Tools for working with Ollama
Project description
Matt's Ollama Tools
I needed some simple tools to make it easier to work with integrating Ollama with the real world. This is a collection of those tools.
Chunker
Sometimes you need to take a bunch of text in and then spit it out in an array of chunks. This will take in a long text and then split it into chunks of up to a defined number of words. It won't ever get sentence fragments. It will overlap each chunk by one sentence. If you have a text with a bunch of poorly written run-on sentences, this might not work.
Usage
from mattsollamatools import chunker
textchunks = chunker(text, max_words_per_chunk=110, language='spanish')
If you don't include max_words_per_chunk, it will default to 100. If you don't include language, it will default to 'english'.
Project details
Release history Release notifications | RSS feed
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
Filter files by name, interpreter, ABI, and platform.
If you're not sure about the file name format, learn more about wheel file names.
Copy a direct link to the current filters
File details
Details for the file mattsollamatools-0.0.25.tar.gz.
File metadata
- Download URL: mattsollamatools-0.0.25.tar.gz
- Upload date:
- Size: 3.1 kB
- Tags: Source
- Uploaded using Trusted Publishing? Yes
- Uploaded via: twine/4.0.2 CPython/3.11.9
File hashes
| Algorithm | Hash digest | |
|---|---|---|
| SHA256 |
9b46af73c52eb3d1656c651423ebd11da5aadce148f2931b882edb6c0031f774
|
|
| MD5 |
6179a66e4dec5bd3be41a34c9b6ce9b5
|
|
| BLAKE2b-256 |
8ddf483b56638c619b140e00102ee794869ebf858405fc46062de06c99e01e10
|
File details
Details for the file mattsollamatools-0.0.25-py3-none-any.whl.
File metadata
- Download URL: mattsollamatools-0.0.25-py3-none-any.whl
- Upload date:
- Size: 3.6 kB
- Tags: Python 3
- Uploaded using Trusted Publishing? Yes
- Uploaded via: twine/4.0.2 CPython/3.11.9
File hashes
| Algorithm | Hash digest | |
|---|---|---|
| SHA256 |
a6d32eb65217006faff58591b4187c086047f3ade998b0539d0b6807b7b13533
|
|
| MD5 |
532fdee528d14fca7d64ce0d773d2878
|
|
| BLAKE2b-256 |
2ba736590304bee11ef4fa64f2c36b49f857a633751fe7622e0af8dfa1aa0ce8
|