Skip to main content

doctalk: Dialogue agent handling queries about a given text document

Project description

doctalk

Simple Python-based query answering system with optional voice output

USAGE:

python3 -i

>>> from doctalk import run_with
>>> run_with(fname)

This ctivates dialog about document in <fname>.txt with questions in <fname>_quests.txt

It assumes Stanford Corenlp Server listening on port 9000 with all annotators in params.py started with something like:

java -mx16g -cp "stanford-corenlp-full-2018-10-05/*" edu.stanford.nlp.pipeline.StanfordCoreNLPServer 
-preload tokenize,ssplit,pos,lemma,depparse,natlog,openie

See some examples at : https://github.com/ptarau/pytalk .

Please see the install hints for stanfordnlp, that might involve torch binaries, and require anaconda on some systems.

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

doctalk-0.0.9.tar.gz (15.0 kB view hashes)

Uploaded Source

Built Distribution

doctalk-0.0.9-py3-none-any.whl (21.0 kB view hashes)

Uploaded Python 3

Supported by

AWS AWS Cloud computing and Security Sponsor Datadog Datadog Monitoring Fastly Fastly CDN Google Google Download Analytics Microsoft Microsoft PSF Sponsor Pingdom Pingdom Monitoring Sentry Sentry Error logging StatusPage StatusPage Status page