Відео

Intriguing idea. Well done, and thank you for sharing it!

Could obsidian be used as a source of knowledge when we are developing? I mainly do Android, and the LLMs knowledge is too outdated, and usually fails on the same points. I’d that knowledge could be injected somehow it would be awesome. I added the Android developers site as a source, but that site is not prepared to be scraped properly, and hardly ever finds anything useful. Thanks for the video! I also use obsidian, and this will be really helpful.

I'm not into Coding too much, just browsing various use cases and informative videos, so this might be an obvious question: Does Cursor let you use a local model or more RAG friendly model for its QA section (using 3.5 sonnet in the vid). Seems weird that the model doesn't have access to your "codebase" as a RAG database, especially if it's just text. Would be nice to be able to query the model and the database simultaneously without having to select one option or the other.

I just use msty. It lets me point to an obsidian repo, turn it into a knowledgebase and add it to chats in a friendly chat interface and do the same thing. The big difference is that it lets me use any model, it stores its chat histories, lets me bring in internet search results and generally have a lot more control over the whole interaction. For added bonus I run it on a different machine than my daily driver and I have a remote endpoint (that mirrors the openai spec) that can be called and chatted with from any machine and using whatever model is best for the task with no waste of my main machine processing.

Great content in your vid Ben. I too use Obsidian with lots of plug-ins. Itchin' to integrate Cursor as yo did. Hey what app, setting, or other tool are you using when using your pointer to move and fade out red trails as you make points on your slides. I'd like to do the same. Thanks!

Thx. I have been wanting to dive into cursor. Now this can be just the nudge since Obsidian is my daily goto.

Try this simple question "give me a recap of last week" with this approach. It doesn't know the current time so it has no idea when "last week" is, let alone knowing how to retrieve things from last week. Copilot for Obsidian can do that though. Because it became agentic since its recent update.

Why not use Ollama through an Obisidian extension?

Interesting

Obsidian plugins: - smart connections - obsidian copilot - gemini for obsidian do this all better. Smart connections establish connections between files. 🙌

Does it have a student discount?

Very cool. Powerful tool. Wish I'd consolidated my knowledge base in one place decades ago. What I need is a tool that will do that consolidation from dozens of different formats going back decades and make it all accessible.

thanks big time

If you're trying to test this out today there's unfortunately a bug with the realtime API that breaks this! Hopefully OpenAI will fix this soon: community.openai.com/t/real-time-api-not-responding-from-the-2nd-message/980614

Isn't RAG used with vectors rather than keyword matching? This makes it really costly.

super valuable! thanks for posting

super good video man, keep going! you are definitely going to get big here, you are bringing a lot of value!

Been contemplating using Obsidian + AI tools for a while now and this is so helpful! Thanks for putting this out there, ya got yourself a new sub 🙏🏼

Your video saved a lot of time. Me and my colleagues are working on a project to create a RPG(role playing game) Character Creator with AI. We intended to "train" the AI with fine tunning to give answears based on the context provided by the universe created by the game master. Based on that he would output traits, personality, backstory, tips for building a good character and more. Turns out that we would need to treat raw data to "feed" the AI for fine tunning. And I gess it would be too dificult to accomplish. I feel much more confident on giving the context of the universe as prompt cache. This would make much more sense. If I fine tuned it, I would have less creative outputs and a kind of BIAS towards its training resulting in a less interesting product. The downside is that it seems to cost much more. Thank you for the video.

Thanks for explaining in a way that's easy to understand

Good point

I’d say the solution is ordering in the answer (names and places first) or two independent queries. However, independent queries have a disadvantage- you pay twice for the input tokens (with the current on-demand pricing), which is less than desirable The advantage of independent queries is lower answer latency, though. And with cheaper models, you can often afford the double input tokens depending on the usecase

Cool but fine tuning is a necessary tool if you want to lock domain specific information that doesn't change frequently into the model while freeing up the context window for more dynamic content. An example: I want to make an AI model that generates quests in a game. For this I need to finetune the model to have the basics of the game universe and such and free up the context window to include the information that is coming from the game world, such as population of each territory, which faction controls which places, the user's location and progress, etc.

Do you use native AI note app like Mem or Saner?

You guys are producing some of the best conversations out there around AI and web development! And your speaking style is simply top notch.

Great content, and we appreciate the Pet Portal AI shout-out in the presentation! You've been incredible to work with and have really helped bring our vision to life! Love the way you break down and simplify concepts AND processes (i.e., Sanity 😊)

Thanks for your indepth explanation. It has effect.

You got yourself a new subscriber

Spot on. I'm a product designer who for the last year has switched to mostly dev. I've always done a little bit of html/css but now with Claude, I'm actually able to bypass the great divide and push front-end.... and backend code. And it's not absolutely terrible either, crazy!

Good luck iterating over the initial design/code/test :)

Very well done explaining the uses of this tool! I believe future version of it will change how we go about everything, and a big step will be the ability to visualize and interact with these connections. I wanted to let you (and whoever sees this) know that I've collaborated with Brian (Creator of Smart Connections) and released the official plugin companion: "Smart Connections Visualizer". For this first version, it's an obsidian graph view that shows relevant connections to your current note. I'll still be adding much much more to it, also with an ability to customize how you see things like no other! Give my channel a peak if you want to find out more If it's not too much, could you pin this comment to let people know about this tool to enhance their experience with SC?

If you use ChatGPT does that not just make your Obsidian notes no longer private?

This is good Working tutorial will help viewers to understand more deeply nuances and start applying the concepts learnt. And some of them will come back and enrich every one with their experience

Hello, I don't know the principle of the pipeline, I wonder how can I establish a didicated law's gpt, I just upload some pdf, and each is at about 10Mb，but I failed to let gpt answer my quetion even if the pdf are so precise.

Congratulations. There are tools like Langsmith now that can be used to show the chain used by the GPT.

This is pretty cool. Can you give a tutrial of PDF ingestion pipeline?

❤

Congratulations on the 1k subscriber milestone! Well deserved with such great content. Turning my notifications on!

Have you taken a look at Amazon Q with dev mode in an IDE yet?

🫡❤

"hallucinates a guess". I like that. 😆

There is anyway to use the GPU for this?

My vault is over 3million words across 2k+ files, all geared towards one project. I was excited to use the Co-Pilot plugin because it advertises "vault mode", but was quickly disappointed when its default reference amount was only 3 notes/files at a time (lol), and can only stretch to 10 but gives a warning that it will prolly screw up the responses. I want to communicate with my vault as a whole for perfect macro context, but it seems my case use is still not possible with current Ai? SmartConnections doesn't seem to be any better, or am I mistaken?

We had a well crafted GPT4 prompt with many tests covering our desired outputs. We took gpt35 and fine tuned it and now it's performing the same. Worked well for our use case!

dude try obsidian copilot can use ollama, with that can use dolphin mistral = it's uncensored AI so there is no guardrail, this way we can be anything creative with texts.

Almost none of this is AI.

Well done my man. Keep it up. Your content is valuable because your explainations are excellent!

Hi! Good video! I am wondering if you are using any of the openai service essentially you are not running the model locally right? Is there a local embedding and llm available for this, such as llama2 or mistral. Thanks! Awesome video.

Yes! I’m ready to upload my decades of original notes and content into Obsidian and instruct my LLM to cull through them to create new material based on my own source material. Come on, pick my brain.

Aye, very insightful, and was something I also picked up from using Stable Diffusion a lot. One thing that's helped a lot with prompting ChatGPT is the '-' dash seperator. It's a good way to make sure words are often not linked together as tokens, as 'Space Dash Space' is often just 1 seperate token in and of itself. If there are two seemingly odd words that I want to seperate in a prompt, it seems to give decent indication. I would say with json formatting, this can actually be pretty decent, as it's a clean well understood set of characters with clear meanings, [1,2,3] or whatever value is probably easily interpritable.