obsidian-local-llm
mindforger
obsidian-local-llm | mindforger | |
---|---|---|
3 | 11 | |
100 | 2,195 | |
- | - | |
4.7 | 8.9 | |
about 1 year ago | about 2 months ago | |
TypeScript | C++ | |
MIT License | GNU General Public License v3.0 only |
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.
obsidian-local-llm
-
Show HN: I built a non-linear UI for ChatGPT
You can get the same results for free using Obsidian Canvas and one of the following plugins:
- https://github.com/zatevakhin/obsidian-local-llm
- https://github.com/MetaCorp/obsidian-augmented-canvas
- https://github.com/phasip/obsidian-canvas-llm-extender
- https://github.com/rpggio/obsidian-chat-stream
- Show HN: Reor – An AI note-taking app that runs models locally
-
Integrating a Selfhosted LLM with Obsidian
Also look at Quivr, and anythingllm. Im still looking at using obsidian with one of the llm plugins eg https://github.com/zatevakhin/obsidian-local-llm
mindforger
- Show HN: MindForger – Attention, LLM is all your note-taking app needs
-
Show HN: Reor – An AI note-taking app that runs models locally
Rear is a really interesting project with admirable goals. I believe this is just the beginning, but you have already done a great job!
I have been working on my note-taking application (https://github.com/dvorka/mindforger) for some time and wanted to go in the same direction. However, I gave up (for now). I used ggerganov/llama.cpp to host LLM models locally on a CPU-only machine with 32GB RAM, and used them for both RAG and note-taking use cases (like https://www.mindforger.com/index-200.html#llm). However, it did not work well for me - the performance was poor (high hardware utilization, long response times, failures, and crashes) and the actual responses were rarely useful (off-topic and impractical responses, hallucinations). I tried llama-2 7B with 4b quantization and a couple of similar models. Although I'm not happy about it, I switched to an online commercial LLM because it performs really well in terms of response quality, speed, and affordability. I frequently use the integrated LLM in my note-taking app as it can be used for many things.
Anyway, Reor "only" uses the locally hosted LLM in the generation phase of the RAG, which is a nicely constraint use case. I believe that a really lightweight LLM - I'm thinking about a tiny base model fine-tuned for summarization - could be the way to go (fast, non-hallucinating). I'm really curious to know if you have any suggestions or if you will have any in the future!
As for the vector DB, considering the resource-related problems I mentioned earlier, I was thinking about something similar to facebookresearch/faiss, which, unlike LanceDB, is not a fully-fledged vector DB. Have you made any experiments with similarity search projects or vector DBs? I would be interested in the trade-offs similar to small/large/hosted LLMs.
Overall, I think that both RAG with my personal notes as a corpus and a locally hosted generic purpose LLM for the use cases I mentioned above can take personal note-taking apps to a new level. This is the way! ;)
Good luck with your project!
-
MindForger 1.53.0: Kanban and Eisenhower Matrix on tags, spell check, CSV with OHE tags export and µ terminal
Please share your suggestions, ideas or constructive criticism! You may install or update from GitHubreleases or PPA.
-
MindForger 1.53.0 brings Kanban and Eisenhower Matrix on tags, spell check, CSV with OHE tags export and µ terminal
I finally managed to complete new MindForger release:
-
Forgotten program: Note taking or writing app where you can deep dive into words like a wiki, each one opening further and further to the right...
https://www.mindforger.com/NimbusnoteWikidpadBecause you mentioned writing:
-
Our new plugin Graph Analysis lets you discover hidden links in your vault with a '2nd-order backlinks pane'!
Neat, the Similarity type reminds me of MindForger's Associations feature that also displays similarity scores between your current note and other existing notes
-
But really, come on now
[Mindfrogger](https://github.com/dvorka/mindforger)
- Is there a tool to compare Github forks?
-
Personal knowledge base
Mindforger: https://github.com/dvorka/mindforger/
What are some alternatives?
obsidian-dataview - A data index and query language over Markdown files, for https://obsidian.md/.
obsidian-export - Rust library and CLI to export an Obsidian vault to regular Markdown
jan - Jan is an open source alternative to ChatGPT that runs 100% offline on your computer. Multiple engine support (llama.cpp, TensorRT-LLM)
athens - Athens is a knowledge graph for research and notetaking. Athens is open-source, private, extensible, and community-driven.
obsidian-git - Backup your Obsidian.md vault with git
logseq - A local-first, non-linear, outliner notebook for organizing and sharing your personal knowledge base. Use it to organize your todo list, to write your journals, or to record your unique life.
advanced-tables-obsidian - Improved table navigation, formatting, and manipulation in Obsidian.md
ultimatepp - U++ is a C++ cross-platform rapid application development framework focused on programmer's productivity. It includes a set of libraries (GUI, SQL, Network etc.), and integrated development environment (TheIDE).
obsidian-calendar-plugin - Simple calendar widget for Obsidian.
juCi++
obsidian-kanban - Create markdown-backed Kanban boards in Obsidian.
Joplin - Joplin - the secure note taking and to-do app with synchronisation capabilities for Windows, macOS, Linux, Android and iOS.