| Name | mteb JSON |
| Version |
1.8.7
JSON |
| download |
| home_page | None |
| Summary | Massive Text Embedding Benchmark |
| upload_time | 2024-05-09 16:47:35 |
| maintainer | None |
| docs_url | None |
| author | None |
| requires_python | >=3.8 |
| license | Apache License Version 2.0, January 2004 http://www.apache.org/licenses/ TERMS AND CONDITIONS FOR USE, REPRODUCTION, AND DISTRIBUTION 1. Definitions. "License" shall mean the terms and conditions for use, reproduction, and distribution as defined by Sections 1 through 9 of this document. "Licensor" shall mean the copyright owner or entity authorized by the copyright owner that is granting the License. "Legal Entity" shall mean the union of the acting entity and all other entities that control, are controlled by, or are under common control with that entity. For the purposes of this definition, "control" means (i) the power, direct or indirect, to cause the direction or management of such entity, whether by contract or otherwise, or (ii) ownership of fifty percent (50%) or more of the outstanding shares, or (iii) beneficial ownership of such entity. "You" (or "Your") shall mean an individual or Legal Entity exercising permissions granted by this License. "Source" form shall mean the preferred form for making modifications, including but not limited to software source code, documentation source, and configuration files. "Object" form shall mean any form resulting from mechanical transformation or translation of a Source form, including but not limited to compiled object code, generated documentation, and conversions to other media types. "Work" shall mean the work of authorship, whether in Source or Object form, made available under the License, as indicated by a copyright notice that is included in or attached to the work (an example is provided in the Appendix below). "Derivative Works" shall mean any work, whether in Source or Object form, that is based on (or derived from) the Work and for which the editorial revisions, annotations, elaborations, or other modifications represent, as a whole, an original work of authorship. For the purposes of this License, Derivative Works shall not include works that remain separable from, or merely link (or bind by name) to the interfaces of, the Work and Derivative Works thereof. "Contribution" shall mean any work of authorship, including the original version of the Work and any modifications or additions to that Work or Derivative Works thereof, that is intentionally submitted to Licensor for inclusion in the Work by the copyright owner or by an individual or Legal Entity authorized to submit on behalf of the copyright owner. For the purposes of this definition, "submitted" means any form of electronic, verbal, or written communication sent to the Licensor or its representatives, including but not limited to communication on electronic mailing lists, source code control systems, and issue tracking systems that are managed by, or on behalf of, the Licensor for the purpose of discussing and improving the Work, but excluding communication that is conspicuously marked or otherwise designated in writing by the copyright owner as "Not a Contribution." "Contributor" shall mean Licensor and any individual or Legal Entity on behalf of whom a Contribution has been received by Licensor and subsequently incorporated within the Work. 2. Grant of Copyright License. Subject to the terms and conditions of this License, each Contributor hereby grants to You a perpetual, worldwide, non-exclusive, no-charge, royalty-free, irrevocable copyright license to reproduce, prepare Derivative Works of, publicly display, publicly perform, sublicense, and distribute the Work and such Derivative Works in Source or Object form. 3. Grant of Patent License. Subject to the terms and conditions of this License, each Contributor hereby grants to You a perpetual, worldwide, non-exclusive, no-charge, royalty-free, irrevocable (except as stated in this section) patent license to make, have made, use, offer to sell, sell, import, and otherwise transfer the Work, where such license applies only to those patent claims licensable by such Contributor that are necessarily infringed by their Contribution(s) alone or by combination of their Contribution(s) with the Work to which such Contribution(s) was submitted. If You institute patent litigation against any entity (including a cross-claim or counterclaim in a lawsuit) alleging that the Work or a Contribution incorporated within the Work constitutes direct or contributory patent infringement, then any patent licenses granted to You under this License for that Work shall terminate as of the date such litigation is filed. 4. Redistribution. You may reproduce and distribute copies of the Work or Derivative Works thereof in any medium, with or without modifications, and in Source or Object form, provided that You meet the following conditions: (a) You must give any other recipients of the Work or Derivative Works a copy of this License; and (b) You must cause any modified files to carry prominent notices stating that You changed the files; and (c) You must retain, in the Source form of any Derivative Works that You distribute, all copyright, patent, trademark, and attribution notices from the Source form of the Work, excluding those notices that do not pertain to any part of the Derivative Works; and (d) If the Work includes a "NOTICE" text file as part of its distribution, then any Derivative Works that You distribute must include a readable copy of the attribution notices contained within such NOTICE file, excluding those notices that do not pertain to any part of the Derivative Works, in at least one of the following places: within a NOTICE text file distributed as part of the Derivative Works; within the Source form or documentation, if provided along with the Derivative Works; or, within a display generated by the Derivative Works, if and wherever such third-party notices normally appear. The contents of the NOTICE file are for informational purposes only and do not modify the License. You may add Your own attribution notices within Derivative Works that You distribute, alongside or as an addendum to the NOTICE text from the Work, provided that such additional attribution notices cannot be construed as modifying the License. You may add Your own copyright statement to Your modifications and may provide additional or different license terms and conditions for use, reproduction, or distribution of Your modifications, or for any such Derivative Works as a whole, provided Your use, reproduction, and distribution of the Work otherwise complies with the conditions stated in this License. 5. Submission of Contributions. Unless You explicitly state otherwise, any Contribution intentionally submitted for inclusion in the Work by You to the Licensor shall be under the terms and conditions of this License, without any additional terms or conditions. Notwithstanding the above, nothing herein shall supersede or modify the terms of any separate license agreement you may have executed with Licensor regarding such Contributions. 6. Trademarks. This License does not grant permission to use the trade names, trademarks, service marks, or product names of the Licensor, except as required for reasonable and customary use in describing the origin of the Work and reproducing the content of the NOTICE file. 7. Disclaimer of Warranty. Unless required by applicable law or agreed to in writing, Licensor provides the Work (and each Contributor provides its Contributions) on an "AS IS" BASIS, WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied, including, without limitation, any warranties or conditions of TITLE, NON-INFRINGEMENT, MERCHANTABILITY, or FITNESS FOR A PARTICULAR PURPOSE. You are solely responsible for determining the appropriateness of using or redistributing the Work and assume any risks associated with Your exercise of permissions under this License. 8. Limitation of Liability. In no event and under no legal theory, whether in tort (including negligence), contract, or otherwise, unless required by applicable law (such as deliberate and grossly negligent acts) or agreed to in writing, shall any Contributor be liable to You for damages, including any direct, indirect, special, incidental, or consequential damages of any character arising as a result of this License or out of the use or inability to use the Work (including but not limited to damages for loss of goodwill, work stoppage, computer failure or malfunction, or any and all other commercial damages or losses), even if such Contributor has been advised of the possibility of such damages. 9. Accepting Warranty or Additional Liability. While redistributing the Work or Derivative Works thereof, You may choose to offer, and charge a fee for, acceptance of support, warranty, indemnity, or other liability obligations and/or rights consistent with this License. However, in accepting such obligations, You may act only on Your own behalf and on Your sole responsibility, not on behalf of any other Contributor, and only if You agree to indemnify, defend, and hold each Contributor harmless for any liability incurred by, or claims asserted against, such Contributor by reason of your accepting any such warranty or additional liability. END OF TERMS AND CONDITIONS APPENDIX: How to apply the Apache License to your work. To apply the Apache License to your work, attach the following boilerplate notice, with the fields enclosed by brackets "[]" replaced with your own identifying information. (Don't include the brackets!) The text should be enclosed in the appropriate comment syntax for the file format. We also recommend that a file or class name and description of purpose be included on the same "printed page" as the copyright notice for easier identification within third-party archives. Copyright [yyyy] [name of copyright owner] Licensed under the Apache License, Version 2.0 (the "License"); you may not use this file except in compliance with the License. You may obtain a copy of the License at http://www.apache.org/licenses/LICENSE-2.0 Unless required by applicable law or agreed to in writing, software distributed under the License is distributed on an "AS IS" BASIS, WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. See the License for the specific language governing permissions and limitations under the License. |
| keywords |
deep learning
text embeddings
benchmark
|
| VCS |
 |
| bugtrack_url |
|
| requirements |
No requirements were recorded.
|
| Travis-CI |
No Travis.
|
| coveralls test coverage |
No coveralls.
|
<h1 align="center">Massive Text Embedding Benchmark</h1>
<p align="center">
<a href="https://github.com/embeddings-benchmark/mteb/releases">
<img alt="GitHub release" src="https://img.shields.io/github/release/embeddings-benchmark/mteb.svg">
</a>
<a href="https://arxiv.org/abs/2210.07316">
<img alt="GitHub release" src="https://img.shields.io/badge/arXiv-2305.14251-b31b1b.svg">
</a>
<a href="https://github.com/embeddings-benchmark/mteb/blob/master/LICENSE">
<img alt="License" src="https://img.shields.io/github/license/embeddings-benchmark/mteb.svg?color=green">
</a>
<a href="https://pepy.tech/project/mteb">
<img alt="Downloads" src="https://static.pepy.tech/personalized-badge/mteb?period=total&units=international_system&left_color=grey&right_color=orange&left_text=Downloads">
</a>
</p>
<h4 align="center">
<p>
<a href="#installation">Installation</a> |
<a href="#usage">Usage</a> |
<a href="https://huggingface.co/spaces/mteb/leaderboard">Leaderboard</a> |
<a href="#documentation">Documentation</a> |
<a href="#citing">Citing</a>
<p>
</h4>
<h3 align="center">
<a href="https://huggingface.co/spaces/mteb/leaderboard"><img style="float: middle; padding: 10px 10px 10px 10px;" width="60" height="55" src="./docs/images/hf_logo.png" /></a>
</h3>
## Installation
```bash
pip install mteb
```
## Usage
* Using a python script (see [scripts/run_mteb_english.py](https://github.com/embeddings-benchmark/mteb/blob/main/scripts/run_mteb_english.py) and [mteb/mtebscripts](https://github.com/embeddings-benchmark/mtebscripts) for more):
```python
from mteb import MTEB
from sentence_transformers import SentenceTransformer
# Define the sentence-transformers model name
model_name = "average_word_embeddings_komninos"
# or directly from huggingface:
# model_name = "sentence-transformers/all-MiniLM-L6-v2"
model = SentenceTransformer(model_name)
evaluation = MTEB(tasks=["Banking77Classification"])
results = evaluation.run(model, output_folder=f"results/{model_name}")
```
* Using CLI
```bash
mteb --available_tasks
mteb -m sentence-transformers/all-MiniLM-L6-v2 \
-t Banking77Classification \
--verbosity 3
# if nothing is specified default to saving the results in the results/{model_name} folder
```
* Using multiple GPUs in parallel can be done by just having a custom encode function that distributes the inputs to multiple GPUs like e.g. [here](https://github.com/microsoft/unilm/blob/b60c741f746877293bb85eed6806736fc8fa0ffd/e5/mteb_eval.py#L60) or [here](https://github.com/ContextualAI/gritlm/blob/09d8630f0c95ac6a456354bcb6f964d7b9b6a609/gritlm/gritlm.py#L75).
<br />
<details>
<summary> Advanced Usage (click to unfold) </summary>
## Advanced Usage
### Dataset selection
Datasets can be selected by providing the list of datasets, but also
* by their task (e.g. "Clustering" or "Classification")
```python
evaluation = MTEB(task_types=['Clustering', 'Retrieval']) # Only select clustering and retrieval tasks
```
* by their categories e.g. "S2S" (sentence to sentence) or "P2P" (paragraph to paragraph)
```python
evaluation = MTEB(task_categories=['S2S']) # Only select sentence2sentence datasets
```
* by their languages
```python
evaluation = MTEB(task_langs=["en", "de"]) # Only select datasets which are "en", "de" or "en-de"
```
You can also specify which languages to load for multilingual/crosslingual tasks like below:
```python
from mteb.tasks import AmazonReviewsClassification, BUCCBitextMining
evaluation = MTEB(tasks=[
AmazonReviewsClassification(langs=["en", "fr"]) # Only load "en" and "fr" subsets of Amazon Reviews
BUCCBitextMining(langs=["de-en"]), # Only load "de-en" subset of BUCC
])
```
There are also presets available for certain task collections, e.g. to select the 56 English datasets that form the "Overall MTEB English leaderboard":
```python
from mteb import MTEB_MAIN_EN
evaluation = MTEB(tasks=MTEB_MAIN_EN, task_langs=["en"])
```
### Evaluation split
You can evaluate only on `test` splits of all tasks by doing the following:
```python
evaluation.run(model, eval_splits=["test"])
```
Note that the public leaderboard uses the test splits for all datasets except MSMARCO, where the "dev" split is used.
### Using a custom model
Models should implement the following interface, implementing an `encode` function taking as inputs a list of sentences, and returning a list of embeddings (embeddings can be `np.array`, `torch.tensor`, etc.). For inspiration, you can look at the [mteb/mtebscripts repo](https://github.com/embeddings-benchmark/mtebscripts) used for running diverse models via SLURM scripts for the paper.
```python
class MyModel():
def encode(
self, sentences: list[str], prompt: str, **kwargs: Any
) -> torch.Tensor | np.ndarray:
"""Encodes the given sentences using the encoder.
Args:
sentences: The sentences to encode.
prompt: The prompt to use. Useful for prompt-based models.
**kwargs: Additional arguments to pass to the encoder.
Returns:
The encoded sentences.
"""
pass
model = MyModel()
evaluation = MTEB(tasks=["Banking77Classification"])
evaluation.run(model)
```
If you'd like to use different encoding functions for query and corpus when evaluating on Retrieval or Reranking tasks, you can add separate methods for `encode_queries` and `encode_corpus`. If these methods exist, they will be automatically used for those tasks. You can refer to the `DRESModel` at `mteb/evaluation/evaluators/RetrievalEvaluator.py` for an example of these functions.
```python
class MyModel():
def encode_queries(self, queries: list[str], **kwargs) -> list[np.ndarray] | list[torch.Tensor]:
"""
Returns a list of embeddings for the given sentences.
Args:
queries: List of sentences to encode
Returns:
List of embeddings for the given sentences
"""
pass
def encode_corpus(self, corpus: list[str] | list[dict[str, str]], **kwargs) -> list[np.ndarray] | list[torch.Tensor]:
"""
Returns a list of embeddings for the given sentences.
Args:
corpus: List of sentences to encode
or list of dictionaries with keys "title" and "text"
Returns:
List of embeddings for the given sentences
"""
pass
```
### Evaluating on a custom dataset
To evaluate on a custom task, you can run the following code on your custom task. See [how to add a new task](docs/adding_a_dataset.md), for how to create a new task in MTEB.
```python
from mteb import MTEB
from mteb.abstasks.AbsTaskReranking import AbsTaskReranking
from sentence_transformers import SentenceTransformer
class MyCustomTask(AbsTaskReranking):
...
model = SentenceTransformer("average_word_embeddings_komninos")
evaluation = MTEB(tasks=[MyCustomTask()])
evaluation.run(model)
```
</details>
<br />
## Documentation
| Documentation | |
| ------------------------------ | ---------------------- |
| 📋 [Tasks] | Overview of available tasks |
| 📈 [Leaderboard] | The interactive leaderboard of the benchmark |
| 🤖 [Adding a model] | Information related to how to submit a model to the leaderboard |
| 👩💻 [Adding a dataset] | How to add a new task/dataset to MTEB |
| 👩💻 [Adding a leaderboard tab] | How to add a new leaderboard tab to MTEB |
| 🤝 [Contributing] | How to contribute to MTEB and set it up for development |
<!-- | 🌐 [MMTEB] | An open-source effort to extend MTEB to cover a broad set of languages | -->
[Tasks]: docs/tasks.md
[Contributing]: CONTRIBUTING.md
[Adding a model]: docs/adding_a_model.md
[Adding a dataset]: docs/adding_a_dataset.md
[Adding a leaderboard tab]: docs/adding_a_leaderboard_tab.md
[Leaderboard]: https://huggingface.co/spaces/mteb/leaderboard
[MMTEB]: docs/mmteb/readme.md
## Citing
MTEB was introduced in "[MTEB: Massive Text Embedding Benchmark](https://arxiv.org/abs/2210.07316)", feel free to cite:
```bibtex
@article{muennighoff2022mteb,
doi = {10.48550/ARXIV.2210.07316},
url = {https://arxiv.org/abs/2210.07316},
author = {Muennighoff, Niklas and Tazi, Nouamane and Magne, Lo{\"\i}c and Reimers, Nils},
title = {MTEB: Massive Text Embedding Benchmark},
publisher = {arXiv},
journal={arXiv preprint arXiv:2210.07316},
year = {2022}
}
```
You may also want to read and cite the amazing work that has extended MTEB & integrated new datasets:
- Shitao Xiao, Zheng Liu, Peitian Zhang, Niklas Muennighoff. "[C-Pack: Packaged Resources To Advance General Chinese Embedding](https://arxiv.org/abs/2309.07597)" arXiv 2023
- Michael Günther, Jackmin Ong, Isabelle Mohr, Alaeddine Abdessalem, Tanguy Abel, Mohammad Kalim Akram, Susana Guzman, Georgios Mastrapas, Saba Sturua, Bo Wang, Maximilian Werk, Nan Wang, Han Xiao. "[Jina Embeddings 2: 8192-Token General-Purpose Text Embeddings for Long Documents](https://arxiv.org/abs/2310.19923)" arXiv 2023
- Silvan Wehrli, Bert Arnrich, Christopher Irrgang. "[German Text Embedding Clustering Benchmark](https://arxiv.org/abs/2401.02709)" arXiv 2024
- Dawei Zhu, Liang Wang, Nan Yang, Yifan Song, Wenhao Wu, Furu Wei, and Sujian Li. "[LongEmbed: Extending Embedding Models for Long Context Retrieval](https://arxiv.org/abs/2404.12096)" arXiv 2024
For works that have used MTEB for benchmarking, you can find them on the [leaderboard](https://huggingface.co/spaces/mteb/leaderboard).
Raw data
{
"_id": null,
"home_page": null,
"name": "mteb",
"maintainer": null,
"docs_url": null,
"requires_python": ">=3.8",
"maintainer_email": null,
"keywords": "deep learning, text embeddings, benchmark",
"author": null,
"author_email": "MTEB Contributors <niklas@huggingface.co>, nouamane@huggingface.co, info@nils-reimers.de",
"download_url": "https://files.pythonhosted.org/packages/d7/6c/f7f0c5fb933ec8f6a87f72f30609b61a95fef5aad9b3828e661c9d8cf855/mteb-1.8.7.tar.gz",
"platform": null,
"description": "<h1 align=\"center\">Massive Text Embedding Benchmark</h1>\n\n<p align=\"center\">\n <a href=\"https://github.com/embeddings-benchmark/mteb/releases\">\n <img alt=\"GitHub release\" src=\"https://img.shields.io/github/release/embeddings-benchmark/mteb.svg\">\n </a>\n <a href=\"https://arxiv.org/abs/2210.07316\">\n <img alt=\"GitHub release\" src=\"https://img.shields.io/badge/arXiv-2305.14251-b31b1b.svg\">\n </a>\n <a href=\"https://github.com/embeddings-benchmark/mteb/blob/master/LICENSE\">\n <img alt=\"License\" src=\"https://img.shields.io/github/license/embeddings-benchmark/mteb.svg?color=green\">\n </a>\n <a href=\"https://pepy.tech/project/mteb\">\n <img alt=\"Downloads\" src=\"https://static.pepy.tech/personalized-badge/mteb?period=total&units=international_system&left_color=grey&right_color=orange&left_text=Downloads\">\n </a>\n</p>\n\n<h4 align=\"center\">\n <p>\n <a href=\"#installation\">Installation</a> |\n <a href=\"#usage\">Usage</a> |\n <a href=\"https://huggingface.co/spaces/mteb/leaderboard\">Leaderboard</a> |\n <a href=\"#documentation\">Documentation</a> |\n <a href=\"#citing\">Citing</a>\n <p>\n</h4>\n\n<h3 align=\"center\">\n <a href=\"https://huggingface.co/spaces/mteb/leaderboard\"><img style=\"float: middle; padding: 10px 10px 10px 10px;\" width=\"60\" height=\"55\" src=\"./docs/images/hf_logo.png\" /></a>\n</h3>\n\n\n## Installation\n\n```bash\npip install mteb\n```\n\n## Usage\n\n* Using a python script (see [scripts/run_mteb_english.py](https://github.com/embeddings-benchmark/mteb/blob/main/scripts/run_mteb_english.py) and [mteb/mtebscripts](https://github.com/embeddings-benchmark/mtebscripts) for more):\n\n```python\nfrom mteb import MTEB\nfrom sentence_transformers import SentenceTransformer\n\n# Define the sentence-transformers model name\nmodel_name = \"average_word_embeddings_komninos\"\n# or directly from huggingface:\n# model_name = \"sentence-transformers/all-MiniLM-L6-v2\"\n\nmodel = SentenceTransformer(model_name)\nevaluation = MTEB(tasks=[\"Banking77Classification\"])\nresults = evaluation.run(model, output_folder=f\"results/{model_name}\")\n```\n\n* Using CLI\n\n```bash\nmteb --available_tasks\n\nmteb -m sentence-transformers/all-MiniLM-L6-v2 \\\n -t Banking77Classification \\\n --verbosity 3\n\n# if nothing is specified default to saving the results in the results/{model_name} folder\n```\n\n* Using multiple GPUs in parallel can be done by just having a custom encode function that distributes the inputs to multiple GPUs like e.g. [here](https://github.com/microsoft/unilm/blob/b60c741f746877293bb85eed6806736fc8fa0ffd/e5/mteb_eval.py#L60) or [here](https://github.com/ContextualAI/gritlm/blob/09d8630f0c95ac6a456354bcb6f964d7b9b6a609/gritlm/gritlm.py#L75).\n\n<br /> \n\n<details>\n <summary> Advanced Usage (click to unfold) </summary>\n\n\n## Advanced Usage\n\n\n### Dataset selection\n\nDatasets can be selected by providing the list of datasets, but also\n\n* by their task (e.g. \"Clustering\" or \"Classification\")\n\n```python\nevaluation = MTEB(task_types=['Clustering', 'Retrieval']) # Only select clustering and retrieval tasks\n```\n\n* by their categories e.g. \"S2S\" (sentence to sentence) or \"P2P\" (paragraph to paragraph)\n\n```python\nevaluation = MTEB(task_categories=['S2S']) # Only select sentence2sentence datasets\n```\n\n* by their languages\n\n```python\nevaluation = MTEB(task_langs=[\"en\", \"de\"]) # Only select datasets which are \"en\", \"de\" or \"en-de\"\n```\n\nYou can also specify which languages to load for multilingual/crosslingual tasks like below:\n\n```python\nfrom mteb.tasks import AmazonReviewsClassification, BUCCBitextMining\n\nevaluation = MTEB(tasks=[\n AmazonReviewsClassification(langs=[\"en\", \"fr\"]) # Only load \"en\" and \"fr\" subsets of Amazon Reviews\n BUCCBitextMining(langs=[\"de-en\"]), # Only load \"de-en\" subset of BUCC\n])\n```\n\nThere are also presets available for certain task collections, e.g. to select the 56 English datasets that form the \"Overall MTEB English leaderboard\":\n\n```python\nfrom mteb import MTEB_MAIN_EN\nevaluation = MTEB(tasks=MTEB_MAIN_EN, task_langs=[\"en\"])\n```\n\n\n### Evaluation split\nYou can evaluate only on `test` splits of all tasks by doing the following:\n\n```python\nevaluation.run(model, eval_splits=[\"test\"])\n```\n\nNote that the public leaderboard uses the test splits for all datasets except MSMARCO, where the \"dev\" split is used.\n\n### Using a custom model\n\nModels should implement the following interface, implementing an `encode` function taking as inputs a list of sentences, and returning a list of embeddings (embeddings can be `np.array`, `torch.tensor`, etc.). For inspiration, you can look at the [mteb/mtebscripts repo](https://github.com/embeddings-benchmark/mtebscripts) used for running diverse models via SLURM scripts for the paper.\n\n```python\nclass MyModel():\n def encode(\n self, sentences: list[str], prompt: str, **kwargs: Any\n ) -> torch.Tensor | np.ndarray:\n \"\"\"Encodes the given sentences using the encoder.\n\n Args:\n sentences: The sentences to encode.\n prompt: The prompt to use. Useful for prompt-based models.\n **kwargs: Additional arguments to pass to the encoder.\n\n Returns:\n The encoded sentences.\n \"\"\"\n pass\n\nmodel = MyModel()\nevaluation = MTEB(tasks=[\"Banking77Classification\"])\nevaluation.run(model)\n```\n\nIf you'd like to use different encoding functions for query and corpus when evaluating on Retrieval or Reranking tasks, you can add separate methods for `encode_queries` and `encode_corpus`. If these methods exist, they will be automatically used for those tasks. You can refer to the `DRESModel` at `mteb/evaluation/evaluators/RetrievalEvaluator.py` for an example of these functions.\n\n```python\nclass MyModel():\n def encode_queries(self, queries: list[str], **kwargs) -> list[np.ndarray] | list[torch.Tensor]:\n \"\"\"\n Returns a list of embeddings for the given sentences.\n Args:\n queries: List of sentences to encode\n\n Returns:\n List of embeddings for the given sentences\n \"\"\"\n pass\n\n def encode_corpus(self, corpus: list[str] | list[dict[str, str]], **kwargs) -> list[np.ndarray] | list[torch.Tensor]:\n \"\"\"\n Returns a list of embeddings for the given sentences.\n Args:\n corpus: List of sentences to encode\n or list of dictionaries with keys \"title\" and \"text\"\n\n Returns:\n List of embeddings for the given sentences\n \"\"\"\n pass\n```\n\n### Evaluating on a custom dataset\n\nTo evaluate on a custom task, you can run the following code on your custom task. See [how to add a new task](docs/adding_a_dataset.md), for how to create a new task in MTEB.\n\n```python\nfrom mteb import MTEB\nfrom mteb.abstasks.AbsTaskReranking import AbsTaskReranking\nfrom sentence_transformers import SentenceTransformer\n\n\nclass MyCustomTask(AbsTaskReranking):\n ...\n\nmodel = SentenceTransformer(\"average_word_embeddings_komninos\")\nevaluation = MTEB(tasks=[MyCustomTask()])\nevaluation.run(model)\n```\n\n</details>\n\n<br /> \n\n## Documentation\n\n| Documentation | |\n| ------------------------------ | ---------------------- |\n| \ud83d\udccb [Tasks] |\u00a0Overview of available tasks |\n| \ud83d\udcc8 [Leaderboard] | The interactive leaderboard of the benchmark |\n| \ud83e\udd16 [Adding a model] | Information related to how to submit a model to the leaderboard |\n| \ud83d\udc69\u200d\ud83d\udcbb [Adding a dataset] | How to add a new task/dataset to MTEB |\u00a0\n| \ud83d\udc69\u200d\ud83d\udcbb [Adding a leaderboard tab] | How to add a new leaderboard tab to MTEB |\u00a0\n| \ud83e\udd1d [Contributing] | How to contribute to MTEB and set it up for development |\n<!-- | \ud83c\udf10 [MMTEB] | An open-source effort to extend MTEB to cover a broad set of languages | \u00a0 -->\n\n[Tasks]: docs/tasks.md\n[Contributing]: CONTRIBUTING.md\n[Adding a model]: docs/adding_a_model.md\n[Adding a dataset]: docs/adding_a_dataset.md\n[Adding a leaderboard tab]: docs/adding_a_leaderboard_tab.md\n[Leaderboard]: https://huggingface.co/spaces/mteb/leaderboard\n[MMTEB]: docs/mmteb/readme.md\n\n## Citing\n\nMTEB was introduced in \"[MTEB: Massive Text Embedding Benchmark](https://arxiv.org/abs/2210.07316)\", feel free to cite:\n\n```bibtex\n@article{muennighoff2022mteb,\n doi = {10.48550/ARXIV.2210.07316},\n url = {https://arxiv.org/abs/2210.07316},\n author = {Muennighoff, Niklas and Tazi, Nouamane and Magne, Lo{\\\"\\i}c and Reimers, Nils},\n title = {MTEB: Massive Text Embedding Benchmark},\n publisher = {arXiv},\n journal={arXiv preprint arXiv:2210.07316}, \n year = {2022}\n}\n```\n\nYou may also want to read and cite the amazing work that has extended MTEB & integrated new datasets:\n- Shitao Xiao, Zheng Liu, Peitian Zhang, Niklas Muennighoff. \"[C-Pack: Packaged Resources To Advance General Chinese Embedding](https://arxiv.org/abs/2309.07597)\" arXiv 2023\n- Michael G\u00fcnther, Jackmin Ong, Isabelle Mohr, Alaeddine Abdessalem, Tanguy Abel, Mohammad Kalim Akram, Susana Guzman, Georgios Mastrapas, Saba Sturua, Bo Wang, Maximilian Werk, Nan Wang, Han Xiao. \"[Jina Embeddings 2: 8192-Token General-Purpose Text Embeddings for Long Documents](https://arxiv.org/abs/2310.19923)\" arXiv 2023\n- Silvan Wehrli, Bert Arnrich, Christopher Irrgang. \"[German Text Embedding Clustering Benchmark](https://arxiv.org/abs/2401.02709)\" arXiv 2024\n- Dawei Zhu, Liang Wang, Nan Yang, Yifan Song, Wenhao Wu, Furu Wei, and Sujian Li. \"[LongEmbed: Extending Embedding Models for Long Context Retrieval](https://arxiv.org/abs/2404.12096)\" arXiv 2024\n\nFor works that have used MTEB for benchmarking, you can find them on the [leaderboard](https://huggingface.co/spaces/mteb/leaderboard).\n",
"bugtrack_url": null,
"license": "Apache License Version 2.0, January 2004 http://www.apache.org/licenses/ TERMS AND CONDITIONS FOR USE, REPRODUCTION, AND DISTRIBUTION 1. Definitions. \"License\" shall mean the terms and conditions for use, reproduction, and distribution as defined by Sections 1 through 9 of this document. \"Licensor\" shall mean the copyright owner or entity authorized by the copyright owner that is granting the License. \"Legal Entity\" shall mean the union of the acting entity and all other entities that control, are controlled by, or are under common control with that entity. For the purposes of this definition, \"control\" means (i) the power, direct or indirect, to cause the direction or management of such entity, whether by contract or otherwise, or (ii) ownership of fifty percent (50%) or more of the outstanding shares, or (iii) beneficial ownership of such entity. \"You\" (or \"Your\") shall mean an individual or Legal Entity exercising permissions granted by this License. \"Source\" form shall mean the preferred form for making modifications, including but not limited to software source code, documentation source, and configuration files. \"Object\" form shall mean any form resulting from mechanical transformation or translation of a Source form, including but not limited to compiled object code, generated documentation, and conversions to other media types. \"Work\" shall mean the work of authorship, whether in Source or Object form, made available under the License, as indicated by a copyright notice that is included in or attached to the work (an example is provided in the Appendix below). \"Derivative Works\" shall mean any work, whether in Source or Object form, that is based on (or derived from) the Work and for which the editorial revisions, annotations, elaborations, or other modifications represent, as a whole, an original work of authorship. For the purposes of this License, Derivative Works shall not include works that remain separable from, or merely link (or bind by name) to the interfaces of, the Work and Derivative Works thereof. \"Contribution\" shall mean any work of authorship, including the original version of the Work and any modifications or additions to that Work or Derivative Works thereof, that is intentionally submitted to Licensor for inclusion in the Work by the copyright owner or by an individual or Legal Entity authorized to submit on behalf of the copyright owner. For the purposes of this definition, \"submitted\" means any form of electronic, verbal, or written communication sent to the Licensor or its representatives, including but not limited to communication on electronic mailing lists, source code control systems, and issue tracking systems that are managed by, or on behalf of, the Licensor for the purpose of discussing and improving the Work, but excluding communication that is conspicuously marked or otherwise designated in writing by the copyright owner as \"Not a Contribution.\" \"Contributor\" shall mean Licensor and any individual or Legal Entity on behalf of whom a Contribution has been received by Licensor and subsequently incorporated within the Work. 2. Grant of Copyright License. Subject to the terms and conditions of this License, each Contributor hereby grants to You a perpetual, worldwide, non-exclusive, no-charge, royalty-free, irrevocable copyright license to reproduce, prepare Derivative Works of, publicly display, publicly perform, sublicense, and distribute the Work and such Derivative Works in Source or Object form. 3. Grant of Patent License. Subject to the terms and conditions of this License, each Contributor hereby grants to You a perpetual, worldwide, non-exclusive, no-charge, royalty-free, irrevocable (except as stated in this section) patent license to make, have made, use, offer to sell, sell, import, and otherwise transfer the Work, where such license applies only to those patent claims licensable by such Contributor that are necessarily infringed by their Contribution(s) alone or by combination of their Contribution(s) with the Work to which such Contribution(s) was submitted. If You institute patent litigation against any entity (including a cross-claim or counterclaim in a lawsuit) alleging that the Work or a Contribution incorporated within the Work constitutes direct or contributory patent infringement, then any patent licenses granted to You under this License for that Work shall terminate as of the date such litigation is filed. 4. Redistribution. You may reproduce and distribute copies of the Work or Derivative Works thereof in any medium, with or without modifications, and in Source or Object form, provided that You meet the following conditions: (a) You must give any other recipients of the Work or Derivative Works a copy of this License; and (b) You must cause any modified files to carry prominent notices stating that You changed the files; and (c) You must retain, in the Source form of any Derivative Works that You distribute, all copyright, patent, trademark, and attribution notices from the Source form of the Work, excluding those notices that do not pertain to any part of the Derivative Works; and (d) If the Work includes a \"NOTICE\" text file as part of its distribution, then any Derivative Works that You distribute must include a readable copy of the attribution notices contained within such NOTICE file, excluding those notices that do not pertain to any part of the Derivative Works, in at least one of the following places: within a NOTICE text file distributed as part of the Derivative Works; within the Source form or documentation, if provided along with the Derivative Works; or, within a display generated by the Derivative Works, if and wherever such third-party notices normally appear. The contents of the NOTICE file are for informational purposes only and do not modify the License. You may add Your own attribution notices within Derivative Works that You distribute, alongside or as an addendum to the NOTICE text from the Work, provided that such additional attribution notices cannot be construed as modifying the License. You may add Your own copyright statement to Your modifications and may provide additional or different license terms and conditions for use, reproduction, or distribution of Your modifications, or for any such Derivative Works as a whole, provided Your use, reproduction, and distribution of the Work otherwise complies with the conditions stated in this License. 5. Submission of Contributions. Unless You explicitly state otherwise, any Contribution intentionally submitted for inclusion in the Work by You to the Licensor shall be under the terms and conditions of this License, without any additional terms or conditions. Notwithstanding the above, nothing herein shall supersede or modify the terms of any separate license agreement you may have executed with Licensor regarding such Contributions. 6. Trademarks. This License does not grant permission to use the trade names, trademarks, service marks, or product names of the Licensor, except as required for reasonable and customary use in describing the origin of the Work and reproducing the content of the NOTICE file. 7. Disclaimer of Warranty. Unless required by applicable law or agreed to in writing, Licensor provides the Work (and each Contributor provides its Contributions) on an \"AS IS\" BASIS, WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied, including, without limitation, any warranties or conditions of TITLE, NON-INFRINGEMENT, MERCHANTABILITY, or FITNESS FOR A PARTICULAR PURPOSE. You are solely responsible for determining the appropriateness of using or redistributing the Work and assume any risks associated with Your exercise of permissions under this License. 8. Limitation of Liability. In no event and under no legal theory, whether in tort (including negligence), contract, or otherwise, unless required by applicable law (such as deliberate and grossly negligent acts) or agreed to in writing, shall any Contributor be liable to You for damages, including any direct, indirect, special, incidental, or consequential damages of any character arising as a result of this License or out of the use or inability to use the Work (including but not limited to damages for loss of goodwill, work stoppage, computer failure or malfunction, or any and all other commercial damages or losses), even if such Contributor has been advised of the possibility of such damages. 9. Accepting Warranty or Additional Liability. While redistributing the Work or Derivative Works thereof, You may choose to offer, and charge a fee for, acceptance of support, warranty, indemnity, or other liability obligations and/or rights consistent with this License. However, in accepting such obligations, You may act only on Your own behalf and on Your sole responsibility, not on behalf of any other Contributor, and only if You agree to indemnify, defend, and hold each Contributor harmless for any liability incurred by, or claims asserted against, such Contributor by reason of your accepting any such warranty or additional liability. END OF TERMS AND CONDITIONS APPENDIX: How to apply the Apache License to your work. To apply the Apache License to your work, attach the following boilerplate notice, with the fields enclosed by brackets \"[]\" replaced with your own identifying information. (Don't include the brackets!) The text should be enclosed in the appropriate comment syntax for the file format. We also recommend that a file or class name and description of purpose be included on the same \"printed page\" as the copyright notice for easier identification within third-party archives. Copyright [yyyy] [name of copyright owner] Licensed under the Apache License, Version 2.0 (the \"License\"); you may not use this file except in compliance with the License. You may obtain a copy of the License at http://www.apache.org/licenses/LICENSE-2.0 Unless required by applicable law or agreed to in writing, software distributed under the License is distributed on an \"AS IS\" BASIS, WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. See the License for the specific language governing permissions and limitations under the License. ",
"summary": "Massive Text Embedding Benchmark",
"version": "1.8.7",
"project_urls": {
"Huggingface Organization": "https://huggingface.co/mteb",
"Source Code": "https://github.com/embeddings-benchmark/mteb",
"homepage": "https://github.com/embeddings-benchmark/mteb"
},
"split_keywords": [
"deep learning",
" text embeddings",
" benchmark"
],
"urls": [
{
"comment_text": "",
"digests": {
"blake2b_256": "5742a083fc7c84718c575539ab9f1dfb896b685005328fc7dad7de27a4600b4f",
"md5": "71eb5bcc80345f4eefeaafd9162b085e",
"sha256": "48aef4653f6007c1a28ad3e6a819af9c091f363a0a93c94bb34027675cdc7478"
},
"downloads": -1,
"filename": "mteb-1.8.7-py3-none-any.whl",
"has_sig": false,
"md5_digest": "71eb5bcc80345f4eefeaafd9162b085e",
"packagetype": "bdist_wheel",
"python_version": "py3",
"requires_python": ">=3.8",
"size": 1275696,
"upload_time": "2024-05-09T16:47:32",
"upload_time_iso_8601": "2024-05-09T16:47:32.082328Z",
"url": "https://files.pythonhosted.org/packages/57/42/a083fc7c84718c575539ab9f1dfb896b685005328fc7dad7de27a4600b4f/mteb-1.8.7-py3-none-any.whl",
"yanked": false,
"yanked_reason": null
},
{
"comment_text": "",
"digests": {
"blake2b_256": "d76cf7f0c5fb933ec8f6a87f72f30609b61a95fef5aad9b3828e661c9d8cf855",
"md5": "65781e9a5680e20275b424baad581ad9",
"sha256": "591bd94917520cd729b1167cfd13dbd5d548347f825afad09fddf68b0fb0c47f"
},
"downloads": -1,
"filename": "mteb-1.8.7.tar.gz",
"has_sig": false,
"md5_digest": "65781e9a5680e20275b424baad581ad9",
"packagetype": "sdist",
"python_version": "source",
"requires_python": ">=3.8",
"size": 828144,
"upload_time": "2024-05-09T16:47:35",
"upload_time_iso_8601": "2024-05-09T16:47:35.149651Z",
"url": "https://files.pythonhosted.org/packages/d7/6c/f7f0c5fb933ec8f6a87f72f30609b61a95fef5aad9b3828e661c9d8cf855/mteb-1.8.7.tar.gz",
"yanked": false,
"yanked_reason": null
}
],
"upload_time": "2024-05-09 16:47:35",
"github": true,
"gitlab": false,
"bitbucket": false,
"codeberg": false,
"github_user": "embeddings-benchmark",
"github_project": "mteb",
"travis_ci": false,
"coveralls": false,
"github_actions": true,
"lcname": "mteb"
}
