khoj-assistant 0.1.5a1660451425

A natural language search engine for your personal notes, transactions and images

Khoj 🦅

A natural language search engine for your personal notes, transactions and images

Table of Contents

• Features
• Demo
  • Description
  • Analysis
• Architecture
• Setup
  • Install
  • Configure
  • Run
• Use
• Upgrade
• Troubleshoot
• Miscellaneous
• Performance
  • Query Performance
  • Indexing Performance
  • Miscellaneous
• Development
  • Setup
    • Using Pip
    • Using Docker
    • Using Conda
  • Test
• Credits

Features

• Natural: Advanced natural language understanding using Transformer based ML Models
• Local: Your personal data stays local. All search, indexing is done on your machine*
• Incremental: Incremental search for a fast, search-as-you-type experience
• Pluggable: Modular architecture makes it easy to plug in new data sources, frontends and ML models
• Multiple Sources: Search your Org-mode and Markdown notes, Beancount transactions and Photos
• Multiple Interfaces: Search using a Web Browser, Emacs or the API

Demo

https://user-images.githubusercontent.com/6413477/181664862-31565b0a-0e64-47e1-a79a-599dfc486c74.mp4

Description

• User searches for "Setup editor"
• The demo looks for the most relevant section in this readme and the khoj.el readme
• Top result is what we are looking for, the section to Install Khoj.el on Emacs

Analysis

• The results do not have any words used in the query
  • Based on the top result it seems the re-ranking model understands that Emacs is an editor?
• The results incrementally update as the query is entered
• The results are re-ranked, for better accuracy, once user is idle

Architecture

Setup

1. Install

pip install khoj-assistant

2. Configure

• Set input-files or input-filter in each relevant content-type section of khoj_sample.yml
  • Set input-directories field in content-type.image section
• Delete content-type, processor sub-sections irrelevant for your use-case

3. Run

khoj -c=config/khoj_sample.yml -vv

Loads ML model, generates embeddings and exposes API to search notes, images, transactions etc specified in config YAML

Use

• Khoj via Web
  • Open http://localhost:8000/
• Khoj via Emacs
  • Install khoj.el
  • Run M-x khoj <user-query>
• Khoj via API
  • See Khoj FastAPI Docs, Khoj FastAPI ReDocs

Upgrade

pip install --upgrade khoj-assistant

Troubleshoot

• Symptom: Errors out complaining about Tensors mismatch, null etc

  • Mitigation: Delete content-type > image section from khoj_sample.yml

• Symptom: Errors out with "Killed" in error message in Docker

  • Fix: Increase RAM available to Docker Containers in Docker Settings
  • Refer: StackOverflow Solution, Configure Resources on Docker for Mac

Miscellaneous

• The experimental chat API endpoint uses the OpenAI API
  • It is disabled by default
  • To use it add your openai-api-key to config.yml

Performance

Query performance

• Semantic search using the bi-encoder is fairly fast at <5 ms
• Reranking using the cross-encoder is slower at <2s on 15 results. Tweak top_k to tradeoff speed for accuracy of results
• Applying explicit filters is very slow currently at ~6s. This is because the filters are rudimentary. Considerable speed-ups can be achieved using indexes etc

Indexing performance

• Indexing is more strongly impacted by the size of the source data
• Indexing 100K+ line corpus of notes takes 6 minutes
• Indexing 4000+ images takes about 15 minutes and more than 8Gb of RAM
• Once https://github.com/debanjum/khoj/issues/36 is implemented, it should only take this long on first run

Miscellaneous

• Testing done on a Mac M1 and a >100K line corpus of notes
• Search, indexing on a GPU has not been tested yet

Development

Setup

Using Pip

1. Install

git clone https://github.com/debanjum/khoj && cd khoj
python3 -m venv .venv && source .venv/bin/activate
pip install -e .

2. Configure

• Set input-files or input-filter in each relevant content-type section of khoj_sample.yml
  • Set input-directories field in image content-type section
• Delete content-type, processor sub-sections irrelevant for your use-case

3. Run

khoj -c=config/khoj_sample.yml -vv

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

4. Upgrade

# To Upgrade To Latest Stable Release
# Maps to the latest tagged version of khoj on master branch
pip install --upgrade khoj-assistant

# To Upgrade To Latest Pre-Release
# Maps to the latest commit on the master branch
pip install --upgrade --pre khoj-assistant

# To Upgrade To Specific Development Release.
# Useful to test, review a PR.
# Note: khoj-assistant is published to test PyPi on creating a PR
pip install -i https://test.pypi.org/simple/ khoj-assistant==0.1.5.dev57166025766

Using Docker

1. Clone

git clone https://github.com/debanjum/khoj && cd khoj

2. Configure

• Required: Update docker-compose.yml to mount your images, (org-mode or markdown) notes and beancount directories
• Optional: Edit application configuration in khoj_docker.yml

3. Run

docker-compose up -d

Note: The first run will take time. Let it run, it's mostly not hung, just generating embeddings

4. Upgrade

docker-compose build --pull

Using Conda

1. Install Dependencies

• Install Conda [Required]
• Install Exiftool [Optional]

  sudo apt -y install libimage-exiftool-perl
  

2. Install Khoj

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

3. Configure

• Set input-files or input-filter in each relevant content-type section of khoj_sample.yml
  • Set input-directories field in image content-type section
• Delete content-type, processor sub-sections irrelevant for your use-case

4. Run

python3 -m src.main config/khoj_sample.yml -vv

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

5. Upgrade

cd khoj
git pull origin master
conda deactivate khoj
conda env update -f config/environment.yml
conda activate khoj

Test

pytest

Credits

• Multi-QA MiniLM Model, All MiniLM Model for Text Search. See SBert Documentation
• OpenAI CLIP Model for Image Search. See SBert Documentation
• Charles Cave for OrgNode Parser
• Org.js to render Org-mode results on the Web interface
• Markdown-it to render Markdown results on the Web interface
• Sven Marnach for PyExifTool