bge-large-api --gpus all -p 6008:6008 jokerwho/bge-large-api:latest 21 | ``` 22 | 23 | ## Test 24 | 25 | ```sh 26 | curl --location --request POST 'http://127.0.0.1/v1/embeddings' \ 27 | --header 'Authorization: Bearer sk-aaabbbcccdddeeefffggghhhiiijjjkkk' \ 28 | --header 'Content-Type: application/json' \ 29 | --data-raw '{ 30 | "model": "bge-large-zh-v1.5", 31 | "input": ["github是什么"] 32 | }' 33 | ``` 34 | 35 | ## Develop 36 | 37 | ```python 38 | from huggingface_hub import snapshot_download 39 | snapshot_download(repo_id="BAAI/bge-large-zh-v1.5",cache_dir="./cache", local_dir="models/bge-large-zh-v1.5") 40 | print("======download successful=====") 41 | ``` 42 | 43 | ```sh 44 | rm -r ./cache 45 | ``` 46 | 47 | ```sh 48 | pip install -r requirements.txt 49 | python main.py 50 | ``` 51 | -------------------------------------------------------------------------------- /main.py: -------------------------------------------------------------------------------- 1 | from fastapi import FastAPI, Depends, HTTPException, status 2 | from fastapi.security import HTTPBearer, HTTPAuthorizationCredentials 3 | from sentence_transformers import SentenceTransformer 4 | from pydantic import BaseModel 5 | from fastapi.middleware.cors import CORSMiddleware 6 | import uvicorn 7 | import numpy as np 8 | from typing import List 9 | from sklearn.preprocessing import PolynomialFeatures 10 | import torch 11 | import os 12 | 13 | # 环境变量传入 14 | sk_key = os.environ.get("sk-key", "sk-aaabbbcccdddeeefffggghhhiiijjjkkk") 15 | 16 | # 创建FastAPI实例 17 | app = FastAPI() 18 | 19 | # 添加CORS中间件 20 | app.add_middleware( 21 | CORSMiddleware, 22 | allow_origins=["*"], 23 | allow_credentials=True, 24 | allow_methods=["*"], 25 | allow_headers=["*"], 26 | ) 27 | 28 | # 创建HTTPBearer实例 29 | security = HTTPBearer() 30 | 31 | 32 | # 预加载模型 33 | def load_model(): 34 | device = torch.device("cuda" if torch.cuda.is_available() else "cpu") 35 | print( 36 | f"本次加载模型的设备为：{'GPU: ' + torch.cuda.get_device_name(0) if torch.cuda.is_available() else 'CPU.'}" 37 | ) 38 | return SentenceTransformer("./models/bge-large-zh-v1.5", device=device) 39 | 40 | 41 | model = load_model() 42 | 43 | 44 | # 请求和响应模型 45 | class EmbeddingRequest(BaseModel): 46 | input: List[str] 47 | model: str 48 | 49 | 50 | class EmbeddingResponse(BaseModel): 51 | data: list 52 | model: str 53 | object: str 54 | usage: dict 55 | 56 | 57 | # 功能函数 58 | def process_embedding(embedding, target_length): 59 | """扩展或截断嵌入向量以匹配目标长度。""" 60 | poly = PolynomialFeatures(degree=2) 61 | expanded_embedding = poly.fit_transform(embedding.reshape(1, -1)).flatten() 62 | 63 | if len(expanded_embedding) > target_length: 64 | return expanded_embedding[:target_length] 65 | elif len(expanded_embedding) < target_length: 66 | return np.pad(expanded_embedding, (0, target_length - len(expanded_embedding))) 67 | return expanded_embedding 68 | 69 | 70 | @app.post("/v1/embeddings", response_model=EmbeddingResponse) 71 | async def get_embeddings( 72 | request: EmbeddingRequest, 73 | credentials: HTTPAuthorizationCredentials = Depends(security), 74 | ): 75 | if credentials.credentials != sk_key: 76 | raise HTTPException( 77 | status_code=status.HTTP_401_UNAUTHORIZED, 78 | detail="Invalid authorization code", 79 | ) 80 | 81 | # 计算嵌入向量 82 | embeddings = [ 83 | model.encode(text, normalize_embeddings=True) for text in request.input 84 | ] 85 | embeddings = [process_embedding(embedding, 1536) for embedding in embeddings] 86 | 87 | # Min-Max normalization 88 | embeddings = [embedding / np.linalg.norm(embedding) for embedding in embeddings] 89 | 90 | # 转换为列表 91 | embeddings = [embedding.tolist() for embedding in embeddings] 92 | prompt_tokens = sum(len(text.split()) for text in request.input) 93 | total_tokens = sum(len(text) for text in request.input) # 示例：计算总tokens数量 94 | 95 | response = { 96 | "data": [ 97 | {"embedding": embedding, "index": index, "object": "embedding"} 98 | for index, embedding in enumerate(embeddings) 99 | ], 100 | "model": request.model, 101 | "object": "list", 102 | "usage": { 103 | "prompt_tokens": prompt_tokens, 104 | "total_tokens": total_tokens, 105 | }, 106 | } 107 | 108 | return response 109 | 110 | 111 | if __name__ == "__main__": 112 | uvicorn.run("main:app", host="0.0.0.0", port=6008, workers=1) 113 | -------------------------------------------------------------------------------- /.gitignore: -------------------------------------------------------------------------------- 1 | .vscode/ 2 | models/ 3 | download.py 4 | # Byte-compiled / optimized / DLL files 5 | __pycache__/ 6 | *.py[cod] 7 | *$py.class 8 | 9 | # C extensions 10 | *.so 11 | 12 | # Distribution / packaging 13 | .Python 14 | build/ 15 | develop-eggs/ 16 | dist/ 17 | downloads/ 18 | eggs/ 19 | .eggs/ 20 | lib/ 21 | lib64/ 22 | parts/ 23 | sdist/ 24 | var/ 25 | wheels/ 26 | share/python-wheels/ 27 | *.egg-info/ 28 | .installed.cfg 29 | *.egg 30 | MANIFEST 31 | 32 | # PyInstaller 33 | # Usually these files are written by a python script from a template 34 | # before PyInstaller builds the exe, so as to inject date/other infos into it. 35 | *.manifest 36 | *.spec 37 | 38 | # Installer logs 39 | pip-log.txt 40 | pip-delete-this-directory.txt 41 | 42 | # Unit test / coverage reports 43 | htmlcov/ 44 | .tox/ 45 | .nox/ 46 | .coverage 47 | .coverage.* 48 | .cache 49 | nosetests.xml 50 | coverage.xml 51 | *.cover 52 | *.py,cover 53 | .hypothesis/ 54 | .pytest_cache/ 55 | cover/ 56 | 57 | # Translations 58 | *.mo 59 | *.pot 60 | 61 | # Django stuff: 62 | *.log 63 | local_settings.py 64 | db.sqlite3 65 | db.sqlite3-journal 66 | 67 | # Flask stuff: 68 | instance/ 69 | .webassets-cache 70 | 71 | # Scrapy stuff: 72 | .scrapy 73 | 74 | # Sphinx documentation 75 | docs/_build/ 76 | 77 | # PyBuilder 78 | .pybuilder/ 79 | target/ 80 | 81 | # Jupyter Notebook 82 | .ipynb_checkpoints 83 | 84 | # IPython 85 | profile_default/ 86 | ipython_config.py 87 | 88 | # pyenv 89 | # For a library or package, you might want to ignore these files since the code is 90 | # intended to run in multiple environments; otherwise, check them in: 91 | # .python-version 92 | 93 | # pipenv 94 | # According to pypa/pipenv#598, it is recommended to include Pipfile.lock in version control. 95 | # However, in case of collaboration, if having platform-specific dependencies or dependencies 96 | # having no cross-platform support, pipenv may install dependencies that don't work, or not 97 | # install all needed dependencies. 98 | #Pipfile.lock 99 | 100 | # poetry 101 | # Similar to Pipfile.lock, it is generally recommended to include poetry.lock in version control. 102 | # This is especially recommended for binary packages to ensure reproducibility, and is more 103 | # commonly ignored for libraries. 104 | # https://python-poetry.org/docs/basic-usage/#commit-your-poetrylock-file-to-version-control 105 | #poetry.lock 106 | 107 | # pdm 108 | # Similar to Pipfile.lock, it is generally recommended to include pdm.lock in version control. 109 | #pdm.lock 110 | # pdm stores project-wide configurations in .pdm.toml, but it is recommended to not include it 111 | # in version control. 112 | # https://pdm.fming.dev/#use-with-ide 113 | .pdm.toml 114 | 115 | # PEP 582; used by e.g. github.com/David-OConnor/pyflow and github.com/pdm-project/pdm 116 | __pypackages__/ 117 | 118 | # Celery stuff 119 | celerybeat-schedule 120 | celerybeat.pid 121 | 122 | # SageMath parsed files 123 | *.sage.py 124 | 125 | # Environments 126 | .env 127 | .venv 128 | env/ 129 | venv/ 130 | ENV/ 131 | env.bak/ 132 | venv.bak/ 133 | 134 | # Spyder project settings 135 | .spyderproject 136 | .spyproject 137 | 138 | # Rope project settings 139 | .ropeproject 140 | 141 | # mkdocs documentation 142 | /site 143 | 144 | # mypy 145 | .mypy_cache/ 146 | .dmypy.json 147 | dmypy.json 148 | 149 | # Pyre type checker 150 | .pyre/ 151 | 152 | # pytype static type analyzer 153 | .pytype/ 154 | 155 | # Cython debug symbols 156 | cython_debug/ 157 | 158 | # PyCharm 159 | # JetBrains specific template is maintained in a separate JetBrains.gitignore that can 160 | # be found at https://github.com/github/gitignore/blob/main/Global/JetBrains.gitignore 161 | # and can be added to the global gitignore or merged into this file. For a more nuclear 162 | # option (not recommended) you can uncomment the following to ignore the entire idea folder. 163 | #.idea/ 164 | -------------------------------------------------------------------------------- /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 | --------------------------------------------------------------------------------