# contextkit
<!-- WARNING: THIS FILE WAS AUTOGENERATED! DO NOT EDIT! -->
## Usage
### Installation
pip install contextkit
### Using
To get context from an LLM, use one of the helper functions to pull it.
If a function pulls a single context snippit it will return the text, if
it return multiple it will return a dictionary.
``` python
import contextkit.read as rd
```
#### Read_X Functions
Each `read_x` function is designed to work with a single argument, which
is the location of the resource. This typically means a URL or a file
path.
``` python
rd.read_url('https://www.answer.ai/')[:200]
```
'Answer.AI\n\n * __\n * __\n\n# Answer.AI - Practical AI R&D\n\n##### Categories\n\nAll (33)\n\nai (20)\n\ncoding (5)\n\ncompany (2)\n\ncourses (1)\n\neducation (1)\n\ninterview (1)\n\nopen-source (14)\n\npolicy (4)\n\nproduct'
Other arguments are always optional, but can be useful at times. For
example, the `heavy` argument in `read_url` allows you to do a heavy
scrape with a contactless browser using `playwrightnb`.
``` python
rd.read_url('https://www.answer.ai/',heavy=True)[:200]
```
'Answer.AI\n\n * __\n * __\n\n# Answer.AI - Practical AI R&D\n\n##### Categories\n\nAll (33)\n\nai (20)\n\ncoding (5)\n\ncompany (2)\n\ncourses (1)\n\neducation (1)\n\ninterview (1)\n\nopen-source (14)\n\npolicy (4)\n\nproduct'
Many have been creates so far, such as
``` python
[o for o in dir(rd) if o.startswith('read_')]
```
['read_dir',
'read_file',
'read_gdoc',
'read_gh_file',
'read_gh_repo',
'read_gist',
'read_git_path',
'read_google_sheet',
'read_html',
'read_pdf',
'read_url',
'read_yt_transcript']
Raw data
{
"_id": null,
"home_page": "https://github.com/AnswerDotAI/contextkit",
"name": "contextkit",
"maintainer": null,
"docs_url": null,
"requires_python": ">=3.11",
"maintainer_email": null,
"keywords": "nbdev jupyter notebook python",
"author": "Isaac Flath",
"author_email": "isaac.flath@gmail.com",
"download_url": "https://files.pythonhosted.org/packages/71/c1/31a627d8eee8dc9fe9fbd6b656ca1765507034592d6aa40c38fc000a7afc/contextkit-0.0.2.tar.gz",
"platform": null,
"description": "# contextkit\n\n\n<!-- WARNING: THIS FILE WAS AUTOGENERATED! DO NOT EDIT! -->\n\n## Usage\n\n### Installation\n\n pip install contextkit\n\n### Using\n\nTo get context from an LLM, use one of the helper functions to pull it.\n\nIf a function pulls a single context snippit it will return the text, if\nit return multiple it will return a dictionary.\n\n``` python\nimport contextkit.read as rd\n```\n\n#### Read_X Functions\n\nEach `read_x` function is designed to work with a single argument, which\nis the location of the resource. This typically means a URL or a file\npath.\n\n``` python\nrd.read_url('https://www.answer.ai/')[:200]\n```\n\n 'Answer.AI\\n\\n * __\\n * __\\n\\n# Answer.AI - Practical AI R&D\\n\\n##### Categories\\n\\nAll (33)\\n\\nai (20)\\n\\ncoding (5)\\n\\ncompany (2)\\n\\ncourses (1)\\n\\neducation (1)\\n\\ninterview (1)\\n\\nopen-source (14)\\n\\npolicy (4)\\n\\nproduct'\n\nOther arguments are always optional, but can be useful at times. For\nexample, the `heavy` argument in `read_url` allows you to do a heavy\nscrape with a contactless browser using `playwrightnb`.\n\n``` python\nrd.read_url('https://www.answer.ai/',heavy=True)[:200]\n```\n\n 'Answer.AI\\n\\n * __\\n * __\\n\\n# Answer.AI - Practical AI R&D\\n\\n##### Categories\\n\\nAll (33)\\n\\nai (20)\\n\\ncoding (5)\\n\\ncompany (2)\\n\\ncourses (1)\\n\\neducation (1)\\n\\ninterview (1)\\n\\nopen-source (14)\\n\\npolicy (4)\\n\\nproduct'\n\nMany have been creates so far, such as\n\n``` python\n[o for o in dir(rd) if o.startswith('read_')]\n```\n\n ['read_dir',\n 'read_file',\n 'read_gdoc',\n 'read_gh_file',\n 'read_gh_repo',\n 'read_gist',\n 'read_git_path',\n 'read_google_sheet',\n 'read_html',\n 'read_pdf',\n 'read_url',\n 'read_yt_transcript']\n",
"bugtrack_url": null,
"license": "Apache Software License 2.0",
"summary": "Reusable contexts for LLMs",
"version": "0.0.2",
"project_urls": {
"Homepage": "https://github.com/AnswerDotAI/contextkit"
},
"split_keywords": [
"nbdev",
"jupyter",
"notebook",
"python"
],
"urls": [
{
"comment_text": "",
"digests": {
"blake2b_256": "9ff97d181276b668c7b5c4af90acf23a52c9b28d638843ef080e24636261fa9f",
"md5": "5aa72bd40c44732c2b0c2af5e329f022",
"sha256": "50bf3389b8fe258d218a6614652737442efd060ca355dd9408ea86efcd59077d"
},
"downloads": -1,
"filename": "contextkit-0.0.2-py3-none-any.whl",
"has_sig": false,
"md5_digest": "5aa72bd40c44732c2b0c2af5e329f022",
"packagetype": "bdist_wheel",
"python_version": "py3",
"requires_python": ">=3.11",
"size": 9220,
"upload_time": "2025-02-03T22:34:34",
"upload_time_iso_8601": "2025-02-03T22:34:34.678151Z",
"url": "https://files.pythonhosted.org/packages/9f/f9/7d181276b668c7b5c4af90acf23a52c9b28d638843ef080e24636261fa9f/contextkit-0.0.2-py3-none-any.whl",
"yanked": false,
"yanked_reason": null
},
{
"comment_text": "",
"digests": {
"blake2b_256": "71c131a627d8eee8dc9fe9fbd6b656ca1765507034592d6aa40c38fc000a7afc",
"md5": "415787f6bb2afafd111f8268f951229b",
"sha256": "df847aff0c537f448169906915a2b275c53522e79cf2382c75b36887d5e44894"
},
"downloads": -1,
"filename": "contextkit-0.0.2.tar.gz",
"has_sig": false,
"md5_digest": "415787f6bb2afafd111f8268f951229b",
"packagetype": "sdist",
"python_version": "source",
"requires_python": ">=3.11",
"size": 9915,
"upload_time": "2025-02-03T22:34:36",
"upload_time_iso_8601": "2025-02-03T22:34:36.346235Z",
"url": "https://files.pythonhosted.org/packages/71/c1/31a627d8eee8dc9fe9fbd6b656ca1765507034592d6aa40c38fc000a7afc/contextkit-0.0.2.tar.gz",
"yanked": false,
"yanked_reason": null
}
],
"upload_time": "2025-02-03 22:34:36",
"github": true,
"gitlab": false,
"bitbucket": false,
"codeberg": false,
"github_user": "AnswerDotAI",
"github_project": "contextkit",
"travis_ci": false,
"coveralls": false,
"github_actions": true,
"lcname": "contextkit"
}
JSON
