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/
Project details
Download files
Download the file for your platform. If you're not sure which to choose, learn more about installing packages.
Source Distribution
wisdomweaver-0.3.0.tar.gz
(8.7 kB
view hashes)
Built Distribution
Close
Hashes for wisdomweaver-0.3.0-py3-none-any.whl
Algorithm | Hash digest | |
---|---|---|
SHA256 | a462209f9747a46333bfe8e262cb773eccf12c4c92827d8a8c13427cf75d5d6b |
|
MD5 | b7f55f833989933f7c5557e162007b84 |
|
BLAKE2b-256 | e16c1671628ab58ea8ab54f017e4e0eda6879162c228e87ddf7fdea38401a892 |