├── Dockerfile ├── LICENSE ├── README.md └── app.py /Dockerfile: -------------------------------------------------------------------------------- 1 | # Use Python 3.8 as base image 2 | FROM python:3.8 3 | 4 | # Set working directory inside the container 5 | WORKDIR /app 6 | 7 | # Download the model during build 8 | RUN pip install --no-cache-dir sentence_transformers transformers nltk 9 | RUN python -c "from sentence_transformers import SentenceTransformer; SentenceTransformer('intfloat/e5-small-v2')" 10 | RUN python -c "from transformers import AutoTokenizer; AutoTokenizer.from_pretrained('intfloat/e5-small-v2')" 11 | RUN python -c "import nltk; nltk.download('punkt')" 12 | 13 | # Install required Python packages 14 | RUN pip install --no-cache-dir Flask gunicorn numpy 15 | 16 | # Copy the Flask app to the container 17 | COPY app.py . 18 | 19 | # Expose the port the app runs on 20 | EXPOSE 8080 21 | 22 | # Run the app 23 | # 24 | # For CPU based servers, 4 processes can over-saturate a Ryzen 5950x 32-cpu 25 | # chip. htop shows load avg of 52, which means processes are waiting for CPU 26 | # time. So, let's limit this to only 2 processes. 27 | CMD ["gunicorn", "-w", "2", "-b", "0.0.0.0:8080", "app:app"] 28 | # CMD ["python", "-u", "app.py"] 29 | -------------------------------------------------------------------------------- /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 | # Vector Embedding Server 2 | 3 | Server to generate vector embeddings for arbitrary-length documents using E5 model, in under 100 lines of code. 4 | 5 | Contains a Dockerfile which downloads [e5-small-v2][] during build time (hence 6 | avoiding any runtime surprises), and runs app.py. 7 | 8 | [e5-small-v2]: https://huggingface.co/intfloat/e5-small-v2 9 | 10 | app.py uses this model to generate embeddings, even for longer documents, by 11 | chunking them up at sentence level, and taking a mean at the end. The sentences 12 | are chunked at 500 tokens each, to avoid crossing the 512 token limit enforced 13 | by E5 models. 14 | 15 | ## Why build this? 16 | 17 | I was looking for a Docker-based server, which can expose a simple endpoint to 18 | generate vector embeddings for documents. The solution needs to deal with 19 | lengthy documents that exceed the 512-token limit enforced by E5 models. Such 20 | documents require intelligent chunking, ideally at sentence boundaries, followed 21 | by taking a mean of the vectors, to work effectively. Since I couldn't find a 22 | solution that met these criteria, I decided to create this setup myself. 23 | 24 | This setup doesn't deal with storing and searching over the vectors. It only 25 | deals with generation of the vectors. To search over the vectors, you'd need 26 | another system. 27 | 28 | ## Build 29 | 30 | ```bash 31 | $ docker build -t . 32 | $ docker run -p 10002:10002 33 | ``` 34 | 35 | By default, this is using `e5-small-v2` model. If you wish to change the model, 36 | you'd have to update the name in both Dockerfile and app.py. 37 | 38 | ## Usage 39 | 40 | When passing a document, use the prefix: `passage: `. When querying for similar 41 | documents, use the prefix `query: `. [e5-small-v2][] has a question about 42 | these prefixes in the FAQ. 43 | 44 | If a single sentence exceeds the 512 tokens limit, then we ignore that sentence, 45 | considering it invalid, and adding its tokens to the `invalid_tokens` count. 46 | 47 | `num_tokens` is the total number of tokens the document has, including the 48 | `invalid_tokens`. 49 | 50 | ``` 51 | $ curl http://localhost:10002/embed -XPOST -H "content-type: application/json" -d '{"prefix": "passage: ", "text": "This is a sentence."}' | jq 52 | 53 | { 54 | "embedding": [ 55 | -0.07240722328424454, 56 | 0.03763573244214058, 57 | 0.02595547027885914, 58 | -0.017270879819989204, 59 | -0.023462336510419846, 60 | 0.05062587931752205, 61 | 0.07775235176086426, 62 | -0.06687597930431366, 63 | ... 64 | -0.06454016268253326, 65 | 0.006377237383276224, 66 | -0.0546715222299099, 67 | -0.002629948779940605, 68 | -0.0011916998773813248, 69 | 0.026298822835087776 70 | ], 71 | "invalid_tokens": 0, 72 | "num_tokens": 5 73 | } 74 | ``` 75 | -------------------------------------------------------------------------------- /app.py: -------------------------------------------------------------------------------- 1 | from flask import Flask, request, jsonify 2 | from sentence_transformers import SentenceTransformer 3 | from transformers import AutoTokenizer 4 | import numpy as np 5 | from nltk.tokenize import sent_tokenize 6 | import logging 7 | 8 | import nltk 9 | nltk.download('punkt') 10 | 11 | logging.basicConfig(level=logging.INFO) 12 | app = Flask(__name__) 13 | 14 | model_name = 'intfloat/e5-small-v2' 15 | model = SentenceTransformer(model_name) 16 | # Initialize the Hugging Face tokenizer using the same model name 17 | tokenizer = AutoTokenizer.from_pretrained(model_name) 18 | 19 | @app.route('/health', methods=['GET']) 20 | def health(): 21 | return jsonify({"status": "ok"}), 200 22 | 23 | @app.route('/embed', methods=['POST']) 24 | def embed_text(): 25 | data = request.json 26 | text = data.get('text', None) 27 | prefix = data.get('prefix', None) 28 | 29 | if text is None: 30 | return jsonify({"error": "No text provided"}), 400 31 | if prefix is None: 32 | return jsonify({"error": "No prefix provided"}), 400 33 | 34 | try: 35 | # Tokenize the text into sentences 36 | sentences = sent_tokenize(text) 37 | 38 | # Combine the sentences back into chunks of approximately 500 tokens each 39 | chunks = [] 40 | current_chunk = "" 41 | current_length = 0 42 | num_tokens = 0 43 | invalid_tokens = 0 44 | 45 | for sentence in sentences: 46 | # Tokenize the current sentence 47 | sentence_ids = tokenizer.encode(sentence, add_special_tokens=False) 48 | sentence_length = len(sentence_ids) 49 | num_tokens = num_tokens + sentence_length 50 | 51 | if sentence_length > 500: 52 | logging.info(f"Skipping too long of a sentence: {sentence}") 53 | invalid_tokens = invalid_tokens + sentence_length 54 | continue 55 | 56 | # Check if adding this sentence exceeds the chunk size 57 | if current_length + sentence_length > 500: 58 | chunks.append(current_chunk.strip()) 59 | current_chunk = "" 60 | current_length = 0 61 | 62 | current_chunk += sentence + " " 63 | current_length += sentence_length 64 | 65 | # Don't forget the last chunk 66 | if current_chunk: 67 | chunks.append(current_chunk.strip()) 68 | 69 | # Process chunks as before 70 | # ... 71 | 72 | # Loop over the token IDs and break them into CHUNK_SIZE chunks 73 | chunk_embeddings = [] 74 | for chunk in chunks: 75 | # Decode chunk back to text 76 | chunk_text = prefix + chunk 77 | # logging.info(f"Chunk text: {chunk_text}") 78 | 79 | # Generate embedding for the chunk 80 | chunk_embedding = model.encode([chunk_text], normalize_embeddings=True)[0] 81 | chunk_embeddings.append(chunk_embedding) 82 | 83 | # Average the embeddings to get a single document embedding 84 | if len(chunk_embeddings) == 0: 85 | logging.warning("No valid chunks found for embedding.") 86 | embedding = None 87 | else: 88 | embedding = np.mean(chunk_embeddings, axis=0).tolist() 89 | logging.info(f"Generated embedding for {num_tokens} tokens." 90 | f" Found {invalid_tokens} invalid tokens.") 91 | return jsonify({"embedding": embedding, "num_tokens": num_tokens, 92 | "invalid_tokens": invalid_tokens}) 93 | 94 | except Exception as e: 95 | # Log the exception for debugging 96 | logging.error(f"An error occurred: {e}") 97 | return jsonify({"error": f"An error occurred during encoding: {str(e)}"}), 500 98 | 99 | if __name__ == "__main__": 100 | app.run(host='0.0.0.0', port=8080) 101 | --------------------------------------------------------------------------------