contextkit 0.0.4

Reusable contexts for LLMs

contextkit

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.

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.

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.

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

[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']