Wisdom indexer and generator
Project description
WisdomWeaver
This is a document question answering implementation that combines several concepts together to produce an arbitrary document question answering machine.
- Sentence Transformers: used to index text into a vector database
- Question Answering Model: used to find answers in text most likely to contain them
- ChatGPT: used to post process the answers
Getting started
pip3 install wisdomweaver
Index a directory of asciidoc files:
wisdom -v index --path /path/to/data
Search the index in interactive mode:
wisdom ask "What practice did many ancient C projects use?" --max 5 --threshold 0.2 --interactive --gpt
License
Apache 2.0
Learn Mode
- Learn techniques used in this project: https://swedishembedded.com/tag/gpt/
Download files
Download the file for your platform. If you're not sure which to choose, learn more about installing packages.
Source Distributions
No source distribution files available for this release.See tutorial on generating distribution archives.
Built Distribution
File details
Details for the file wisdomweaver-0.4.0-py3-none-any.whl.
File metadata
- Download URL: wisdomweaver-0.4.0-py3-none-any.whl
- Upload date:
- Size: 9.5 kB
- Tags: Python 3
- Uploaded using Trusted Publishing? No
- Uploaded via: twine/4.0.2 CPython/3.10.7
File hashes
| Algorithm | Hash digest | |
|---|---|---|
| SHA256 | 812cd28068d414e7eb8c36fc86d67eec1dd6b652d4a87e1ea6d14e35b39fd53b |
|
| MD5 | 3542b42616820c2d1db8c55610cc4126 |
|
| BLAKE2b-256 | 255c485ec2c27e8332d70123367ba1eb5a730fa7b95db841cfeee8eec2e5967c |
