Mirror of khoj from Github
Find a file
2021-12-16 20:36:36 -05:00
.github/workflows Use ubuntu-latest as machine for Github Actions 2021-12-11 12:54:32 -05:00
src Use default value False for verbose parameter, and small changes 2021-12-11 14:13:14 -05:00
tests Skip Flaky Image Search Test 2021-12-12 02:15:20 -08:00
views Fix input text behavior for null/empty value fields 2021-12-04 10:45:48 -05:00
.gitignore Set up basic ui page with no functionality 2021-11-26 14:51:11 -05:00
environment.yml Fix key error model_name issue by upgrade sentence-transformers version 2021-12-11 11:58:19 -05:00
LICENSE Add Readme, License. Update .gitignore 2021-08-15 22:52:37 -07:00
README.org Fix formatting of REAMDE env dependencies 2021-12-16 20:36:31 -05:00
sample_config.yml Make conversation processor configurable 2021-11-27 18:12:01 +05:30

https://github.com/debanjum/semantic-search/actions/workflows/build.yml/badge.svg

Semantic Search

Allow natural language search on user content like notes, images, transactions using transformer based models

All data is processed locally. User can interface with semantic-search app via Emacs, API or Commandline

Dependencies

Install

git clone https://github.com/debanjum/semantic-search && cd semantic-search
conda env create -f environment.yml
conda activate semantic-search

Install Environmental Dependencies

sudo apt-get -y install libimage-exiftool-perl

Configure

Configure application search types and their underlying data source/files in sample_config.yml Use the sample_config.yml as reference

Run

Load ML model, generate embeddings and expose API to query notes, images, transactions etc specified in config YAML

python3 -m src.main -c=sample_config.yml -vv

Use

Upgrade

  cd semantic-search
  git pull origin master
  conda env update -f environment.yml
  conda activate semantic-search

Acknowledgments