yaoxinbin / docwarehouse

this repo can store,deal with private docs as q/a data warehouse.

docwarehouse

This repository can store and manage private documents such as a Q/A data warehouse. #python 1.import google api,obtain 40 websites focus on involed fields. 2.import web extracted model process website data to text. 3.google translate model and translate text to local language. 4.text2vec,data filter,indexing, and embedding. 5.vector DB store and query. 6.every day for main media news for these websites data sunmary. 7.import text2voice model and can automated produce broadcast news.