# QnA Builder
[](https://pypi.org/project/qna-builder/)
<p>
<img src="https://raw.githubusercontent.com/msamsami/qna-builder/main/docs/logo.jpg" alt="QnA Builder logo" width="200"/>
<br>
</p>
## Introduction
**QnA Builder** is a simple, no-code way to build chatbots in Python. It provides a similarity-based conversational dialog
engine, **QnA Bot**, which makes it easy to generate automated responses to input questions according to a set of known
conversations, i.e., question-answer pairs, stored in a ***knowledge base***. QnA Bot relies on a collection of
question-answer pairs to generate answers for new inputs.
## Install
The easiest way to install the qna-builder is by using `pip`:
```shell
pip install qna-builder
```
This library is shipped as an all-in-one module implementation with minimalistic dependencies and requirements.
## Getting started
A QnA Bot can be set up and used in four simple steps:
1. Import `QnABot` class
```python
from qnabuilder import QnABot
```
2. Initialize a bot
```python
bot = QnABot()
```
3. Fit the bot engine to a knowledge base
```python
bot.fit(kb="knowledge_base.json")
```
4. Generate answers
```python
bot.answer("Hey. What's up?")
```
`"All good. What's up with you?"`
## Algorithms
Currently, QnA Bot engine supports the following algorithms for similarity-based answer generation:
- TF-IDF Vectorization (`'tfidf'`)
- Murmurhash3 Vectorization (`'murmurhash'`)
- Count Vectorization (`'count'`)
Supported similarity metrics are as follows:
- Cosine similarity (`'cosine'`)
- Euclidean distance (`'euclidean'`)
- Manhattan distance (`'manhattan'`)
## Knowledge base editor
By calling `run_editor()` method of `QnAKnowledgeBase` class, the knowledge base editor window will open up in
your web browser and allows you to edit your knowledge base by adding, removing, or modifying questions/answers.
```python
from qnabuilder import QnAKnowledgeBase
kb = QnAKnowledgeBase('my_knowledge_base.json')
kb.run_editor()
```
Here, you can see a screenshot of the knowledge base editor:
<div style="text-align:center">
<img src="https://raw.githubusercontent.com/msamsami/qna-builder/main/docs/kb_editor.png" alt="QnA Bot Knowledge Base Editor" width="450"/>
</div>
Note that you need to install the optional requirement [streamlit](https://streamlit.io/) to be able to use the
knowledge base editor.
## Tests
To run the tests, install development requirements:
```
pip install -r requirements_dev.txt
```
Then, run pytest:
```
pytest
```
Raw data
{
"_id": null,
"home_page": "https://github.com/msamsami/qna-builder",
"name": "qna-builder",
"maintainer": "",
"docs_url": null,
"requires_python": ">=3.7",
"maintainer_email": "",
"keywords": "python,qna,qnabuilder,chat,chatbot,conversation,dialog",
"author": "Mehdi Samsami",
"author_email": "mehdisamsami@live.com",
"download_url": "https://files.pythonhosted.org/packages/15/f6/439bf873040b39bcdc353ab621c6b5e5527f190edbfa0bf8485602688b45/qna-builder-0.1.3.tar.gz",
"platform": null,
"description": "# QnA Builder\n\n\n\n\n[](https://pypi.org/project/qna-builder/)\n\n\n<p>\n<img src=\"https://raw.githubusercontent.com/msamsami/qna-builder/main/docs/logo.jpg\" alt=\"QnA Builder logo\" width=\"200\"/>\n<br>\n</p>\n\n## Introduction\n**QnA Builder** is a simple, no-code way to build chatbots in Python. It provides a similarity-based conversational dialog\nengine, **QnA Bot**, which makes it easy to generate automated responses to input questions according to a set of known\nconversations, i.e., question-answer pairs, stored in a ***knowledge base***. QnA Bot relies on a collection of\nquestion-answer pairs to generate answers for new inputs.\n\n## Install\nThe easiest way to install the qna-builder is by using `pip`:\n```shell\npip install qna-builder\n```\nThis library is shipped as an all-in-one module implementation with minimalistic dependencies and requirements.\n\n## Getting started\nA QnA Bot can be set up and used in four simple steps:\n\n1. Import `QnABot` class\n\n```python\nfrom qnabuilder import QnABot\n```\n\n2. Initialize a bot\n```python\nbot = QnABot()\n```\n\n3. Fit the bot engine to a knowledge base\n```python\nbot.fit(kb=\"knowledge_base.json\")\n```\n\n4. Generate answers\n```python\nbot.answer(\"Hey. What's up?\")\n```\n`\"All good. What's up with you?\"`\n\n## Algorithms\nCurrently, QnA Bot engine supports the following algorithms for similarity-based answer generation:\n- TF-IDF Vectorization (`'tfidf'`)\n- Murmurhash3 Vectorization (`'murmurhash'`)\n- Count Vectorization (`'count'`)\n\nSupported similarity metrics are as follows:\n- Cosine similarity (`'cosine'`)\n- Euclidean distance (`'euclidean'`)\n- Manhattan distance (`'manhattan'`)\n\n## Knowledge base editor\nBy calling `run_editor()` method of `QnAKnowledgeBase` class, the knowledge base editor window will open up in\nyour web browser and allows you to edit your knowledge base by adding, removing, or modifying questions/answers.\n\n```python\nfrom qnabuilder import QnAKnowledgeBase\n\nkb = QnAKnowledgeBase('my_knowledge_base.json')\nkb.run_editor()\n```\n\nHere, you can see a screenshot of the knowledge base editor:\n\n<div style=\"text-align:center\">\n<img src=\"https://raw.githubusercontent.com/msamsami/qna-builder/main/docs/kb_editor.png\" alt=\"QnA Bot Knowledge Base Editor\" width=\"450\"/>\n</div>\n\nNote that you need to install the optional requirement [streamlit](https://streamlit.io/) to be able to use the\nknowledge base editor.\n\n## Tests\nTo run the tests, install development requirements:\n```\npip install -r requirements_dev.txt\n```\n\nThen, run pytest:\n```\npytest\n```\n",
"bugtrack_url": null,
"license": "",
"summary": "Similarity-based conversational dialog engine for Python.",
"version": "0.1.3",
"project_urls": {
"Homepage": "https://github.com/msamsami/qna-builder"
},
"split_keywords": [
"python",
"qna",
"qnabuilder",
"chat",
"chatbot",
"conversation",
"dialog"
],
"urls": [
{
"comment_text": "",
"digests": {
"blake2b_256": "9037c48a0fe15f5fe3a54c5d95c4156dc7b86f18252a5dd22af56058e6446665",
"md5": "456e9957cfcd8aa7e209eeb5c67faa05",
"sha256": "617c039298ddf47759a8c7f657c077938348f518f2b3f7f9c58c6f302c0229b0"
},
"downloads": -1,
"filename": "qna_builder-0.1.3-py3-none-any.whl",
"has_sig": false,
"md5_digest": "456e9957cfcd8aa7e209eeb5c67faa05",
"packagetype": "bdist_wheel",
"python_version": "py3",
"requires_python": ">=3.7",
"size": 6493,
"upload_time": "2023-07-13T02:03:19",
"upload_time_iso_8601": "2023-07-13T02:03:19.888004Z",
"url": "https://files.pythonhosted.org/packages/90/37/c48a0fe15f5fe3a54c5d95c4156dc7b86f18252a5dd22af56058e6446665/qna_builder-0.1.3-py3-none-any.whl",
"yanked": false,
"yanked_reason": null
},
{
"comment_text": "",
"digests": {
"blake2b_256": "15f6439bf873040b39bcdc353ab621c6b5e5527f190edbfa0bf8485602688b45",
"md5": "26a0f696737900f6dd9744fffcabeaea",
"sha256": "a5c1c5429a54b91dd24ec85c2463a8cf8cabebd6fba3ec0f634fb1b3747b9ad9"
},
"downloads": -1,
"filename": "qna-builder-0.1.3.tar.gz",
"has_sig": false,
"md5_digest": "26a0f696737900f6dd9744fffcabeaea",
"packagetype": "sdist",
"python_version": "source",
"requires_python": ">=3.7",
"size": 6271,
"upload_time": "2023-07-13T02:03:21",
"upload_time_iso_8601": "2023-07-13T02:03:21.319471Z",
"url": "https://files.pythonhosted.org/packages/15/f6/439bf873040b39bcdc353ab621c6b5e5527f190edbfa0bf8485602688b45/qna-builder-0.1.3.tar.gz",
"yanked": false,
"yanked_reason": null
}
],
"upload_time": "2023-07-13 02:03:21",
"github": true,
"gitlab": false,
"bitbucket": false,
"codeberg": false,
"github_user": "msamsami",
"github_project": "qna-builder",
"travis_ci": false,
"coveralls": false,
"github_actions": true,
"requirements": [
{
"name": "scikit-learn",
"specs": [
[
"==",
"1.0.2"
]
]
}
],
"lcname": "qna-builder"
}
JSON
