sij/khoj
1
0
Fork 0
mirror of https://github.com/khoj-ai/khoj.git synced 2025-02-17 08:04:21 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions
Mirror of khoj from Github
2381 commits 15 branches 128 tags 142 MiB
Python 50.1%
TypeScript 37.6%
Emacs Lisp 3.1%
HTML 3%
JavaScript 2.9%
Other 3.3%
Find a file
Debanjum Singh Solanky 8ca39a436c Use llama.cpp for offline chat models 
- Benefits of moving to llama-cpp-python from gpt4all:
  - Support for all GGUF format chat models
  - Support for AMD, Nvidia, Mac, Vulcan GPU machines (instead of just Vulcan, Mac)
  - Supports models with more capabilities like tools, schema
    enforcement, speculative ddecoding, image gen etc.
- Upgrade default chat model, prompt size, tokenizer for new supported
  chat models

- Load offline chat model when present on disk without requiring internet
  - Load model onto GPU if not disabled and device has GPU
  - Load model onto CPU if loading model onto GPU fails
  - Create helper function to check and load model from disk, when model
    glob is present on disk.

    `Llama.from_pretrained' needs internet to get repo info from
    HuggingFace. This isn't required, if the model is already downloaded

    Didn't find any existing HF or llama.cpp method that looked for model
    glob on disk without internet
2024-03-26 22:33:01 +05:30
.github Free space on Github workflow VM to build Khoj docker images 2024-02-06 23:37:51 +05:30
documentation Default to gpt-4-turbo-preview for chat model, extract questions actor 2024-03-14 01:22:33 +05:30
scripts Fix bump_version.sh to commit, clean-up after desktop app version bump 2023-12-22 21:42:03 +05:30
src Use llama.cpp for offline chat models 2024-03-26 22:33:01 +05:30
tests Use llama.cpp for offline chat models 2024-03-26 22:33:01 +05:30
.dockerignore Use pypi khoj to fix docker builds and dockerize github workflow 2023-02-19 01:57:01 -06:00
.gitattributes Exclude tests data file from programming stats on Github 2023-08-28 11:00:52 -07:00
.gitignore [Multi-User Part 5]: Add a production Docker file and use a gunicorn configuration with it (#514) 2023-10-26 13:15:31 -07:00
.pre-commit-config.yaml Add isort to the pre-commit configuration and apply it to the whole project (#595) 2023-12-28 18:04:02 +05:30
docker-compose.yml Set default value of KHOJ_DEBUG to False in the docker-compose file 2024-03-01 21:51:13 +05:30
Dockerfile Remove unused git dependency from Docker images 2024-02-16 17:41:09 +05:30
gunicorn-config.py [Temp] Reduce to 1 gunicorn worker 2024-03-25 16:13:04 +05:30
LICENSE Change license to GNU AGPLv3 from GNU GPLv3 2023-11-16 11:14:06 -08:00
manifest.json Release Khoj version 1.7.0 2024-03-15 00:08:32 +05:30
prod.Dockerfile Change prod docker image to use jammy, rather than nvidia base image 2024-03-25 23:09:58 +05:30
pyproject.toml Use llama.cpp for offline chat models 2024-03-26 22:33:01 +05:30
pytest.ini Move the django app into the src/khoj folder for better organization and functionality 2023-11-21 10:56:04 -08:00
README.md Add num online for Discord badge 2024-03-10 17:48:30 +05:30
versions.json Release Khoj version 1.7.0 2024-03-15 00:08:32 +05:30

README.md

Khoj Logo

test dockerize pypi Discord

An AI personal assistant for your digital brain

Khoj is an AI application to search and chat with your notes and documents.
It is open-source, self-hostable and accessible on Desktop, Emacs, Obsidian, Web and Whatsapp.
It works with pdf, markdown, org-mode, notion files and github repositories.
It can paint, search the internet and understand speech.

🔎 Search 💬 Chat
Quickly retrieve relevant documents using natural language Get answers and create content from your existing knowledge base
Does not need internet Can be configured to work without internet

Contributors

Cheers to our awesome contributors! 🎉

Made with contrib.rocks.