Tools to make language models a bit easier to use
Project description
toolslm
This is a work in progress…
Install
pip install toolslm
How to use
Context creation
toolslm has some helpers to make it easier to generate XML context from
files, for instance folder2ctx:
print(folder2ctx('samples', prefix=False, file_glob='*.py'))
<documents>
<document index="1">
<source>
samples/sample_core.py
</source>
<document_content>
import inspect
empty = inspect.Parameter.empty
models = 'claude-3-opus-20240229','claude-3-sonnet-20240229','claude-3-haiku-20240307'
</document_content>
</document>
</documents>
XML helpers
Many language models work well with XML inputs, but XML can be a bit clunky to work with manually. Therefore, toolslm includes a couple of more streamlined approaches for XML generation.
An XML node contains a tag, optional children, and optional attributes.
xt creates a tuple of these three things, which we will use to general
XML shortly. Attributes are passed as kwargs; since these might conflict
with reserved words in Python, you can optionally add a _ prefix and
it’ll be stripped off.
xt('x-custom', ['hi'], _class='bar')
('x-custom', ['hi'], {'class': 'bar'})
Claudette has functions defined for some common HTML elements to create
xt tuples more easily, including these:
from toolslm.xml import div,img,h1,h2,p,hr,html
a = html([
p('This is a paragraph'),
hr(),
img(src='http://example.prg'),
div([
h1('This is a header'),
h2('This is a sub-header', style='k:v'),
], _class='foo')
])
a
('html',
[('p', 'This is a paragraph', {}),
('hr', None, {}),
('img', None, {'src': 'http://example.prg'}),
('div',
[('h1', 'This is a header', {}),
('h2', 'This is a sub-header', {'style': 'k:v'})],
{'class': 'foo'})],
{})
To convert a tuple data structure created with xt and friends into
XML, use to_xml, adding the hl parameter to optionally add syntax
highlighting:
to_xml(a, hl=True)
<html>
<p>This is a paragraph</p>
<hr />
<img src="http://example.prg" />
<div class="foo">
<h1>This is a header</h1>
<h2 style="k:v">This is a sub-header</h2>
</div>
</html>
JSON doesn’t map as nicely to XML as the xt data structure, but for
simple XML trees it can be convenient. The json_to_xml function
handles that conversion:
a = dict(surname='Howard', firstnames=['Jeremy','Peter'],
address=dict(state='Queensland',country='Australia'))
print(json_to_xml(a, 'person'))
<person>
<surname>Howard</surname>
<firstnames>
<item>Jeremy</item>
<item>Peter</item>
</firstnames>
<address>
<state>Queensland</state>
<country>Australia</country>
</address>
</person>
See the xml source section for a walkthru of XML and document context
generation functionality.
Download files
Download the file for your platform. If you're not sure which to choose, learn more about installing packages.
Source Distribution
Built Distribution
File details
Details for the file toolslm-0.0.7.tar.gz.
File metadata
- Download URL: toolslm-0.0.7.tar.gz
- Upload date:
- Size: 17.4 kB
- Tags: Source
- Uploaded using Trusted Publishing? No
- Uploaded via: twine/4.0.2 CPython/3.11.8
File hashes
| Algorithm | Hash digest | |
|---|---|---|
| SHA256 | 674200c368caed88a55306ef557639726f3b8445c0c708b30a128c85cef352b4 |
|
| MD5 | 634a979b8a4d948e7b7931745b86ff59 |
|
| BLAKE2b-256 | 57d68d71bcb2e42a81c90cebcda49cde3f13bd16b80be2d3bfd36f838ad13039 |
File details
Details for the file toolslm-0.0.7-py3-none-any.whl.
File metadata
- Download URL: toolslm-0.0.7-py3-none-any.whl
- Upload date:
- Size: 16.4 kB
- Tags: Python 3
- Uploaded using Trusted Publishing? No
- Uploaded via: twine/4.0.2 CPython/3.11.8
File hashes
| Algorithm | Hash digest | |
|---|---|---|
| SHA256 | cc22bf7ac41d45b9a250e6d322a0dfe662ec82a12a7c8eac22397ba0f8ec2d26 |
|
| MD5 | 8f867ce574e6c12eff79bc9e6871a931 |
|
| BLAKE2b-256 | c7bcc46f03b62880791d34f8cc6d801217d3b808fb315b9d3ec88c75fe3eb06d |
