Memacs
khoj
Our great sponsors
Memacs | khoj | |
---|---|---|
20 | 50 | |
963 | 4,786 | |
- | 6.2% | |
2.7 | 9.9 | |
3 months ago | 4 days ago | |
Python | Python | |
GNU General Public License v3.0 only | GNU Affero General Public License v3.0 |
Stars - the number of stars that a project has on GitHub. Growth - month over month growth in stars.
Activity is a relative number indicating how actively a project is being developed. Recent commits have higher weight than older ones.
For example, an activity of 9.0 indicates that a project is amongst the top 10% of the most actively developed projects that we are tracking.
Memacs
-
Show HN: Khoj – Chat Offline with Your Second Brain Using Llama 2
Might look into some of the tools like novoids Memacs. Notion here is to build tools that push feeds, history data, into Emacs. Using org in your use case with the Khoj tool, could be the "glue" you need to tie it all together. https://github.com/novoid/Memacs#readme.
-
Multi-Layered Calendars
See the whitepaper, called "What really happened on September 15th 2008? Getting The Most from Your Personal Information with Memacs"[2].
This project is now a little bit dead, but the concept of private data fusion was fantastic, and transformed my view of calendars.
Agree that calendars are a little underused in that way, and would love to see more work towards that private calendar data usage.
[1]: https://github.com/novoid/Memacs
-
Indexing and tagging files: how to do this?
Another method is used via Memacs filename module: it generates a text file with all files that start with a date- or time-stamp. This file can then be used for all sorts of workflows for retrieving files. For example, this is how I include images in my blog using lazyblorg and its "Smart tsfile Image File Search".
-
Share your folder structure
Renaming files isn't an issue any more once you've started using file file referencing methods that are not prone to changed folder paths (alternative method) or even the basic file name (by using the unchanged first part of the file name as long as it is unique among all indexed files). This way, I really don't care about broken links any more because I don´t get them. But you don't get that freedom with most PIM tools except mine, I'm afraid.
- Memacs: Visualize your (digital) life in Org-mode
-
Best practices / examples of using org attach for file management/system.
Yes. AFAIK, it is exactly how Karl Voit uses his file tags. And a lot more: https://github.com/novoid/Memacs
-
[Poll] Best software for hoarders and curators?
Memacs - a framework for integrating various data sources into Org-mode
-
Cobbling together a Resonance calendar in org-mode
https://github.com/novoid/Memacs sounds like it might be somewhat related to your goal of making a timeline of your activity.
-
Is there a good list of up-to-date data archiving tools for different websites?
Back to the original question. In order to get as much content as possible into a common format to be displayed in a common temporal view, I've created a framework that consists of some general functionality and a set of modules that deal with different input sources and formats. This project is called Memacs. You can also read a whitepaper about it.
-
How do you curate your knowledge while browsing the web?
My observation in the last few years here seem to indicate that - not many Emacs users are necessarily into Org mode and this kind of data curation, or atleast that few have very elaborate setups that they have shared. Here's some serious inspiration: https://beepb00p.xyz/myinfra.html, and AFAIK the most comprehensive example out there. For example, there's the Promnesia package by the same author (https://github.com/karlicoss/promnesia) which I used for awhile and its cool ! There's also Karl Voit's Memacs https://github.com/novoid/Memacs/ (which appears mentioned in the previous link).
khoj
-
Show HN: I made an app to use local AI as daily driver
There are already several RAG chat open source solutions available. Two that immediately come to mind are:
Danswer
https://github.com/danswer-ai/danswer
Khoj
https://github.com/khoj-ai/khoj
-
Ask HN: How do I train a custom LLM/ChatGPT on my own documents in Dec 2023?
I'm a fan of Khoj. Been using it for months. https://github.com/khoj-ai/khoj
-
You probably don’t need to fine-tune LLMs
https://github.com/khoj-ai/khoj
This is the easiest I found, on here too.
-
Show HN: Khoj – Chat Offline with Your Second Brain Using Llama 2
Thanks for the feedback. Does your machine have a GPU? 32GB CPU RAM should be enough but GPU speeds up response time.
We have fixes for the seg fault[1] and improvement to the query speed[2] that should be released by end of day today[3].
Update khoj to version 0.10.1 with pip install --upgrade khoj-assistant to see if that improves your experience.
The number of documents/pages/entries doesn't scale memory utilization as quickly and doesn't affect the search, chat response time as much
[1]: The seg fault would occur when folks sent multiple chat queries at the same time. A lock and some UX improvements fixed that
[2]: The query time improvements are done by increasing batch size, to trade-off increased memory utilization for more speed
[3]: The relevant pull request for reference: https://github.com/khoj-ai/khoj/pull/393
-
A Review: Using Llama 2 to Chat with Notes on Consumer Hardware
We recently integrated Llama 2 into Khoj. I wanted to share a short real-world evaluation of using Llama 2 for the chat with docs use-cases and hear which models have worked best for you all. The standard benchmarks (ARC, HellaSwag, MMLU etc.) are not tuned for evaluating this
- FLaNK Stack Weekly for 17 July 2023
-
An open source AI search + chat assistant for your Notion workspace
Self-host your Notion assistant using the instructions here. You'll need Python >= 3.8 to get started.
-
When will we get JARVIS?
Here's an early example: https://github.com/khoj-ai/khoj
What are some alternatives?
mycloud-restsdk-recovery-script - A script to recover files from MyCloud REST SDK Folder Structure
obsidian-smart-connections - Chat with your notes & see links to related content with AI embeddings. Use local models or 100+ via APIs like Claude, Gemini, ChatGPT & Llama 3
ArchiveBox - 🗃 Open source self-hosted web archiving. Takes URLs/browser history/bookmarks/Pocket/Pinboard/etc., saves HTML, JS, PDFs, media, and more...
ollama - Get up and running with Llama 3, Mistral, Gemma, and other large language models.
emacs-everywhere - Mirror of https://git.tecosaur.net/tec/emacs-everywhere
qdrant - Qdrant - High-performance, massive-scale Vector Database for the next generation of AI. Also available in the cloud https://cloud.qdrant.io/
monolith - ⬛️ CLI tool for saving complete web pages as a single HTML file
llama-cpp-python - Python bindings for llama.cpp
aw-watcher-window - Cross-platform window watcher (for use with ActivityWatch)
obsidian-ava - Quickly format your notes with ChatGPT in Obsidian
OrgModeClocking2Calendar - one way synchronization of your clocking (time tracking) entries from OrgMode Emacs
logseq-plugin-gpt3-openai - A plugin for GPT-3 AI assisted note taking in Logseq