[](https://github.com/deepmipt/DeepPavlov/blob/master/LICENSE)
[](https://pepy.tech/project/deeppavlov)
<img align="right" height="27%" width="27%" src="https://raw.githubusercontent.com/deepmipt/DeepPavlov/master/docs/_static/deeppavlov_logo.png"/>
DeepPavlov is an open-source conversational AI library built on [PyTorch](https://pytorch.org/).
DeepPavlov is designed for
* development of production ready chat-bots and complex conversational systems,
* research in the area of NLP and, particularly, of dialog systems.
## Quick Links
* Demo [*demo.deeppavlov.ai*](https://demo.deeppavlov.ai/)
* Documentation [*docs.deeppavlov.ai*](http://docs.deeppavlov.ai/)
* Model List [*docs:features/*](http://docs.deeppavlov.ai/en/master/features/overview.html)
* Contribution Guide [*docs:contribution_guide/*](http://docs.deeppavlov.ai/en/master/devguides/contribution_guide.html)
* Issues [*github/issues/*](https://github.com/deepmipt/DeepPavlov/issues)
* Forum [*forum.deeppavlov.ai*](https://forum.deeppavlov.ai/)
* Blogs [*medium.com/deeppavlov*](https://medium.com/deeppavlov)
* Tutorials [*examples/*](https://github.com/deepmipt/DeepPavlov/tree/master/examples) and [extended colab tutorials](https://github.com/deepmipt/dp_tutorials)
* Docker Hub [*hub.docker.com/u/deeppavlov/*](https://hub.docker.com/u/deeppavlov/)
* Docker Images Documentation [*docs:docker-images/*](http://docs.deeppavlov.ai/en/master/intro/installation.html#docker-images)
Please leave us [your feedback](https://forms.gle/i64fowQmiVhMMC7f9) on how we can improve the DeepPavlov framework.
**Models**
[Named Entity Recognition](http://docs.deeppavlov.ai/en/master/features/models/ner.html) | [Intent/Sentence Classification](http://docs.deeppavlov.ai/en/master/features/models/classifiers.html) |
[Question Answering over Text (SQuAD)](http://docs.deeppavlov.ai/en/master/features/models/squad.html) | [Knowledge Base Question Answering](http://docs.deeppavlov.ai/en/master/features/models/kbqa.html)
[Sentence Similarity/Ranking](http://docs.deeppavlov.ai/en/master/features/models/neural_ranking.html) | [TF-IDF Ranking](http://docs.deeppavlov.ai/en/master/features/models/tfidf_ranking.html)
[Automatic Spelling Correction](http://docs.deeppavlov.ai/en/master/features/models/spelling_correction.html) | [Entity Linking](http://docs.deeppavlov.ai/en/master/features/models/entity_linking.html)
[Russian SuperGLUE](http://docs.deeppavlov.ai/en/master/features/models/superglue.html)
**Skills**
[Open Domain Questions Answering](http://docs.deeppavlov.ai/en/master/features/skills/odqa.html)
[Frequently Asked Questions Answering](http://docs.deeppavlov.ai/en/master/features/skills/faq.html)
**Embeddings**
[BERT embeddings for the Russian, Polish, Bulgarian, Czech, and informal English](http://docs.deeppavlov.ai/en/master/features/pretrained_vectors.html#bert)
[ELMo embeddings for the Russian language](http://docs.deeppavlov.ai/en/master/features/pretrained_vectors.html#elmo)
[FastText embeddings for the Russian language](http://docs.deeppavlov.ai/en/master/features/pretrained_vectors.html#fasttext)
**Auto ML**
[Tuning Models](http://docs.deeppavlov.ai/en/master/features/hypersearch.html)
**Integrations**
[REST API](http://docs.deeppavlov.ai/en/master/integrations/rest_api.html) | [Socket API](http://docs.deeppavlov.ai/en/master/integrations/socket_api.html)
[Amazon AWS](http://docs.deeppavlov.ai/en/master/integrations/aws_ec2.html)
## Installation
0. We support `Linux` platform, `Python 3.6`, `3.7`, `3.8` and `3.9`
* **`Python 3.5` is not supported!**
1. Create and activate a virtual environment:
* `Linux`
```
python -m venv env
source ./env/bin/activate
```
2. Install the package inside the environment:
```
pip install deeppavlov
```
## QuickStart
There is a bunch of great pre-trained NLP models in DeepPavlov. Each model is
determined by its config file.
List of models is available on
[the doc page](http://docs.deeppavlov.ai/en/master/features/overview.html) in
the `deeppavlov.configs` (Python):
```python
from deeppavlov import configs
```
When you're decided on the model (+ config file), there are two ways to train,
evaluate and infer it:
* via [Command line interface (CLI)](https://github.com/deepmipt/DeepPavlov/blob/master/#command-line-interface-cli) and
* via [Python](https://github.com/deepmipt/DeepPavlov/blob/master/#python).
#### GPU requirements
To run supported DeepPavlov models on GPU you should have [CUDA](https://developer.nvidia.com/cuda-toolkit) compatible
with used GPU and [library PyTorch version](https://github.com/deepmipt/DeepPavlov/blob/master/deeppavlov/requirements/pytorch.txt).
### Command line interface (CLI)
To get predictions from a model interactively through CLI, run
```bash
python -m deeppavlov interact <config_path> [-d]
```
* `-d` downloads required data -- pretrained model files and embeddings
(optional).
You can train it in the same simple way:
```bash
python -m deeppavlov train <config_path> [-d]
```
Dataset will be downloaded regardless of whether there was `-d` flag or not.
To train on your own data you need to modify dataset reader path in the
[train config doc](http://docs.deeppavlov.ai/en/master/intro/config_description.html#train-config).
The data format is specified in the corresponding model doc page.
There are even more actions you can perform with configs:
```bash
python -m deeppavlov <action> <config_path> [-d]
```
* `<action>` can be
* `download` to download model's data (same as `-d`),
* `train` to train the model on the data specified in the config file,
* `evaluate` to calculate metrics on the same dataset,
* `interact` to interact via CLI,
* `riseapi` to run a REST API server (see
[doc](http://docs.deeppavlov.ai/en/master/integrations/rest_api.html)),
* `predict` to get prediction for samples from *stdin* or from
*<file_path>* if `-f <file_path>` is specified.
* `<config_path>` specifies path (or name) of model's config file
* `-d` downloads required data
### Python
To get predictions from a model interactively through Python, run
```python
from deeppavlov import build_model
model = build_model(<config_path>, download=True)
# get predictions for 'input_text1', 'input_text2'
model(['input_text1', 'input_text2'])
```
* where `download=True` downloads required data from web -- pretrained model
files and embeddings (optional),
* `<config_path>` is path to the chosen model's config file (e.g.
`"deeppavlov/configs/ner/ner_ontonotes_bert_mult.json"`) or
`deeppavlov.configs` attribute (e.g.
`deeppavlov.configs.ner.ner_ontonotes_bert_mult` without quotation marks).
You can train it in the same simple way:
```python
from deeppavlov import train_model
model = train_model(<config_path>, download=True)
```
* `download=True` downloads pretrained model, therefore the pretrained
model will be, first, loaded and then train (optional).
Dataset will be downloaded regardless of whether there was ``-d`` flag or
not.
To train on your own data you need to modify dataset reader path in the
[train config doc](http://docs.deeppavlov.ai/en/master/intro/config_description.html#train-config).
The data format is specified in the corresponding model doc page.
You can also calculate metrics on the dataset specified in your config file:
```python
from deeppavlov import evaluate_model
model = evaluate_model(<config_path>, download=True)
```
## License
DeepPavlov is Apache 2.0 - licensed.
##
<p align="center">
<img src="https://raw.githubusercontent.com/deepmipt/DeepPavlov/master/docs/_static/ipavlov_footer.png" width="50%" height="50%"/>
</p>
Raw data
{
"_id": null,
"home_page": "https://github.com/deepmipt/DeepPavlov",
"name": "shallowpavlov",
"maintainer": "",
"docs_url": null,
"requires_python": "",
"maintainer_email": "",
"keywords": "NLP,NER,SQUAD,Intents,Chatbot",
"author": "Neural Networks and Deep Learning lab, MIPT",
"author_email": "info@deeppavlov.ai",
"download_url": "https://files.pythonhosted.org/packages/c9/70/862f429b7a3e8933cdd2bb332840200949a6599c040357366b6d91bb3339/shallowpavlov-0.0.2.tar.gz",
"platform": null,
"description": "[](https://github.com/deepmipt/DeepPavlov/blob/master/LICENSE)\n\n[](https://pepy.tech/project/deeppavlov)\n<img align=\"right\" height=\"27%\" width=\"27%\" src=\"https://raw.githubusercontent.com/deepmipt/DeepPavlov/master/docs/_static/deeppavlov_logo.png\"/>\n\nDeepPavlov is an open-source conversational AI library built on [PyTorch](https://pytorch.org/).\n\nDeepPavlov is designed for\n* development of production ready chat-bots and complex conversational systems,\n* research in the area of NLP and, particularly, of dialog systems.\n\n## Quick Links\n\n* Demo [*demo.deeppavlov.ai*](https://demo.deeppavlov.ai/)\n* Documentation [*docs.deeppavlov.ai*](http://docs.deeppavlov.ai/)\n * Model List [*docs:features/*](http://docs.deeppavlov.ai/en/master/features/overview.html)\n * Contribution Guide [*docs:contribution_guide/*](http://docs.deeppavlov.ai/en/master/devguides/contribution_guide.html)\n* Issues [*github/issues/*](https://github.com/deepmipt/DeepPavlov/issues)\n* Forum [*forum.deeppavlov.ai*](https://forum.deeppavlov.ai/)\n* Blogs [*medium.com/deeppavlov*](https://medium.com/deeppavlov)\n* Tutorials [*examples/*](https://github.com/deepmipt/DeepPavlov/tree/master/examples) and [extended colab tutorials](https://github.com/deepmipt/dp_tutorials)\n* Docker Hub [*hub.docker.com/u/deeppavlov/*](https://hub.docker.com/u/deeppavlov/) \n * Docker Images Documentation [*docs:docker-images/*](http://docs.deeppavlov.ai/en/master/intro/installation.html#docker-images)\n\nPlease leave us [your feedback](https://forms.gle/i64fowQmiVhMMC7f9) on how we can improve the DeepPavlov framework.\n\n**Models**\n\n[Named Entity Recognition](http://docs.deeppavlov.ai/en/master/features/models/ner.html) | [Intent/Sentence Classification](http://docs.deeppavlov.ai/en/master/features/models/classifiers.html) |\n\n[Question Answering over Text (SQuAD)](http://docs.deeppavlov.ai/en/master/features/models/squad.html) | [Knowledge Base Question Answering](http://docs.deeppavlov.ai/en/master/features/models/kbqa.html)\n\n[Sentence Similarity/Ranking](http://docs.deeppavlov.ai/en/master/features/models/neural_ranking.html) | [TF-IDF Ranking](http://docs.deeppavlov.ai/en/master/features/models/tfidf_ranking.html) \n\n[Automatic Spelling Correction](http://docs.deeppavlov.ai/en/master/features/models/spelling_correction.html) | [Entity Linking](http://docs.deeppavlov.ai/en/master/features/models/entity_linking.html)\n\n[Russian SuperGLUE](http://docs.deeppavlov.ai/en/master/features/models/superglue.html)\n\n**Skills**\n\n[Open Domain Questions Answering](http://docs.deeppavlov.ai/en/master/features/skills/odqa.html)\n\n[Frequently Asked Questions Answering](http://docs.deeppavlov.ai/en/master/features/skills/faq.html)\n\n**Embeddings**\n\n[BERT embeddings for the Russian, Polish, Bulgarian, Czech, and informal English](http://docs.deeppavlov.ai/en/master/features/pretrained_vectors.html#bert)\n\n[ELMo embeddings for the Russian language](http://docs.deeppavlov.ai/en/master/features/pretrained_vectors.html#elmo)\n\n[FastText embeddings for the Russian language](http://docs.deeppavlov.ai/en/master/features/pretrained_vectors.html#fasttext)\n\n**Auto ML**\n\n[Tuning Models](http://docs.deeppavlov.ai/en/master/features/hypersearch.html)\n\n**Integrations**\n\n[REST API](http://docs.deeppavlov.ai/en/master/integrations/rest_api.html) | [Socket API](http://docs.deeppavlov.ai/en/master/integrations/socket_api.html)\n\n[Amazon AWS](http://docs.deeppavlov.ai/en/master/integrations/aws_ec2.html)\n\n## Installation\n\n0. We support `Linux` platform, `Python 3.6`, `3.7`, `3.8` and `3.9`\n * **`Python 3.5` is not supported!**\n\n1. Create and activate a virtual environment:\n * `Linux`\n ```\n python -m venv env\n source ./env/bin/activate\n ```\n2. Install the package inside the environment:\n ```\n pip install deeppavlov\n ```\n\n## QuickStart\n\nThere is a bunch of great pre-trained NLP models in DeepPavlov. Each model is\ndetermined by its config file.\n\nList of models is available on\n[the doc page](http://docs.deeppavlov.ai/en/master/features/overview.html) in\nthe `deeppavlov.configs` (Python):\n\n```python\nfrom deeppavlov import configs\n```\n\nWhen you're decided on the model (+ config file), there are two ways to train,\nevaluate and infer it:\n\n* via [Command line interface (CLI)](https://github.com/deepmipt/DeepPavlov/blob/master/#command-line-interface-cli) and\n* via [Python](https://github.com/deepmipt/DeepPavlov/blob/master/#python).\n\n#### GPU requirements\n\nTo run supported DeepPavlov models on GPU you should have [CUDA](https://developer.nvidia.com/cuda-toolkit) compatible\nwith used GPU and [library PyTorch version](https://github.com/deepmipt/DeepPavlov/blob/master/deeppavlov/requirements/pytorch.txt).\n\n### Command line interface (CLI)\n\nTo get predictions from a model interactively through CLI, run\n\n```bash\npython -m deeppavlov interact <config_path> [-d]\n```\n\n* `-d` downloads required data -- pretrained model files and embeddings\n (optional).\n\nYou can train it in the same simple way:\n\n```bash\npython -m deeppavlov train <config_path> [-d]\n```\n\nDataset will be downloaded regardless of whether there was `-d` flag or not.\n\nTo train on your own data you need to modify dataset reader path in the\n[train config doc](http://docs.deeppavlov.ai/en/master/intro/config_description.html#train-config).\nThe data format is specified in the corresponding model doc page. \n\nThere are even more actions you can perform with configs:\n\n```bash\npython -m deeppavlov <action> <config_path> [-d]\n```\n\n* `<action>` can be\n * `download` to download model's data (same as `-d`),\n * `train` to train the model on the data specified in the config file,\n * `evaluate` to calculate metrics on the same dataset,\n * `interact` to interact via CLI,\n * `riseapi` to run a REST API server (see\n [doc](http://docs.deeppavlov.ai/en/master/integrations/rest_api.html)),\n * `predict` to get prediction for samples from *stdin* or from\n *<file_path>* if `-f <file_path>` is specified.\n* `<config_path>` specifies path (or name) of model's config file\n* `-d` downloads required data\n\n\n### Python\n\nTo get predictions from a model interactively through Python, run\n\n```python\nfrom deeppavlov import build_model\n\nmodel = build_model(<config_path>, download=True)\n\n# get predictions for 'input_text1', 'input_text2'\nmodel(['input_text1', 'input_text2'])\n```\n\n* where `download=True` downloads required data from web -- pretrained model\n files and embeddings (optional),\n* `<config_path>` is path to the chosen model's config file (e.g.\n `\"deeppavlov/configs/ner/ner_ontonotes_bert_mult.json\"`) or\n `deeppavlov.configs` attribute (e.g.\n `deeppavlov.configs.ner.ner_ontonotes_bert_mult` without quotation marks).\n\nYou can train it in the same simple way:\n\n```python\nfrom deeppavlov import train_model \n\nmodel = train_model(<config_path>, download=True)\n```\n\n* `download=True` downloads pretrained model, therefore the pretrained\nmodel will be, first, loaded and then train (optional).\n\nDataset will be downloaded regardless of whether there was ``-d`` flag or\nnot.\n\nTo train on your own data you need to modify dataset reader path in the\n[train config doc](http://docs.deeppavlov.ai/en/master/intro/config_description.html#train-config).\nThe data format is specified in the corresponding model doc page. \n\nYou can also calculate metrics on the dataset specified in your config file:\n\n```python\nfrom deeppavlov import evaluate_model \n\nmodel = evaluate_model(<config_path>, download=True)\n```\n\n\n## License\n\nDeepPavlov is Apache 2.0 - licensed.\n\n##\n\n<p align=\"center\">\n<img src=\"https://raw.githubusercontent.com/deepmipt/DeepPavlov/master/docs/_static/ipavlov_footer.png\" width=\"50%\" height=\"50%\"/>\n</p>\n",
"bugtrack_url": null,
"license": "Apache License, Version 2.0",
"summary": "An open source library for building end-to-end dialog systems and training chatbots.",
"version": "0.0.2",
"project_urls": {
"Download": "https://github.com/deepmipt/DeepPavlov/archive/1.0.0rc1.tar.gz",
"Homepage": "https://github.com/deepmipt/DeepPavlov"
},
"split_keywords": [
"nlp",
"ner",
"squad",
"intents",
"chatbot"
],
"urls": [
{
"comment_text": "",
"digests": {
"blake2b_256": "c76801dfa433447ad694863598a6ea4ce97e407e6277ee0fc9e268f8afd43a10",
"md5": "69b43e8c37eefe29131fc7ed96953bf1",
"sha256": "0d733811d8aa2b535758859997d18f1069503f6924d410454560e5f0572674db"
},
"downloads": -1,
"filename": "shallowpavlov-0.0.2-py3-none-any.whl",
"has_sig": false,
"md5_digest": "69b43e8c37eefe29131fc7ed96953bf1",
"packagetype": "bdist_wheel",
"python_version": "py3",
"requires_python": null,
"size": 460261,
"upload_time": "2023-05-20T21:23:52",
"upload_time_iso_8601": "2023-05-20T21:23:52.667043Z",
"url": "https://files.pythonhosted.org/packages/c7/68/01dfa433447ad694863598a6ea4ce97e407e6277ee0fc9e268f8afd43a10/shallowpavlov-0.0.2-py3-none-any.whl",
"yanked": false,
"yanked_reason": null
},
{
"comment_text": "",
"digests": {
"blake2b_256": "c970862f429b7a3e8933cdd2bb332840200949a6599c040357366b6d91bb3339",
"md5": "120d99bff842707a7642d37471260c9e",
"sha256": "ca52a52f25ead8f1b3b9a9b32ac516cf21e284c148805e3eb7bf6ae4bd2ee7a9"
},
"downloads": -1,
"filename": "shallowpavlov-0.0.2.tar.gz",
"has_sig": false,
"md5_digest": "120d99bff842707a7642d37471260c9e",
"packagetype": "sdist",
"python_version": "source",
"requires_python": null,
"size": 267127,
"upload_time": "2023-05-20T21:23:54",
"upload_time_iso_8601": "2023-05-20T21:23:54.683458Z",
"url": "https://files.pythonhosted.org/packages/c9/70/862f429b7a3e8933cdd2bb332840200949a6599c040357366b6d91bb3339/shallowpavlov-0.0.2.tar.gz",
"yanked": false,
"yanked_reason": null
}
],
"upload_time": "2023-05-20 21:23:54",
"github": true,
"gitlab": false,
"bitbucket": false,
"codeberg": false,
"github_user": "deepmipt",
"github_project": "DeepPavlov",
"travis_ci": false,
"coveralls": false,
"github_actions": false,
"requirements": [],
"lcname": "shallowpavlov"
}
JSON
